Optical flow evaluation results |
Statistics:
Average
SD
R0.5
R1.0
R2.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
A95 endpoint error |
avg. |
Army (Hidden texture) GT im0 im1 |
Mequon (Hidden texture) GT im0 im1 |
Schefflera (Hidden texture) GT im0 im1 |
Wooden (Hidden texture) GT im0 im1 |
Grove (Synthetic) GT im0 im1 |
Urban (Synthetic) GT im0 im1 |
Yosemite (Synthetic) GT im0 im1 |
Teddy (Stereo) GT im0 im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
RAFT-it+_RVC [198] | 5.1 | 0.16 1 | 1.15 66 | 0.08 1 | 0.34 2 | 2.00 4 | 0.28 5 | 0.42 6 | 1.38 1 | 0.23 1 | 0.06 1 | 1.63 9 | 0.06 1 | 1.81 4 | 2.51 1 | 0.57 1 | 0.24 2 | 1.72 3 | 0.17 1 | 0.16 2 | 0.24 2 | 0.15 1 | 0.78 2 | 2.82 4 | 0.47 1 |
RAFT-it [194] | 8.2 | 0.17 3 | 1.17 72 | 0.10 4 | 0.39 6 | 2.26 11 | 0.29 9 | 0.38 3 | 1.63 5 | 0.27 8 | 0.07 2 | 1.04 4 | 0.06 1 | 2.09 6 | 3.13 7 | 0.70 4 | 0.21 1 | 1.31 2 | 0.17 1 | 0.20 6 | 0.33 33 | 0.15 1 | 0.80 3 | 2.40 3 | 0.54 2 |
MS_RAFT+_RVC [195] | 14.3 | 0.17 3 | 1.18 75 | 0.09 2 | 0.71 68 | 2.18 8 | 0.71 109 | 0.40 4 | 2.09 16 | 0.31 20 | 0.08 3 | 1.40 6 | 0.07 3 | 1.80 2 | 2.93 5 | 0.70 4 | 0.28 3 | 1.12 1 | 0.19 3 | 0.15 1 | 0.23 1 | 0.15 1 | 0.69 1 | 1.82 1 | 0.55 3 |
NNF-Local [75] | 16.0 | 0.19 8 | 0.97 9 | 0.10 4 | 0.47 20 | 2.00 4 | 0.36 26 | 0.45 8 | 1.58 4 | 0.31 20 | 0.23 19 | 1.93 13 | 0.15 21 | 1.80 2 | 2.62 2 | 0.67 2 | 0.92 10 | 3.05 9 | 0.52 15 | 0.34 47 | 0.38 79 | 0.40 31 | 1.32 14 | 3.74 12 | 0.78 5 |
RAFT-TF_RVC [179] | 18.7 | 0.28 57 | 1.39 127 | 0.10 4 | 0.50 22 | 2.36 14 | 0.41 36 | 0.57 17 | 2.09 16 | 0.40 42 | 0.11 4 | 0.95 3 | 0.09 4 | 2.11 7 | 3.08 6 | 0.80 9 | 0.33 4 | 1.79 4 | 0.25 4 | 0.21 8 | 0.33 33 | 0.15 1 | 1.28 13 | 3.07 6 | 0.94 8 |
MDP-Flow2 [68] | 22.7 | 0.20 10 | 0.91 4 | 0.14 21 | 0.37 4 | 2.11 6 | 0.28 5 | 0.40 4 | 1.89 11 | 0.27 8 | 0.21 14 | 4.76 67 | 0.13 9 | 3.73 38 | 4.67 35 | 2.57 42 | 1.07 12 | 4.13 15 | 0.80 29 | 0.36 54 | 0.34 41 | 0.49 59 | 1.27 12 | 4.18 22 | 2.27 22 |
PMMST [112] | 23.2 | 0.21 14 | 0.78 1 | 0.15 30 | 0.56 34 | 1.85 2 | 0.47 49 | 0.61 23 | 1.73 8 | 0.44 51 | 0.21 14 | 1.58 8 | 0.18 36 | 2.48 9 | 3.84 9 | 1.13 14 | 1.10 16 | 2.57 5 | 0.69 19 | 0.37 64 | 0.37 69 | 0.48 55 | 1.13 8 | 3.60 8 | 1.15 12 |
NN-field [71] | 23.5 | 0.21 14 | 1.05 25 | 0.10 4 | 0.55 31 | 1.97 3 | 0.41 36 | 0.45 8 | 1.81 9 | 0.31 20 | 0.20 11 | 2.01 15 | 0.13 9 | 1.78 1 | 2.62 2 | 0.67 2 | 5.40 125 | 3.52 10 | 0.33 5 | 0.39 71 | 0.37 69 | 0.48 55 | 1.33 15 | 4.03 19 | 0.65 4 |
OFLAF [78] | 24.0 | 0.18 5 | 0.97 9 | 0.12 11 | 0.44 14 | 2.29 12 | 0.35 25 | 0.35 1 | 1.67 7 | 0.27 8 | 0.18 9 | 7.02 134 | 0.13 9 | 3.14 22 | 4.38 23 | 0.79 8 | 1.49 37 | 3.88 12 | 0.82 30 | 0.35 49 | 0.30 12 | 0.47 49 | 1.21 11 | 4.04 20 | 4.87 60 |
GMFlow_RVC [196] | 29.4 | 0.41 100 | 1.10 49 | 0.30 117 | 0.69 63 | 1.75 1 | 0.63 96 | 0.62 24 | 1.46 2 | 0.51 70 | 0.20 11 | 1.68 11 | 0.16 28 | 2.08 5 | 2.84 4 | 1.00 12 | 0.54 6 | 2.71 7 | 0.37 7 | 0.27 17 | 0.35 50 | 0.26 13 | 0.95 5 | 2.34 2 | 0.78 5 |
PRAFlow_RVC [177] | 32.8 | 0.27 53 | 1.23 88 | 0.16 38 | 0.72 72 | 2.40 16 | 0.55 74 | 0.91 56 | 2.48 27 | 0.60 77 | 0.17 8 | 6.29 106 | 0.13 9 | 2.63 10 | 3.86 10 | 1.22 17 | 0.41 5 | 2.62 6 | 0.33 5 | 0.18 3 | 0.36 61 | 0.18 6 | 1.38 16 | 3.72 10 | 1.22 13 |
CoT-AMFlow [174] | 33.8 | 0.21 14 | 0.97 9 | 0.15 30 | 0.41 9 | 2.15 7 | 0.32 17 | 0.43 7 | 2.18 21 | 0.29 15 | 0.24 22 | 6.28 105 | 0.15 21 | 3.99 55 | 4.81 45 | 3.38 73 | 1.08 13 | 4.65 32 | 0.76 23 | 0.39 71 | 0.36 61 | 0.51 63 | 1.47 20 | 4.49 28 | 4.27 49 |
NNF-EAC [101] | 35.4 | 0.22 22 | 0.98 13 | 0.15 30 | 0.44 14 | 2.49 19 | 0.32 17 | 0.51 14 | 2.43 26 | 0.29 15 | 0.30 49 | 4.28 56 | 0.17 32 | 3.44 25 | 4.48 25 | 2.00 33 | 1.76 45 | 4.14 16 | 1.09 43 | 0.40 78 | 0.37 69 | 0.49 59 | 1.82 34 | 5.75 72 | 4.09 44 |
ComponentFusion [94] | 37.6 | 0.20 10 | 1.12 58 | 0.14 21 | 0.42 12 | 2.56 22 | 0.36 26 | 0.50 13 | 2.09 16 | 0.30 18 | 0.25 29 | 4.26 55 | 0.15 21 | 4.34 71 | 5.53 105 | 3.20 68 | 1.39 30 | 4.77 41 | 1.21 47 | 0.36 54 | 0.34 41 | 0.49 59 | 1.46 19 | 4.63 31 | 3.43 36 |
UnDAF [187] | 39.1 | 0.22 22 | 1.42 132 | 0.14 21 | 0.41 9 | 2.19 9 | 0.30 13 | 0.52 15 | 2.12 19 | 0.28 11 | 0.24 22 | 6.62 119 | 0.14 17 | 3.92 48 | 4.98 56 | 2.87 53 | 1.34 25 | 4.65 32 | 0.77 25 | 0.38 68 | 0.37 69 | 0.49 59 | 1.63 24 | 4.39 26 | 4.10 45 |
WLIF-Flow [91] | 41.5 | 0.20 10 | 0.99 15 | 0.14 21 | 0.58 41 | 2.33 13 | 0.48 52 | 0.60 22 | 3.98 43 | 0.36 32 | 0.24 22 | 3.87 43 | 0.16 28 | 3.48 27 | 4.59 29 | 1.94 32 | 1.98 55 | 4.68 36 | 1.21 47 | 0.41 80 | 0.35 50 | 0.67 98 | 1.98 45 | 5.84 74 | 5.79 82 |
VCN_RVC [178] | 42.0 | 0.40 99 | 1.09 45 | 0.24 101 | 0.72 72 | 2.85 32 | 0.56 82 | 0.95 59 | 2.05 13 | 0.69 81 | 0.44 81 | 2.79 19 | 0.23 75 | 3.09 21 | 4.08 14 | 1.46 22 | 1.87 49 | 4.18 17 | 0.56 17 | 0.20 6 | 0.30 12 | 0.22 8 | 1.76 32 | 4.43 27 | 2.31 23 |
Correlation Flow [76] | 42.6 | 0.24 32 | 0.96 7 | 0.13 17 | 0.44 14 | 2.72 28 | 0.28 5 | 1.13 65 | 7.59 168 | 0.26 4 | 0.25 29 | 2.18 16 | 0.18 36 | 4.34 71 | 5.12 66 | 3.88 83 | 1.60 38 | 4.99 62 | 0.78 27 | 0.43 89 | 0.35 50 | 0.61 83 | 1.14 9 | 3.93 14 | 1.00 10 |
HAST [107] | 43.0 | 0.16 1 | 1.11 53 | 0.10 4 | 0.60 43 | 2.45 18 | 0.38 32 | 0.37 2 | 1.66 6 | 0.23 1 | 0.16 6 | 7.63 148 | 0.11 6 | 2.69 11 | 4.02 13 | 0.75 6 | 2.28 65 | 5.16 74 | 2.11 96 | 0.76 148 | 0.50 138 | 1.22 147 | 0.80 3 | 2.97 5 | 0.88 7 |
Layers++ [37] | 43.4 | 0.22 22 | 1.09 45 | 0.19 53 | 0.57 38 | 2.79 31 | 0.48 52 | 0.49 12 | 2.07 14 | 0.40 42 | 0.16 6 | 3.00 23 | 0.12 8 | 2.69 11 | 3.92 11 | 1.41 21 | 2.67 79 | 4.82 51 | 2.11 96 | 0.48 103 | 0.39 89 | 0.56 72 | 1.48 21 | 4.57 30 | 6.44 111 |
TC/T-Flow [77] | 43.5 | 0.22 22 | 0.89 3 | 0.09 2 | 0.50 22 | 3.52 76 | 0.29 9 | 0.57 17 | 4.47 57 | 0.28 11 | 0.25 29 | 6.68 120 | 0.13 9 | 4.01 59 | 5.07 63 | 2.83 51 | 0.72 7 | 4.54 25 | 0.53 16 | 0.44 93 | 0.38 79 | 0.80 125 | 1.79 33 | 5.27 51 | 5.05 64 |
MCPFlow_RVC [197] | 44.5 | 0.48 112 | 1.21 84 | 0.32 121 | 1.10 114 | 2.56 22 | 0.88 118 | 1.32 78 | 2.20 22 | 1.30 113 | 0.25 29 | 1.63 9 | 0.20 49 | 2.27 8 | 3.20 8 | 1.15 15 | 0.85 9 | 2.71 7 | 0.48 12 | 0.19 5 | 0.38 79 | 0.22 8 | 1.39 17 | 4.01 18 | 1.11 11 |
PWC-Net_RVC [143] | 45.0 | 0.43 104 | 1.13 62 | 0.25 108 | 0.73 75 | 3.56 80 | 0.55 74 | 1.26 73 | 3.18 32 | 0.69 81 | 0.25 29 | 1.94 14 | 0.16 28 | 3.39 24 | 4.45 24 | 1.82 29 | 3.08 87 | 4.62 28 | 0.99 40 | 0.18 3 | 0.33 33 | 0.16 5 | 1.40 18 | 3.93 14 | 1.32 15 |
FC-2Layers-FF [74] | 45.0 | 0.21 14 | 1.06 28 | 0.15 30 | 0.62 45 | 2.91 35 | 0.49 55 | 0.47 10 | 2.01 12 | 0.41 44 | 0.24 22 | 5.40 83 | 0.17 32 | 2.71 13 | 4.34 21 | 1.18 16 | 3.69 97 | 4.62 28 | 2.29 109 | 0.52 118 | 0.38 79 | 0.66 93 | 1.94 41 | 3.95 16 | 3.89 40 |
3DFlow [133] | 45.3 | 0.24 32 | 1.08 40 | 0.12 11 | 0.52 24 | 3.13 47 | 0.34 23 | 0.52 15 | 5.06 71 | 0.26 4 | 0.28 39 | 0.78 1 | 0.24 78 | 3.71 36 | 4.69 36 | 2.14 34 | 3.73 99 | 4.49 23 | 1.56 64 | 0.83 152 | 0.39 89 | 1.20 146 | 1.09 7 | 3.19 7 | 0.96 9 |
IROF++ [58] | 45.4 | 0.23 28 | 1.11 53 | 0.15 30 | 0.69 63 | 3.07 41 | 0.55 74 | 0.71 35 | 3.60 36 | 0.49 68 | 0.31 56 | 3.72 38 | 0.21 61 | 3.45 26 | 4.49 27 | 1.91 31 | 2.27 64 | 4.87 53 | 1.85 77 | 0.28 23 | 0.35 50 | 0.35 22 | 1.84 37 | 4.90 39 | 4.73 58 |
LME [70] | 46.3 | 0.19 8 | 1.18 75 | 0.14 21 | 0.40 8 | 2.36 14 | 0.31 14 | 1.12 64 | 4.78 61 | 2.16 127 | 0.28 39 | 4.22 54 | 0.18 36 | 3.83 41 | 4.64 33 | 3.19 67 | 1.35 27 | 5.14 71 | 1.20 46 | 0.39 71 | 0.36 61 | 0.51 63 | 1.74 30 | 4.69 33 | 4.21 47 |
HCFN [157] | 47.6 | 0.22 22 | 0.99 15 | 0.14 21 | 0.35 3 | 3.31 56 | 0.26 2 | 0.59 19 | 2.20 22 | 0.26 4 | 0.21 14 | 6.31 107 | 0.15 21 | 3.59 31 | 4.62 31 | 2.31 38 | 1.43 32 | 4.43 22 | 0.69 19 | 0.80 150 | 0.56 148 | 1.23 148 | 2.38 66 | 5.91 76 | 5.51 75 |
IIOF-NLDP [129] | 47.8 | 0.30 67 | 1.20 82 | 0.14 21 | 0.65 52 | 3.39 62 | 0.43 41 | 0.77 46 | 6.24 92 | 0.32 24 | 0.29 41 | 1.50 7 | 0.20 49 | 3.85 43 | 4.87 49 | 1.89 30 | 3.17 88 | 5.46 84 | 1.68 72 | 0.33 44 | 0.32 23 | 0.45 45 | 1.69 27 | 4.66 32 | 2.34 25 |
ProFlow_ROB [142] | 48.0 | 0.25 41 | 1.22 86 | 0.12 11 | 0.54 27 | 3.63 87 | 0.36 26 | 1.16 66 | 5.30 77 | 0.34 31 | 0.21 14 | 3.96 48 | 0.10 5 | 4.47 82 | 5.60 118 | 3.16 66 | 1.39 30 | 5.22 76 | 0.47 10 | 0.24 14 | 0.31 18 | 0.28 15 | 2.38 66 | 6.15 84 | 4.38 53 |
PH-Flow [99] | 49.9 | 0.25 41 | 1.08 40 | 0.19 53 | 0.67 60 | 2.99 39 | 0.54 68 | 0.59 19 | 2.14 20 | 0.47 64 | 0.32 58 | 6.83 125 | 0.21 61 | 2.89 16 | 4.26 17 | 1.23 18 | 1.69 40 | 3.71 11 | 1.30 50 | 0.50 110 | 0.40 98 | 0.67 98 | 1.64 25 | 4.06 21 | 4.13 46 |
PMF [73] | 50.4 | 0.24 32 | 1.20 82 | 0.12 11 | 0.55 31 | 2.53 20 | 0.36 26 | 0.73 41 | 2.07 14 | 0.33 27 | 0.23 19 | 7.68 150 | 0.16 28 | 2.88 15 | 4.18 16 | 0.81 10 | 2.19 61 | 4.86 52 | 1.77 74 | 0.57 132 | 0.69 159 | 0.88 132 | 1.16 10 | 3.64 9 | 4.75 59 |
Efficient-NL [60] | 51.0 | 0.21 14 | 1.07 35 | 0.13 17 | 0.68 61 | 2.73 29 | 0.54 68 | 0.76 43 | 5.11 73 | 0.42 46 | 0.25 29 | 4.36 57 | 0.17 32 | 3.55 28 | 4.65 34 | 1.75 26 | 13.6 145 | 4.78 43 | 2.28 106 | 0.43 89 | 0.38 79 | 0.64 86 | 1.85 38 | 3.96 17 | 2.86 29 |
nLayers [57] | 51.1 | 0.18 5 | 1.13 62 | 0.11 9 | 0.71 68 | 2.43 17 | 0.60 86 | 0.79 48 | 3.30 33 | 0.59 76 | 0.14 5 | 7.94 157 | 0.11 6 | 3.02 18 | 4.52 28 | 1.30 19 | 2.95 83 | 4.35 20 | 2.38 118 | 0.41 80 | 0.40 98 | 0.45 45 | 1.73 29 | 5.23 49 | 5.32 67 |
RNLOD-Flow [119] | 52.1 | 0.18 5 | 0.94 6 | 0.13 17 | 0.56 34 | 3.22 54 | 0.39 33 | 0.79 48 | 5.57 84 | 0.32 24 | 0.19 10 | 5.51 85 | 0.14 17 | 4.13 63 | 5.10 65 | 3.04 62 | 2.15 59 | 4.65 32 | 1.95 83 | 0.52 118 | 0.45 119 | 0.66 93 | 1.67 26 | 4.70 35 | 5.61 78 |
FESL [72] | 53.2 | 0.21 14 | 0.99 15 | 0.12 11 | 0.85 96 | 3.07 41 | 0.65 102 | 0.71 35 | 4.19 46 | 0.46 57 | 0.24 22 | 3.77 40 | 0.18 36 | 3.59 31 | 4.69 36 | 1.76 27 | 3.92 107 | 4.81 49 | 2.23 103 | 0.43 89 | 0.43 114 | 0.63 85 | 1.97 42 | 4.79 36 | 3.97 43 |
AGIF+OF [84] | 54.9 | 0.22 22 | 1.08 40 | 0.16 38 | 0.73 75 | 3.41 63 | 0.60 86 | 0.68 31 | 4.45 55 | 0.42 46 | 0.29 41 | 3.90 46 | 0.21 61 | 3.23 23 | 4.32 20 | 1.63 23 | 3.43 91 | 4.63 31 | 2.00 87 | 0.42 85 | 0.35 50 | 0.67 98 | 2.05 49 | 5.63 66 | 5.98 90 |
TC-Flow [46] | 55.3 | 0.21 14 | 0.92 5 | 0.13 17 | 0.37 4 | 3.53 77 | 0.25 1 | 0.69 34 | 5.91 87 | 0.25 3 | 0.25 29 | 6.61 118 | 0.13 9 | 4.42 78 | 5.37 82 | 3.69 77 | 1.20 22 | 5.45 83 | 0.50 13 | 0.39 71 | 0.37 69 | 0.88 132 | 2.91 82 | 6.70 99 | 6.54 122 |
ALD-Flow [66] | 55.6 | 0.20 10 | 0.96 7 | 0.11 9 | 0.43 13 | 3.49 73 | 0.32 17 | 0.76 43 | 5.29 76 | 0.29 15 | 0.21 14 | 6.51 116 | 0.13 9 | 4.62 96 | 5.54 109 | 4.19 103 | 1.14 19 | 5.03 67 | 0.47 10 | 0.42 85 | 0.37 69 | 0.80 125 | 2.48 71 | 6.03 81 | 6.25 97 |
MLDP_OF [87] | 55.9 | 0.29 65 | 1.08 40 | 0.20 69 | 0.46 18 | 2.23 10 | 0.33 20 | 0.74 42 | 5.53 83 | 0.33 27 | 0.26 37 | 6.85 126 | 0.19 44 | 3.95 50 | 4.95 54 | 2.16 35 | 1.08 13 | 4.99 62 | 0.74 22 | 0.66 142 | 0.40 98 | 1.14 143 | 2.33 64 | 5.26 50 | 2.66 27 |
EPPM w/o HM [86] | 56.1 | 0.39 95 | 1.06 28 | 0.21 80 | 0.56 34 | 2.53 20 | 0.34 23 | 0.83 53 | 4.71 59 | 0.38 39 | 0.43 78 | 4.42 58 | 0.22 70 | 3.08 20 | 4.30 19 | 1.11 13 | 2.35 72 | 4.79 46 | 1.58 66 | 0.75 144 | 0.38 79 | 1.07 138 | 1.49 22 | 4.37 23 | 5.32 67 |
LSM [39] | 56.6 | 0.24 32 | 1.02 23 | 0.19 53 | 0.65 52 | 3.08 44 | 0.52 62 | 0.72 37 | 3.97 42 | 0.43 48 | 0.33 63 | 3.60 33 | 0.20 49 | 3.70 35 | 4.69 36 | 2.45 40 | 3.76 100 | 4.77 41 | 2.29 109 | 0.51 117 | 0.34 41 | 0.66 93 | 2.17 58 | 5.39 56 | 6.15 94 |
Classic+CPF [82] | 57.2 | 0.24 32 | 1.07 35 | 0.18 50 | 0.68 61 | 3.41 63 | 0.54 68 | 0.72 37 | 4.90 63 | 0.41 44 | 0.29 41 | 4.02 49 | 0.20 49 | 3.82 40 | 4.85 48 | 2.18 36 | 4.18 110 | 4.72 39 | 2.08 95 | 0.49 105 | 0.35 50 | 0.66 93 | 1.82 34 | 5.09 45 | 5.91 86 |
CostFilter [40] | 57.2 | 0.28 57 | 1.18 75 | 0.19 53 | 0.54 27 | 2.61 26 | 0.36 26 | 0.72 37 | 1.86 10 | 0.38 39 | 0.29 41 | 6.22 104 | 0.20 49 | 3.00 17 | 4.16 15 | 0.87 11 | 2.17 60 | 4.96 60 | 1.39 56 | 0.63 138 | 0.63 157 | 1.07 138 | 1.86 39 | 5.47 60 | 5.74 79 |
CombBMOF [111] | 57.3 | 0.31 68 | 1.06 28 | 0.16 38 | 0.62 45 | 2.64 27 | 0.46 48 | 0.67 29 | 2.39 24 | 0.46 57 | 0.52 93 | 3.34 27 | 0.33 98 | 3.71 36 | 5.03 62 | 1.77 28 | 3.65 96 | 4.51 24 | 3.27 137 | 0.47 100 | 0.49 135 | 0.52 68 | 1.70 28 | 5.02 42 | 3.45 37 |
SVFilterOh [109] | 57.9 | 0.25 41 | 1.35 116 | 0.17 46 | 0.56 34 | 2.77 30 | 0.41 36 | 0.48 11 | 2.49 28 | 0.36 32 | 0.25 29 | 7.54 147 | 0.19 44 | 3.69 34 | 5.13 67 | 0.75 6 | 3.76 100 | 5.14 71 | 1.48 59 | 0.75 144 | 0.47 127 | 1.15 145 | 0.96 6 | 4.37 23 | 1.26 14 |
Sparse-NonSparse [56] | 58.2 | 0.24 32 | 1.06 28 | 0.20 69 | 0.65 52 | 3.13 47 | 0.54 68 | 0.68 31 | 4.08 45 | 0.43 48 | 0.34 66 | 3.65 36 | 0.21 61 | 3.81 39 | 4.81 45 | 2.51 41 | 3.72 98 | 4.72 39 | 2.29 109 | 0.50 110 | 0.33 33 | 0.65 90 | 2.04 47 | 5.64 68 | 6.16 95 |
ProbFlowFields [126] | 58.3 | 0.36 85 | 1.14 65 | 0.25 108 | 0.59 42 | 3.46 68 | 0.53 65 | 0.80 51 | 3.81 41 | 0.62 79 | 0.32 58 | 1.74 12 | 0.21 61 | 4.78 109 | 5.78 149 | 3.78 80 | 0.82 8 | 4.95 59 | 0.50 13 | 0.28 23 | 0.28 4 | 0.38 28 | 2.60 75 | 6.16 85 | 3.28 32 |
FlowFields+ [128] | 58.4 | 0.48 112 | 1.17 72 | 0.24 101 | 0.78 87 | 2.58 25 | 0.62 92 | 1.16 66 | 3.17 31 | 0.85 94 | 0.49 87 | 2.34 17 | 0.34 101 | 4.25 69 | 5.29 77 | 2.97 57 | 1.12 17 | 4.78 43 | 0.86 32 | 0.30 28 | 0.30 12 | 0.40 31 | 2.26 62 | 5.53 62 | 2.56 26 |
IROF-TV [53] | 58.5 | 0.25 41 | 1.23 88 | 0.19 53 | 0.71 68 | 3.17 53 | 0.55 74 | 0.79 48 | 4.71 59 | 0.45 54 | 0.39 76 | 4.60 61 | 0.23 75 | 3.97 53 | 4.88 50 | 2.57 42 | 1.89 52 | 6.80 120 | 1.56 64 | 0.27 17 | 0.32 23 | 0.34 21 | 2.08 51 | 5.76 73 | 5.97 89 |
Ramp [62] | 58.5 | 0.25 41 | 1.07 35 | 0.19 53 | 0.66 58 | 3.12 46 | 0.53 65 | 0.67 29 | 3.70 38 | 0.44 51 | 0.32 58 | 3.63 35 | 0.20 49 | 3.95 50 | 4.83 47 | 2.60 46 | 3.80 103 | 4.78 43 | 2.29 109 | 0.50 110 | 0.38 79 | 0.69 109 | 2.10 53 | 4.69 33 | 5.27 65 |
JOF [136] | 59.1 | 0.21 14 | 1.13 62 | 0.15 30 | 0.70 67 | 3.13 47 | 0.55 74 | 0.59 19 | 2.80 29 | 0.47 64 | 0.29 41 | 5.45 84 | 0.19 44 | 2.86 14 | 4.00 12 | 1.35 20 | 2.39 74 | 4.56 26 | 2.06 93 | 0.71 143 | 0.48 131 | 0.99 136 | 1.89 40 | 5.84 74 | 5.77 81 |
FMOF [92] | 59.8 | 0.23 28 | 0.99 15 | 0.18 50 | 0.75 80 | 3.31 56 | 0.60 86 | 0.62 24 | 3.02 30 | 0.43 48 | 0.29 41 | 3.77 40 | 0.20 49 | 3.96 52 | 4.78 43 | 1.69 25 | 4.72 117 | 4.81 49 | 2.14 100 | 0.49 105 | 0.35 50 | 0.71 117 | 2.72 79 | 5.97 79 | 5.50 73 |
NL-TV-NCC [25] | 60.0 | 0.28 57 | 1.12 58 | 0.16 38 | 0.63 48 | 3.28 55 | 0.39 33 | 0.78 47 | 6.29 94 | 0.30 18 | 0.30 49 | 3.60 33 | 0.21 61 | 3.97 53 | 4.88 50 | 3.23 69 | 5.50 126 | 5.64 89 | 1.75 73 | 0.47 100 | 0.34 41 | 0.70 111 | 2.25 61 | 5.36 54 | 2.04 21 |
Classic+NL [31] | 60.2 | 0.25 41 | 1.09 45 | 0.20 69 | 0.66 58 | 3.15 50 | 0.51 58 | 0.68 31 | 4.28 49 | 0.46 57 | 0.34 66 | 3.70 37 | 0.22 70 | 3.55 28 | 4.59 29 | 2.29 37 | 3.76 100 | 4.67 35 | 2.30 114 | 0.52 118 | 0.39 89 | 0.66 93 | 2.04 47 | 4.96 41 | 5.83 83 |
TV-L1-MCT [64] | 60.3 | 0.24 32 | 1.09 45 | 0.20 69 | 0.78 87 | 3.45 67 | 0.62 92 | 0.86 54 | 5.03 68 | 0.46 57 | 0.27 38 | 3.48 31 | 0.20 49 | 3.92 48 | 4.94 53 | 3.06 63 | 4.00 109 | 4.80 48 | 2.05 90 | 0.33 44 | 0.32 23 | 0.64 86 | 2.47 70 | 5.20 47 | 5.59 77 |
COFM [59] | 60.4 | 0.23 28 | 1.28 102 | 0.16 38 | 0.55 31 | 3.02 40 | 0.40 35 | 1.27 74 | 4.99 67 | 0.48 67 | 0.23 19 | 7.47 143 | 0.14 17 | 4.36 74 | 5.28 75 | 4.20 104 | 1.75 43 | 4.98 61 | 1.37 55 | 0.49 105 | 0.35 50 | 0.72 118 | 1.50 23 | 4.54 29 | 4.36 52 |
S2F-IF [121] | 61.2 | 0.46 110 | 1.19 80 | 0.23 91 | 0.74 78 | 3.08 44 | 0.57 85 | 1.09 63 | 3.74 39 | 0.78 89 | 0.48 86 | 3.19 26 | 0.32 97 | 4.51 83 | 5.40 86 | 3.90 87 | 1.13 18 | 4.91 55 | 0.82 30 | 0.32 40 | 0.32 23 | 0.44 44 | 2.11 54 | 4.89 38 | 2.32 24 |
OAR-Flow [123] | 61.4 | 0.26 49 | 1.11 53 | 0.14 21 | 0.73 75 | 4.65 137 | 0.44 44 | 1.58 86 | 6.32 95 | 0.47 64 | 0.36 71 | 6.57 117 | 0.13 9 | 4.73 104 | 5.63 120 | 4.10 98 | 1.19 20 | 5.01 65 | 0.42 8 | 0.27 17 | 0.32 23 | 0.42 36 | 2.31 63 | 5.41 57 | 3.90 41 |
MDP-Flow [26] | 61.8 | 0.28 57 | 1.00 20 | 0.22 85 | 0.54 27 | 2.56 22 | 0.49 55 | 0.72 37 | 2.40 25 | 0.56 75 | 0.38 75 | 5.14 74 | 0.24 78 | 3.85 43 | 4.78 43 | 2.95 55 | 2.29 67 | 4.68 36 | 1.83 75 | 0.37 64 | 0.37 69 | 0.47 49 | 4.44 117 | 8.33 123 | 6.47 113 |
OFH [38] | 62.6 | 0.31 68 | 0.97 9 | 0.23 91 | 0.49 21 | 3.57 81 | 0.29 9 | 1.68 90 | 6.87 113 | 0.33 27 | 0.31 56 | 7.52 146 | 0.15 21 | 4.62 96 | 5.44 91 | 4.26 106 | 1.36 29 | 6.26 109 | 0.68 18 | 0.30 28 | 0.33 33 | 0.39 30 | 2.93 83 | 6.20 87 | 4.92 61 |
FlowFields [108] | 62.8 | 0.48 112 | 1.18 75 | 0.24 101 | 0.77 84 | 2.87 33 | 0.62 92 | 1.17 68 | 3.79 40 | 0.85 94 | 0.49 87 | 3.12 25 | 0.33 98 | 4.45 79 | 5.33 81 | 3.53 74 | 1.19 20 | 4.94 57 | 0.86 32 | 0.32 40 | 0.31 18 | 0.41 33 | 2.49 72 | 5.61 65 | 2.75 28 |
C-RAFT_RVC [181] | 64.6 | 0.77 141 | 1.29 105 | 0.37 126 | 1.56 124 | 3.16 52 | 1.25 129 | 1.57 85 | 3.60 36 | 1.45 117 | 0.51 91 | 3.87 43 | 0.40 110 | 3.58 30 | 4.34 21 | 2.59 45 | 1.09 15 | 4.26 18 | 0.97 37 | 0.34 47 | 0.38 79 | 0.43 38 | 1.74 30 | 3.85 13 | 1.51 18 |
Sparse Occlusion [54] | 64.8 | 0.24 32 | 1.01 22 | 0.18 50 | 0.62 45 | 2.87 33 | 0.54 68 | 0.93 58 | 6.27 93 | 0.38 39 | 0.30 49 | 5.16 75 | 0.21 61 | 4.14 64 | 5.21 71 | 3.08 64 | 1.70 41 | 4.62 28 | 1.31 51 | 0.60 136 | 0.62 155 | 0.68 105 | 2.46 69 | 5.70 70 | 5.56 76 |
LiteFlowNet [138] | 71.2 | 0.56 130 | 1.33 113 | 0.31 120 | 0.90 99 | 3.33 58 | 0.66 103 | 1.31 77 | 4.34 52 | 0.78 89 | 0.50 90 | 2.50 18 | 0.26 82 | 4.27 70 | 5.18 69 | 3.28 70 | 2.13 58 | 4.70 38 | 0.77 25 | 0.24 14 | 0.40 98 | 0.29 17 | 2.65 77 | 5.94 78 | 4.99 63 |
DPOF [18] | 71.4 | 0.43 104 | 1.12 58 | 0.19 53 | 0.90 99 | 3.38 61 | 0.56 82 | 0.76 43 | 1.50 3 | 0.55 73 | 0.46 83 | 3.50 32 | 0.36 103 | 3.07 19 | 4.29 18 | 1.64 24 | 9.19 138 | 7.16 127 | 2.59 125 | 0.93 155 | 0.40 98 | 1.36 151 | 1.82 34 | 3.73 11 | 1.68 19 |
PBOFVI [189] | 71.4 | 0.26 49 | 1.35 116 | 0.20 69 | 0.46 18 | 3.85 107 | 0.31 14 | 0.92 57 | 8.03 190 | 0.26 4 | 0.20 11 | 3.72 38 | 0.15 21 | 4.38 75 | 5.23 73 | 4.14 100 | 5.19 124 | 4.93 56 | 1.32 52 | 0.47 100 | 0.47 127 | 0.65 90 | 2.07 50 | 5.93 77 | 6.16 95 |
HBM-GC [103] | 71.4 | 0.28 57 | 1.33 113 | 0.20 69 | 0.63 48 | 3.44 65 | 0.55 74 | 0.62 24 | 5.03 68 | 0.46 57 | 0.33 63 | 4.59 60 | 0.28 85 | 3.99 55 | 4.98 56 | 2.68 47 | 2.71 80 | 4.10 14 | 0.72 21 | 0.64 139 | 0.42 110 | 0.90 134 | 2.20 59 | 6.62 97 | 6.50 119 |
2DHMM-SAS [90] | 72.0 | 0.25 41 | 1.07 35 | 0.19 53 | 0.76 82 | 3.63 87 | 0.55 74 | 1.29 75 | 6.70 108 | 0.52 71 | 0.34 66 | 4.11 50 | 0.22 70 | 3.88 45 | 4.73 40 | 2.58 44 | 4.27 113 | 4.88 54 | 1.97 85 | 0.50 110 | 0.40 98 | 0.68 105 | 2.35 65 | 5.70 70 | 5.95 87 |
Complementary OF [21] | 72.9 | 0.32 72 | 1.04 24 | 0.22 85 | 0.41 9 | 3.36 60 | 0.26 2 | 0.82 52 | 4.95 65 | 0.37 37 | 0.32 58 | 6.71 121 | 0.21 61 | 5.20 139 | 5.66 124 | 5.72 153 | 24.5 164 | 5.71 91 | 0.91 35 | 0.33 44 | 0.32 23 | 0.55 71 | 3.10 89 | 6.16 85 | 5.88 85 |
WRT [146] | 73.0 | 0.31 68 | 1.23 88 | 0.14 21 | 0.79 91 | 3.89 112 | 0.53 65 | 4.25 140 | 7.48 163 | 0.36 32 | 0.29 41 | 0.80 2 | 0.25 80 | 3.91 46 | 4.75 41 | 3.03 61 | 22.1 161 | 5.59 87 | 1.89 78 | 0.45 95 | 0.34 41 | 0.70 111 | 2.09 52 | 5.05 44 | 3.16 31 |
S2D-Matching [83] | 73.3 | 0.24 32 | 1.35 116 | 0.20 69 | 0.65 52 | 3.62 85 | 0.51 58 | 1.29 75 | 6.38 97 | 0.44 51 | 0.30 49 | 3.45 30 | 0.20 49 | 4.17 66 | 5.29 77 | 2.86 52 | 4.25 112 | 4.79 46 | 2.29 109 | 0.54 127 | 0.39 89 | 0.70 111 | 1.97 42 | 5.09 45 | 6.52 121 |
SRR-TVOF-NL [89] | 74.0 | 0.34 79 | 1.12 58 | 0.20 69 | 1.01 107 | 3.98 119 | 0.54 68 | 1.74 92 | 5.48 81 | 0.79 91 | 0.36 71 | 3.43 29 | 0.22 70 | 4.23 68 | 4.95 54 | 4.73 115 | 1.47 34 | 4.33 19 | 1.43 57 | 0.52 118 | 0.51 139 | 0.70 111 | 2.16 56 | 4.37 23 | 4.23 48 |
ACK-Prior [27] | 74.2 | 0.27 53 | 0.98 13 | 0.20 69 | 0.44 14 | 2.96 37 | 0.29 9 | 0.63 28 | 4.42 54 | 0.28 11 | 0.24 22 | 5.07 72 | 0.18 36 | 4.46 81 | 5.22 72 | 4.13 99 | 23.3 163 | 6.26 109 | 3.16 136 | 0.83 152 | 0.57 150 | 1.12 142 | 4.06 105 | 6.70 99 | 4.42 54 |
SegFlow [156] | 74.4 | 0.48 112 | 1.24 94 | 0.23 91 | 0.78 87 | 3.70 96 | 0.63 96 | 1.22 71 | 4.34 52 | 0.87 97 | 0.57 99 | 5.77 94 | 0.30 92 | 4.58 91 | 5.47 95 | 4.01 93 | 1.83 46 | 5.04 68 | 1.52 62 | 0.30 28 | 0.29 7 | 0.43 38 | 2.22 60 | 5.45 59 | 4.67 57 |
FF++_ROB [141] | 74.7 | 0.50 121 | 1.30 110 | 0.23 91 | 0.79 91 | 3.44 65 | 0.63 96 | 1.40 80 | 5.03 68 | 0.91 103 | 0.51 91 | 2.87 21 | 0.33 98 | 4.39 76 | 5.28 75 | 3.31 71 | 1.47 34 | 4.94 57 | 0.98 39 | 0.31 36 | 0.32 23 | 0.45 45 | 2.41 68 | 6.45 92 | 7.14 141 |
AggregFlow [95] | 74.8 | 0.34 79 | 1.48 139 | 0.17 46 | 0.94 105 | 4.38 127 | 0.60 86 | 1.65 89 | 5.13 74 | 1.01 106 | 0.30 49 | 6.85 126 | 0.20 49 | 4.45 79 | 5.53 105 | 3.36 72 | 1.04 11 | 4.58 27 | 0.46 9 | 0.35 49 | 0.42 110 | 0.47 49 | 2.50 73 | 5.60 64 | 5.50 73 |
PGM-C [118] | 74.9 | 0.48 112 | 1.24 94 | 0.23 91 | 0.77 84 | 3.62 85 | 0.63 96 | 1.23 72 | 4.33 51 | 0.87 97 | 0.56 96 | 5.51 85 | 0.30 92 | 4.58 91 | 5.49 100 | 3.87 82 | 1.48 36 | 5.50 85 | 1.34 53 | 0.30 28 | 0.29 7 | 0.43 38 | 2.65 77 | 6.11 83 | 4.96 62 |
Occlusion-TV-L1 [63] | 75.5 | 0.27 53 | 1.08 40 | 0.16 38 | 0.61 44 | 3.58 83 | 0.47 49 | 2.20 109 | 7.85 179 | 0.45 54 | 0.32 58 | 5.18 77 | 0.17 32 | 4.60 94 | 5.43 89 | 3.95 89 | 2.33 71 | 6.22 107 | 2.14 100 | 0.27 17 | 0.34 41 | 0.28 15 | 5.04 123 | 8.77 133 | 6.49 116 |
ROF-ND [105] | 76.1 | 0.38 90 | 1.16 70 | 0.21 80 | 0.91 102 | 3.47 70 | 0.33 20 | 0.95 59 | 6.42 99 | 0.32 24 | 0.43 78 | 1.11 5 | 0.37 104 | 4.34 71 | 5.20 70 | 4.09 97 | 2.35 72 | 5.23 77 | 1.91 79 | 0.62 137 | 0.44 117 | 0.79 122 | 3.43 97 | 5.34 53 | 3.34 34 |
ResPWCR_ROB [140] | 77.1 | 0.54 127 | 1.18 75 | 0.39 131 | 1.01 107 | 2.95 36 | 0.81 114 | 1.55 84 | 4.04 44 | 1.15 110 | 0.73 112 | 2.84 20 | 0.52 121 | 3.68 33 | 4.48 25 | 2.90 54 | 3.59 95 | 5.01 65 | 2.39 120 | 0.36 54 | 0.37 69 | 0.51 63 | 2.83 80 | 5.58 63 | 4.27 49 |
ComplOF-FED-GPU [35] | 77.2 | 0.32 72 | 1.00 20 | 0.19 53 | 0.69 63 | 3.71 98 | 0.31 14 | 0.98 61 | 5.10 72 | 0.36 32 | 0.35 69 | 6.81 123 | 0.18 36 | 4.60 94 | 5.43 89 | 4.17 102 | 12.7 143 | 6.78 119 | 1.36 54 | 0.44 93 | 0.36 61 | 0.82 127 | 3.18 92 | 6.56 95 | 5.43 71 |
TCOF [69] | 77.4 | 0.34 79 | 1.06 28 | 0.19 53 | 0.71 68 | 3.50 74 | 0.51 58 | 1.88 96 | 7.86 182 | 0.87 97 | 0.64 102 | 4.88 68 | 0.59 128 | 4.59 93 | 5.39 85 | 4.34 108 | 2.28 65 | 4.41 21 | 2.05 90 | 0.38 68 | 0.39 89 | 0.57 77 | 1.97 42 | 4.87 37 | 4.27 49 |
CompactFlow_ROB [155] | 78.1 | 0.78 142 | 1.47 138 | 0.42 134 | 1.32 118 | 3.48 71 | 1.07 122 | 2.19 108 | 4.21 48 | 2.27 133 | 0.71 109 | 2.93 22 | 0.48 114 | 4.04 61 | 4.76 42 | 2.96 56 | 1.68 39 | 5.14 71 | 1.59 68 | 0.23 12 | 0.30 12 | 0.20 7 | 3.37 96 | 5.98 80 | 5.43 71 |
CPM-Flow [114] | 78.5 | 0.48 112 | 1.25 99 | 0.23 91 | 0.78 87 | 3.67 93 | 0.63 96 | 1.21 70 | 4.28 49 | 0.87 97 | 0.55 95 | 5.69 91 | 0.30 92 | 4.55 87 | 5.47 95 | 3.79 81 | 1.93 54 | 5.05 69 | 1.51 61 | 0.30 28 | 0.29 7 | 0.43 38 | 3.04 87 | 6.58 96 | 6.38 108 |
DeepFlow2 [106] | 79.2 | 0.34 79 | 1.10 49 | 0.17 46 | 0.69 63 | 3.81 104 | 0.45 47 | 1.45 81 | 6.41 98 | 0.75 86 | 0.71 109 | 6.00 99 | 0.22 70 | 4.53 86 | 5.44 91 | 3.90 87 | 1.75 43 | 5.96 99 | 0.89 34 | 0.35 49 | 0.33 33 | 0.64 86 | 4.40 116 | 7.85 116 | 6.67 129 |
ContinualFlow_ROB [148] | 80.5 | 0.73 139 | 1.38 124 | 0.37 126 | 1.47 122 | 3.61 84 | 1.16 127 | 2.07 105 | 5.94 88 | 1.83 121 | 0.69 107 | 6.50 114 | 0.48 114 | 3.91 46 | 4.72 39 | 2.71 48 | 4.41 115 | 5.00 64 | 2.12 98 | 0.21 8 | 0.31 18 | 0.23 10 | 2.13 55 | 4.95 40 | 1.74 20 |
Steered-L1 [116] | 81.6 | 0.23 28 | 0.83 2 | 0.15 30 | 0.31 1 | 2.97 38 | 0.26 2 | 0.62 24 | 4.90 63 | 0.28 11 | 0.29 41 | 6.50 114 | 0.14 17 | 4.69 101 | 5.44 91 | 4.95 120 | 13.5 144 | 6.38 114 | 3.53 140 | 0.95 157 | 0.53 143 | 2.54 155 | 7.20 145 | 8.68 130 | 8.48 147 |
SimpleFlow [49] | 82.0 | 0.27 53 | 1.10 49 | 0.22 85 | 0.76 82 | 3.63 87 | 0.62 92 | 1.38 79 | 7.03 119 | 0.53 72 | 0.42 77 | 3.90 46 | 0.25 80 | 4.16 65 | 5.08 64 | 2.98 58 | 20.7 160 | 6.30 112 | 2.31 116 | 0.41 80 | 0.40 98 | 0.59 81 | 2.00 46 | 5.38 55 | 6.47 113 |
RFlow [88] | 83.0 | 0.29 65 | 1.05 25 | 0.19 53 | 0.39 6 | 3.46 68 | 0.28 5 | 1.80 93 | 7.45 162 | 0.31 20 | 0.30 49 | 7.40 139 | 0.19 44 | 5.17 137 | 5.76 143 | 5.24 132 | 2.26 63 | 6.13 104 | 1.98 86 | 0.45 95 | 0.36 61 | 0.56 72 | 4.48 118 | 7.88 118 | 6.75 135 |
EpicFlow [100] | 84.8 | 0.48 112 | 1.24 94 | 0.23 91 | 0.79 91 | 3.69 94 | 0.63 96 | 1.51 83 | 5.73 86 | 0.87 97 | 0.56 96 | 5.32 81 | 0.30 92 | 4.63 98 | 5.56 114 | 4.08 95 | 3.58 94 | 5.91 97 | 1.63 70 | 0.30 28 | 0.29 7 | 0.43 38 | 3.08 88 | 6.36 89 | 6.33 103 |
LSM_FLOW_RVC [182] | 85.0 | 0.82 145 | 1.53 141 | 0.56 144 | 1.56 124 | 4.81 140 | 1.15 125 | 2.28 112 | 6.50 103 | 1.67 119 | 1.03 125 | 7.43 140 | 0.68 133 | 3.83 41 | 4.63 32 | 2.72 49 | 1.34 25 | 5.26 79 | 1.09 43 | 0.23 12 | 0.32 23 | 0.24 12 | 2.62 76 | 5.41 57 | 3.69 39 |
Adaptive [20] | 85.0 | 0.26 49 | 1.15 66 | 0.12 11 | 0.65 52 | 3.63 87 | 0.50 57 | 2.48 116 | 8.26 196 | 0.45 54 | 0.36 71 | 4.65 64 | 0.19 44 | 4.57 90 | 5.38 84 | 4.08 95 | 3.92 107 | 6.03 103 | 1.94 80 | 0.46 99 | 0.47 127 | 0.58 80 | 3.22 94 | 7.41 105 | 6.43 110 |
CRTflow [81] | 86.6 | 0.37 89 | 1.06 28 | 0.19 53 | 0.63 48 | 3.57 81 | 0.44 44 | 1.71 91 | 7.76 173 | 0.50 69 | 0.49 87 | 7.44 141 | 0.20 49 | 4.77 107 | 5.70 130 | 4.00 91 | 1.84 48 | 8.40 186 | 1.58 66 | 0.36 54 | 0.33 33 | 0.56 72 | 4.13 108 | 8.33 123 | 6.37 107 |
TF+OM [98] | 89.0 | 0.28 57 | 1.23 88 | 0.16 38 | 0.54 27 | 3.53 77 | 0.43 41 | 1.91 99 | 4.53 58 | 2.12 126 | 0.30 49 | 5.24 80 | 0.21 61 | 5.48 156 | 5.91 155 | 5.59 148 | 2.43 76 | 6.24 108 | 0.76 23 | 0.52 118 | 0.49 135 | 0.67 98 | 4.26 113 | 7.69 112 | 6.09 92 |
IRR-PWC_RVC [180] | 89.2 | 0.90 149 | 1.61 144 | 0.46 138 | 1.93 132 | 4.12 122 | 1.41 133 | 2.29 113 | 5.51 82 | 2.24 131 | 0.92 120 | 3.04 24 | 0.76 135 | 4.09 62 | 4.88 50 | 2.73 50 | 1.46 33 | 5.20 75 | 1.10 45 | 0.37 64 | 0.44 117 | 0.37 26 | 3.19 93 | 5.68 69 | 3.34 34 |
DeepFlow [85] | 90.8 | 0.35 84 | 1.11 53 | 0.24 101 | 0.83 94 | 3.86 109 | 0.52 62 | 1.83 95 | 6.36 96 | 1.34 114 | 0.86 118 | 7.76 154 | 0.27 83 | 4.51 83 | 5.49 100 | 3.76 78 | 1.92 53 | 6.38 114 | 0.96 36 | 0.36 54 | 0.31 18 | 0.67 98 | 5.10 125 | 8.51 126 | 6.71 132 |
BriefMatch [122] | 91.6 | 0.25 41 | 1.06 28 | 0.15 30 | 0.65 52 | 3.15 50 | 0.36 26 | 0.98 61 | 3.39 34 | 0.33 27 | 0.24 22 | 7.01 133 | 0.15 21 | 4.70 102 | 5.31 80 | 5.47 144 | 8.12 135 | 7.15 126 | 3.69 143 | 0.84 154 | 0.47 127 | 3.37 162 | 9.00 156 | 10.4 150 | 11.5 195 |
DMF_ROB [135] | 92.0 | 0.39 95 | 1.10 49 | 0.23 91 | 0.77 84 | 4.08 121 | 0.55 74 | 1.94 101 | 6.74 110 | 0.71 84 | 0.67 104 | 5.81 96 | 0.27 83 | 4.87 117 | 5.62 119 | 4.82 118 | 3.45 92 | 7.35 130 | 2.01 88 | 0.32 40 | 0.29 7 | 0.47 49 | 4.52 120 | 7.71 113 | 6.56 124 |
EPMNet [131] | 92.3 | 0.69 135 | 1.52 140 | 0.40 132 | 2.06 136 | 4.42 128 | 1.64 135 | 2.02 103 | 4.20 47 | 1.82 120 | 0.91 119 | 5.88 98 | 0.42 111 | 3.99 55 | 4.99 58 | 3.00 59 | 2.63 77 | 5.85 94 | 2.23 103 | 0.36 54 | 0.51 139 | 0.41 33 | 2.56 74 | 5.21 48 | 1.48 17 |
SIOF [67] | 92.8 | 0.26 49 | 1.29 105 | 0.16 38 | 1.09 112 | 3.92 117 | 0.47 49 | 3.40 126 | 6.92 117 | 2.58 137 | 0.77 115 | 5.51 85 | 0.39 106 | 4.87 117 | 5.54 109 | 5.00 122 | 1.88 50 | 5.61 88 | 1.83 75 | 0.39 71 | 0.39 89 | 0.47 49 | 3.64 99 | 6.69 98 | 6.33 103 |
EAI-Flow [147] | 93.4 | 0.62 133 | 1.35 116 | 0.36 125 | 1.40 121 | 3.81 104 | 0.97 120 | 2.05 104 | 4.89 62 | 1.44 116 | 0.92 120 | 3.88 45 | 0.50 118 | 4.55 87 | 5.37 82 | 3.57 75 | 1.83 46 | 5.36 82 | 1.24 49 | 0.50 110 | 0.38 79 | 0.69 109 | 2.95 84 | 6.33 88 | 5.29 66 |
AugFNG_ROB [139] | 93.6 | 0.90 149 | 1.46 136 | 0.48 140 | 1.85 130 | 3.65 92 | 1.67 136 | 2.54 117 | 6.56 106 | 2.27 133 | 0.74 114 | 4.62 63 | 0.48 114 | 4.21 67 | 4.99 58 | 3.76 78 | 2.82 81 | 5.93 98 | 2.79 130 | 0.30 28 | 0.37 69 | 0.32 19 | 3.15 91 | 5.47 60 | 3.46 38 |
Aniso. Huber-L1 [22] | 95.1 | 0.31 68 | 1.11 53 | 0.20 69 | 1.03 109 | 3.73 100 | 0.83 115 | 2.25 111 | 7.75 172 | 0.96 105 | 0.67 104 | 4.18 53 | 0.43 112 | 4.63 98 | 5.48 98 | 3.89 86 | 1.88 50 | 5.24 78 | 1.43 57 | 0.52 118 | 0.45 119 | 0.84 130 | 3.00 85 | 6.93 101 | 6.07 91 |
Classic++ [32] | 95.2 | 0.28 57 | 1.16 70 | 0.21 80 | 0.64 51 | 3.88 110 | 0.52 62 | 1.96 102 | 6.43 100 | 0.61 78 | 0.36 71 | 6.46 113 | 0.20 49 | 4.72 103 | 5.63 120 | 3.88 83 | 2.31 69 | 7.38 132 | 2.28 106 | 0.56 128 | 0.45 119 | 0.70 111 | 5.09 124 | 8.15 121 | 6.57 126 |
FlowNet2 [120] | 95.7 | 0.72 138 | 1.55 142 | 0.38 130 | 2.00 135 | 4.44 129 | 1.68 138 | 2.15 106 | 4.45 55 | 2.07 125 | 0.56 96 | 6.86 128 | 0.38 105 | 3.99 55 | 4.99 58 | 3.00 59 | 2.63 77 | 5.85 94 | 2.23 103 | 0.42 85 | 0.60 152 | 0.51 63 | 2.16 56 | 5.29 52 | 1.39 16 |
TriangleFlow [30] | 95.9 | 0.32 72 | 1.23 88 | 0.23 91 | 0.72 72 | 4.53 134 | 0.42 40 | 1.60 87 | 7.09 121 | 0.36 32 | 0.33 63 | 4.75 66 | 0.18 36 | 5.39 153 | 5.96 156 | 6.08 157 | 5.72 127 | 5.96 99 | 1.95 83 | 0.49 105 | 0.62 155 | 0.68 105 | 3.00 85 | 6.41 90 | 5.85 84 |
CVENG22+RIC [199] | 96.3 | 0.48 112 | 1.28 102 | 0.22 85 | 0.89 98 | 3.81 104 | 0.66 103 | 1.81 94 | 6.50 103 | 0.85 94 | 0.61 100 | 5.63 89 | 0.28 85 | 5.75 160 | 6.47 161 | 5.58 147 | 2.88 82 | 6.21 106 | 2.07 94 | 0.30 28 | 0.28 4 | 0.43 38 | 3.33 95 | 7.28 103 | 6.56 124 |
LFNet_ROB [145] | 98.5 | 0.69 135 | 1.38 124 | 0.42 134 | 1.09 112 | 3.50 74 | 0.86 117 | 1.88 96 | 6.22 91 | 1.15 110 | 0.72 111 | 4.14 52 | 0.55 124 | 5.15 132 | 5.77 146 | 4.95 120 | 2.00 56 | 6.88 122 | 1.64 71 | 0.29 26 | 0.34 41 | 0.38 28 | 4.16 109 | 8.66 128 | 6.36 106 |
TV-L1-improved [17] | 98.9 | 0.28 57 | 1.05 25 | 0.17 46 | 0.57 38 | 3.55 79 | 0.44 44 | 2.24 110 | 8.19 192 | 0.46 57 | 0.35 69 | 7.45 142 | 0.18 36 | 4.86 116 | 5.68 126 | 4.21 105 | 17.3 152 | 7.54 139 | 2.47 123 | 0.56 128 | 0.48 131 | 0.72 118 | 4.10 107 | 7.73 114 | 6.51 120 |
LocallyOriented [52] | 99.2 | 0.41 100 | 1.38 124 | 0.19 53 | 1.23 116 | 4.25 124 | 0.76 111 | 3.57 133 | 7.52 166 | 1.10 109 | 0.52 93 | 3.81 42 | 0.28 85 | 4.88 121 | 5.47 95 | 4.35 109 | 7.73 132 | 7.52 137 | 1.49 60 | 0.35 49 | 0.35 50 | 0.56 72 | 4.49 119 | 6.47 93 | 5.95 87 |
SegOF [10] | 99.2 | 0.56 130 | 1.27 101 | 0.41 133 | 1.94 133 | 3.85 107 | 1.77 140 | 3.44 128 | 6.14 90 | 1.96 123 | 1.26 135 | 3.34 27 | 0.92 138 | 4.83 112 | 5.24 74 | 4.79 117 | 16.6 151 | 7.57 140 | 4.51 151 | 0.21 8 | 0.32 23 | 0.32 19 | 2.87 81 | 6.41 90 | 3.00 30 |
OFRF [132] | 99.8 | 0.32 72 | 1.46 136 | 0.24 101 | 3.25 151 | 5.13 146 | 3.02 154 | 3.54 131 | 7.77 174 | 2.27 133 | 0.82 117 | 4.12 51 | 0.55 124 | 4.02 60 | 4.99 58 | 2.43 39 | 2.99 84 | 4.07 13 | 1.01 41 | 0.53 125 | 0.48 131 | 0.83 129 | 4.22 112 | 5.04 43 | 5.37 69 |
Brox et al. [5] | 99.8 | 0.38 90 | 1.15 66 | 0.27 113 | 0.84 95 | 3.90 114 | 0.69 106 | 1.45 81 | 5.36 78 | 0.87 97 | 0.98 123 | 6.75 122 | 0.28 85 | 5.17 137 | 5.73 136 | 5.35 138 | 6.14 129 | 7.37 131 | 2.79 130 | 0.27 17 | 0.36 61 | 0.30 18 | 4.93 121 | 7.45 106 | 6.32 102 |
CBF [12] | 100.6 | 0.32 72 | 0.99 15 | 0.20 69 | 1.00 106 | 3.48 71 | 0.97 120 | 1.61 88 | 6.55 105 | 0.81 92 | 0.66 103 | 6.31 107 | 0.46 113 | 4.87 117 | 5.65 123 | 4.92 119 | 2.31 69 | 5.30 80 | 1.62 69 | 0.77 149 | 0.54 145 | 1.11 140 | 4.07 106 | 7.61 110 | 6.58 127 |
F-TV-L1 [15] | 102.4 | 0.38 90 | 1.23 88 | 0.30 117 | 1.32 118 | 4.46 131 | 0.67 105 | 3.59 134 | 7.35 159 | 0.70 83 | 0.69 107 | 7.63 148 | 0.29 91 | 4.74 105 | 5.54 109 | 4.30 107 | 3.49 93 | 6.97 124 | 1.94 80 | 0.38 68 | 0.43 114 | 0.42 36 | 3.65 100 | 7.59 109 | 3.92 42 |
Fusion [6] | 103.5 | 0.38 90 | 1.17 72 | 0.28 115 | 0.53 26 | 3.35 59 | 0.48 52 | 0.90 55 | 3.47 35 | 0.76 88 | 0.63 101 | 5.66 90 | 0.39 106 | 5.21 140 | 5.79 150 | 5.33 137 | 4.41 115 | 5.98 101 | 2.82 132 | 0.56 128 | 0.51 139 | 0.75 120 | 6.49 141 | 11.3 154 | 7.02 139 |
DF-Auto [113] | 103.8 | 0.47 111 | 1.40 129 | 0.22 85 | 1.58 126 | 3.91 116 | 1.18 128 | 2.42 114 | 6.56 106 | 2.21 129 | 1.12 129 | 6.32 109 | 0.51 120 | 4.99 122 | 5.70 130 | 5.07 124 | 1.29 24 | 5.54 86 | 1.03 42 | 0.40 78 | 0.51 139 | 0.36 23 | 3.91 104 | 7.83 115 | 6.33 103 |
p-harmonic [29] | 104.3 | 0.39 95 | 1.15 66 | 0.33 122 | 0.74 78 | 3.63 87 | 0.61 91 | 2.42 114 | 7.91 184 | 0.82 93 | 1.01 124 | 4.53 59 | 0.66 132 | 5.21 140 | 5.70 130 | 5.59 148 | 1.74 42 | 6.29 111 | 1.54 63 | 0.45 95 | 0.41 106 | 0.53 69 | 5.19 127 | 8.53 127 | 6.31 100 |
TriFlow [93] | 105.0 | 0.38 90 | 1.41 130 | 0.19 53 | 0.92 104 | 3.99 120 | 0.77 113 | 3.14 124 | 6.44 101 | 2.81 141 | 0.47 84 | 5.07 72 | 0.39 106 | 5.37 151 | 5.86 153 | 5.27 134 | 1.22 23 | 5.68 90 | 0.79 28 | 1.96 161 | 0.71 160 | 2.60 156 | 3.11 90 | 6.09 82 | 4.44 55 |
Bartels [41] | 105.5 | 0.34 79 | 1.28 102 | 0.26 111 | 0.52 24 | 3.07 41 | 0.41 36 | 1.19 69 | 5.46 80 | 0.46 57 | 0.43 78 | 7.93 155 | 0.31 96 | 5.14 131 | 5.73 136 | 5.26 133 | 5.91 128 | 7.40 133 | 2.13 99 | 0.64 139 | 0.46 124 | 1.26 149 | 6.18 137 | 10.0 149 | 8.44 146 |
CLG-TV [48] | 105.6 | 0.33 77 | 1.07 35 | 0.22 85 | 0.90 99 | 3.76 101 | 0.75 110 | 2.15 106 | 7.98 187 | 0.73 85 | 0.67 104 | 4.67 65 | 0.53 122 | 4.84 114 | 5.55 112 | 4.44 110 | 2.11 57 | 7.44 134 | 2.05 90 | 0.57 132 | 0.56 148 | 0.86 131 | 4.18 111 | 8.19 122 | 6.25 97 |
Local-TV-L1 [65] | 107.1 | 0.43 104 | 1.24 94 | 0.29 116 | 1.98 134 | 4.55 135 | 1.15 125 | 4.88 142 | 7.48 163 | 2.20 128 | 1.35 136 | 6.92 130 | 0.63 131 | 4.63 98 | 5.50 103 | 4.04 94 | 2.22 62 | 5.75 92 | 1.94 80 | 0.36 54 | 0.31 18 | 0.47 49 | 5.53 130 | 7.86 117 | 6.89 136 |
WOLF_ROB [144] | 107.8 | 0.56 130 | 1.45 134 | 0.27 113 | 2.95 148 | 5.57 156 | 1.35 131 | 5.23 146 | 7.51 165 | 1.60 118 | 1.05 126 | 4.99 71 | 0.53 122 | 4.83 112 | 5.44 91 | 5.07 124 | 8.63 136 | 5.77 93 | 4.08 149 | 0.31 36 | 0.33 33 | 0.41 33 | 3.49 98 | 5.63 66 | 4.64 56 |
Dynamic MRF [7] | 108.8 | 0.36 85 | 1.26 100 | 0.24 101 | 0.57 38 | 4.28 126 | 0.33 20 | 1.88 96 | 6.72 109 | 0.37 37 | 0.45 82 | 6.86 128 | 0.23 75 | 5.44 155 | 5.89 154 | 5.60 150 | 12.3 142 | 11.8 195 | 4.03 148 | 0.42 85 | 0.30 12 | 0.79 122 | 7.94 150 | 11.0 152 | 9.07 149 |
Rannacher [23] | 110.3 | 0.33 77 | 1.19 80 | 0.25 108 | 0.75 80 | 3.88 110 | 0.60 86 | 2.69 121 | 8.38 198 | 0.63 80 | 0.47 84 | 7.51 145 | 0.28 85 | 4.78 109 | 5.64 122 | 4.00 91 | 17.7 156 | 7.45 135 | 2.85 133 | 0.50 110 | 0.40 98 | 0.70 111 | 3.80 102 | 7.61 110 | 6.49 116 |
Second-order prior [8] | 111.5 | 0.36 85 | 1.22 86 | 0.21 80 | 1.07 110 | 3.69 94 | 0.70 108 | 2.58 120 | 7.79 176 | 1.06 108 | 0.78 116 | 5.23 79 | 0.28 85 | 4.77 107 | 5.58 116 | 4.74 116 | 3.07 86 | 7.16 127 | 2.63 126 | 0.64 139 | 0.45 119 | 0.79 122 | 4.31 114 | 7.93 119 | 6.99 138 |
LDOF [28] | 113.7 | 0.42 102 | 1.29 105 | 0.21 80 | 1.35 120 | 4.55 135 | 0.69 106 | 1.91 99 | 4.97 66 | 1.24 112 | 1.56 138 | 11.8 199 | 0.49 117 | 5.15 132 | 5.75 142 | 5.19 129 | 4.76 118 | 8.27 184 | 2.28 106 | 0.32 40 | 0.35 50 | 0.56 72 | 5.18 126 | 8.80 135 | 6.49 116 |
StereoFlow [44] | 114.0 | 1.36 161 | 2.53 162 | 0.92 156 | 3.87 156 | 5.71 158 | 2.94 153 | 3.43 127 | 6.77 111 | 2.99 143 | 3.06 145 | 9.56 196 | 2.88 146 | 4.78 109 | 5.57 115 | 4.67 114 | 1.35 27 | 6.94 123 | 0.97 37 | 0.22 11 | 0.28 4 | 0.27 14 | 4.93 121 | 8.34 125 | 6.55 123 |
FlowNetS+ft+v [110] | 114.9 | 0.39 95 | 1.21 84 | 0.19 53 | 1.19 115 | 3.94 118 | 0.83 115 | 3.45 129 | 7.87 183 | 2.02 124 | 1.18 132 | 7.17 137 | 0.59 128 | 5.08 128 | 5.72 135 | 5.16 128 | 2.42 75 | 6.39 117 | 2.22 102 | 0.48 103 | 0.45 119 | 1.46 152 | 3.88 103 | 7.32 104 | 5.74 79 |
StereoOF-V1MT [117] | 115.1 | 0.43 104 | 1.30 110 | 0.23 91 | 1.53 123 | 5.30 148 | 0.43 41 | 3.31 125 | 7.14 122 | 0.55 73 | 0.97 122 | 5.55 88 | 0.35 102 | 5.24 145 | 5.73 136 | 5.22 130 | 18.1 157 | 7.92 142 | 3.97 147 | 0.35 49 | 0.35 50 | 0.67 98 | 8.71 155 | 11.5 155 | 9.09 150 |
UnFlow [127] | 118.0 | 1.23 156 | 2.28 158 | 0.66 148 | 2.36 139 | 3.90 114 | 1.90 142 | 3.94 136 | 5.69 85 | 2.23 130 | 2.29 142 | 5.87 97 | 2.12 142 | 5.37 151 | 5.74 141 | 5.74 154 | 4.39 114 | 7.49 136 | 3.63 141 | 0.25 16 | 0.36 61 | 0.23 10 | 4.16 109 | 9.27 139 | 5.41 70 |
Filter Flow [19] | 118.9 | 0.51 123 | 1.41 130 | 0.37 126 | 1.86 131 | 3.79 103 | 1.12 123 | 4.19 139 | 6.46 102 | 3.20 149 | 3.16 147 | 5.17 76 | 3.07 148 | 5.03 124 | 5.48 98 | 5.54 145 | 3.06 85 | 5.33 81 | 2.41 121 | 0.57 132 | 0.60 152 | 0.60 82 | 5.49 129 | 7.53 108 | 6.27 99 |
Learning Flow [11] | 119.1 | 0.36 85 | 1.29 105 | 0.19 53 | 0.88 97 | 4.18 123 | 0.56 82 | 2.94 122 | 6.87 113 | 1.01 106 | 1.78 139 | 6.81 123 | 0.50 118 | 5.51 157 | 6.19 159 | 5.41 142 | 14.2 147 | 8.05 144 | 3.44 139 | 0.41 80 | 0.54 145 | 0.57 77 | 6.48 140 | 9.99 148 | 6.48 115 |
Shiralkar [42] | 120.7 | 0.44 109 | 1.24 94 | 0.24 101 | 1.29 117 | 4.44 129 | 0.51 58 | 3.66 135 | 8.22 193 | 0.75 86 | 1.05 126 | 6.20 103 | 0.39 106 | 4.87 117 | 5.52 104 | 4.61 113 | 5.13 121 | 8.26 183 | 2.90 135 | 0.75 144 | 0.41 106 | 1.11 140 | 6.02 134 | 8.77 133 | 6.39 109 |
CNN-flow-warp+ref [115] | 120.9 | 0.49 120 | 1.29 105 | 0.35 123 | 1.08 111 | 3.70 96 | 0.94 119 | 3.01 123 | 7.08 120 | 1.40 115 | 1.12 129 | 7.19 138 | 0.58 127 | 5.23 143 | 5.77 146 | 5.36 139 | 5.17 123 | 8.89 190 | 2.38 118 | 0.28 23 | 0.32 23 | 0.67 98 | 10.1 159 | 11.6 158 | 10.5 155 |
Ad-TV-NDC [36] | 121.1 | 0.89 148 | 1.39 127 | 1.05 159 | 4.30 158 | 5.21 147 | 3.61 157 | 7.03 191 | 7.85 179 | 2.68 138 | 2.01 140 | 4.92 69 | 1.93 140 | 4.55 87 | 5.53 105 | 3.64 76 | 2.30 68 | 7.11 125 | 2.02 89 | 0.37 64 | 0.34 41 | 0.48 55 | 8.69 154 | 9.20 138 | 9.22 151 |
GroupFlow [9] | 121.4 | 0.78 142 | 1.73 148 | 0.60 146 | 3.11 149 | 5.38 151 | 2.49 150 | 4.27 141 | 6.91 116 | 2.76 140 | 1.21 133 | 4.61 62 | 0.79 136 | 5.09 129 | 5.76 143 | 3.88 83 | 7.80 134 | 7.20 129 | 5.19 156 | 0.31 36 | 0.42 110 | 0.45 45 | 4.34 115 | 8.00 120 | 6.31 100 |
GraphCuts [14] | 121.8 | 0.53 125 | 1.30 110 | 0.26 111 | 2.63 142 | 5.49 153 | 1.53 134 | 2.57 119 | 5.15 75 | 2.57 136 | 1.14 131 | 4.94 70 | 0.61 130 | 4.40 77 | 5.13 67 | 3.95 89 | 17.3 152 | 6.38 114 | 5.59 158 | 0.75 144 | 0.43 114 | 1.14 143 | 6.31 139 | 9.98 147 | 7.32 142 |
IAOF2 [51] | 122.2 | 0.42 102 | 1.36 121 | 0.30 117 | 1.58 126 | 4.27 125 | 1.14 124 | 3.56 132 | 7.66 170 | 2.70 139 | 3.55 151 | 5.20 78 | 3.60 152 | 4.84 114 | 5.67 125 | 4.15 101 | 4.20 111 | 6.02 102 | 2.87 134 | 0.56 128 | 0.46 124 | 0.98 135 | 5.41 128 | 7.19 102 | 6.10 93 |
TVL1_RVC [175] | 125.7 | 0.85 146 | 1.66 145 | 0.81 155 | 2.87 146 | 4.52 133 | 2.43 148 | 6.96 190 | 7.95 185 | 3.21 150 | 3.15 146 | 5.72 93 | 3.03 147 | 5.03 124 | 5.69 128 | 5.04 123 | 3.86 106 | 7.53 138 | 2.63 126 | 0.29 26 | 0.30 12 | 0.36 23 | 6.57 142 | 9.87 145 | 7.08 140 |
2D-CLG [1] | 127.3 | 1.19 155 | 2.21 156 | 0.70 152 | 2.17 137 | 3.78 102 | 1.93 144 | 6.02 149 | 7.44 161 | 3.48 158 | 3.42 149 | 6.03 100 | 3.32 149 | 5.24 145 | 5.68 126 | 5.39 141 | 15.6 149 | 8.14 146 | 3.77 144 | 0.31 36 | 0.26 3 | 0.48 55 | 5.99 133 | 8.71 132 | 6.74 133 |
Black & Anandan [4] | 128.6 | 0.54 127 | 1.34 115 | 0.48 140 | 2.79 144 | 4.85 141 | 1.86 141 | 6.61 153 | 7.85 179 | 2.99 143 | 2.16 141 | 5.71 92 | 1.95 141 | 5.15 132 | 5.71 134 | 5.30 135 | 11.7 140 | 8.34 185 | 3.41 138 | 0.36 54 | 0.41 106 | 0.37 26 | 5.98 132 | 8.99 136 | 6.44 111 |
HCIC-L [97] | 129.2 | 1.29 159 | 2.09 154 | 0.69 151 | 6.78 197 | 6.72 162 | 7.04 197 | 3.50 130 | 5.40 79 | 3.11 147 | 5.45 159 | 7.14 136 | 5.37 160 | 4.52 85 | 5.40 86 | 3.13 65 | 3.84 105 | 5.12 70 | 3.89 146 | 2.11 163 | 1.50 164 | 2.77 157 | 3.75 101 | 6.50 94 | 3.31 33 |
IAOF [50] | 129.8 | 0.54 127 | 1.35 116 | 0.47 139 | 2.65 143 | 5.31 149 | 1.90 142 | 8.88 199 | 9.21 199 | 3.37 155 | 3.44 150 | 5.36 82 | 3.47 150 | 4.74 105 | 5.53 105 | 4.56 112 | 3.32 90 | 6.48 118 | 2.37 117 | 0.53 125 | 0.39 89 | 0.68 105 | 7.36 148 | 7.48 107 | 7.98 144 |
Nguyen [33] | 131.8 | 0.71 137 | 1.68 146 | 0.49 142 | 2.50 141 | 4.86 142 | 2.21 147 | 7.41 193 | 7.97 186 | 3.47 157 | 3.87 153 | 5.77 94 | 3.73 153 | 5.05 127 | 5.76 143 | 5.14 126 | 3.81 104 | 7.76 141 | 2.63 126 | 0.39 71 | 0.36 61 | 0.57 77 | 6.17 136 | 8.67 129 | 6.69 130 |
SPSA-learn [13] | 132.4 | 0.53 125 | 1.36 121 | 0.45 136 | 2.47 140 | 5.72 159 | 1.69 139 | 4.97 145 | 7.78 175 | 2.93 142 | 2.51 143 | 7.47 143 | 2.31 143 | 5.30 148 | 5.83 152 | 5.44 143 | 22.3 162 | 7.93 143 | 4.87 153 | 0.36 54 | 0.34 41 | 0.51 63 | 6.03 135 | 9.76 144 | 6.66 128 |
Modified CLG [34] | 134.5 | 0.66 134 | 1.45 134 | 0.55 143 | 1.60 129 | 3.72 99 | 1.40 132 | 5.89 148 | 8.02 189 | 3.40 156 | 1.52 137 | 7.10 135 | 1.29 139 | 5.23 143 | 5.80 151 | 5.36 139 | 5.05 120 | 8.25 182 | 2.71 129 | 0.39 71 | 0.39 89 | 0.82 127 | 5.67 131 | 9.44 141 | 6.69 130 |
2bit-BM-tele [96] | 134.5 | 0.51 123 | 1.42 132 | 0.45 136 | 0.91 102 | 4.49 132 | 0.76 111 | 2.54 117 | 7.60 169 | 0.91 103 | 0.73 112 | 7.71 151 | 0.55 124 | 5.30 148 | 5.99 157 | 5.23 131 | 5.13 121 | 6.80 120 | 2.30 114 | 1.15 160 | 0.64 158 | 2.10 154 | 7.02 144 | 11.6 158 | 9.85 152 |
BlockOverlap [61] | 135.6 | 0.43 104 | 1.36 121 | 0.37 126 | 1.58 126 | 3.89 112 | 1.30 130 | 4.01 137 | 7.31 158 | 2.26 132 | 1.22 134 | 7.93 155 | 0.84 137 | 5.24 145 | 5.70 130 | 6.40 159 | 4.80 119 | 6.20 105 | 2.44 122 | 0.80 150 | 0.55 147 | 3.83 163 | 7.28 147 | 9.60 142 | 10.0 154 |
Horn & Schunck [3] | 135.8 | 0.73 139 | 1.72 147 | 0.59 145 | 2.87 146 | 4.93 144 | 2.05 145 | 6.26 152 | 7.71 171 | 3.28 152 | 3.80 152 | 6.43 111 | 3.48 151 | 5.10 130 | 5.55 112 | 5.31 136 | 8.89 137 | 10.1 192 | 4.92 154 | 0.41 80 | 0.46 124 | 0.36 23 | 6.67 143 | 9.11 137 | 6.95 137 |
HBpMotionGpu [43] | 136.2 | 0.50 121 | 1.56 143 | 0.35 123 | 2.28 138 | 5.51 154 | 1.67 136 | 6.22 151 | 7.82 177 | 3.03 145 | 1.10 128 | 8.84 194 | 0.69 134 | 5.58 158 | 6.09 158 | 5.55 146 | 3.29 89 | 6.34 113 | 2.47 123 | 0.52 118 | 0.48 131 | 0.64 86 | 6.21 138 | 8.69 131 | 6.74 133 |
TI-DOFE [24] | 138.8 | 1.13 154 | 2.07 153 | 1.14 160 | 3.43 154 | 4.87 143 | 3.26 156 | 7.27 192 | 7.84 178 | 3.50 159 | 4.33 155 | 6.11 101 | 4.19 155 | 5.04 126 | 5.58 116 | 5.15 127 | 6.52 130 | 10.3 193 | 4.70 152 | 0.36 54 | 0.37 69 | 0.53 69 | 7.85 149 | 9.38 140 | 8.17 145 |
Heeger++ [102] | 139.3 | 0.85 146 | 1.84 151 | 0.60 146 | 3.55 155 | 5.57 156 | 2.47 149 | 4.90 143 | 6.81 112 | 1.89 122 | 3.39 148 | 7.75 153 | 2.84 145 | 5.15 132 | 5.29 77 | 6.01 156 | 17.5 155 | 8.65 188 | 5.32 157 | 0.45 95 | 0.41 106 | 0.61 83 | 9.73 157 | 11.5 155 | 10.9 157 |
H+S_RVC [176] | 142.0 | 1.36 161 | 2.38 160 | 0.97 158 | 2.82 145 | 4.65 137 | 2.20 146 | 5.77 147 | 7.55 167 | 3.34 154 | 4.72 156 | 6.35 110 | 4.53 156 | 5.22 142 | 5.42 88 | 5.68 151 | 9.48 139 | 11.7 194 | 7.38 162 | 0.43 89 | 0.42 110 | 0.65 90 | 8.22 151 | 9.88 146 | 8.66 148 |
Adaptive flow [45] | 142.7 | 0.94 152 | 2.01 152 | 0.71 153 | 4.43 159 | 5.33 150 | 4.12 158 | 6.07 150 | 6.90 115 | 3.85 161 | 4.09 154 | 6.17 102 | 4.06 154 | 5.00 123 | 5.73 136 | 4.48 111 | 6.57 131 | 5.86 96 | 3.68 142 | 2.03 162 | 1.05 162 | 3.31 161 | 7.27 146 | 11.0 152 | 7.57 143 |
SILK [80] | 147.0 | 0.80 144 | 1.82 150 | 0.80 154 | 3.23 150 | 5.00 145 | 2.92 152 | 7.68 196 | 8.24 194 | 3.11 147 | 3.00 144 | 6.98 131 | 2.43 144 | 5.34 150 | 5.77 146 | 5.92 155 | 15.0 148 | 8.08 145 | 4.36 150 | 0.50 110 | 0.38 79 | 1.01 137 | 8.67 153 | 10.9 151 | 9.92 153 |
FFV1MT [104] | 151.3 | 0.93 151 | 2.34 159 | 0.67 150 | 3.35 152 | 5.54 155 | 2.51 151 | 4.92 144 | 6.95 118 | 3.22 151 | 5.72 160 | 8.77 193 | 5.31 159 | 5.74 159 | 5.73 136 | 7.13 160 | 13.6 145 | 15.3 199 | 6.77 160 | 0.49 105 | 0.49 135 | 0.75 120 | 9.73 157 | 11.5 155 | 10.9 157 |
PGAM+LK [55] | 152.2 | 1.38 163 | 2.26 157 | 2.75 198 | 4.11 157 | 5.46 152 | 4.31 159 | 4.04 138 | 5.95 89 | 3.10 146 | 6.71 163 | 9.38 195 | 6.38 162 | 5.15 132 | 5.49 100 | 5.71 152 | 7.75 133 | 8.68 189 | 3.81 145 | 1.11 158 | 0.72 161 | 1.89 153 | 8.55 152 | 9.73 143 | 10.6 156 |
SLK [47] | 153.8 | 1.25 157 | 2.15 155 | 1.34 161 | 3.35 152 | 4.75 139 | 3.16 155 | 7.53 194 | 8.14 191 | 3.31 153 | 5.19 158 | 6.99 132 | 4.99 158 | 5.42 154 | 5.69 128 | 6.26 158 | 16.1 150 | 8.44 187 | 4.98 155 | 0.59 135 | 0.39 89 | 1.26 149 | 10.7 160 | 12.1 161 | 11.0 159 |
AdaConv-v1 [124] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
SepConv-v1 [125] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
SuperSlomo [130] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
CtxSyn [134] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
CyclicGen [149] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
TOF-M [150] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
MPRN [151] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
DAIN [152] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
FRUCnet [153] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
OFRI [154] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
FGME [158] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
MS-PFT [159] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
MEMC-Net+ [160] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
ADC [161] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
DSepConv [162] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
MAF-net [163] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
STAR-Net [164] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
AdaCoF [165] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
TC-GAN [166] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
FeFlow [167] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
DAI [168] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
SoftSplat [169] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
STSR [170] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
BMBC [171] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
GDCN [172] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
EDSC [173] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
MV_VFI [183] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
DistillNet [184] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
SepConv++ [185] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
EAFI [186] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
FLAVR [188] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
SoftsplatAug [190] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
ProBoost-Net [191] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
IDIAL [192] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
IFRNet [193] | 160.1 | 2.32 164 | 2.67 163 | 1.41 162 | 5.68 161 | 7.08 163 | 5.41 161 | 6.88 155 | 7.15 123 | 6.23 163 | 7.42 164 | 8.22 158 | 7.70 164 | 13.5 163 | 14.0 163 | 12.0 163 | 31.6 165 | 8.14 146 | 8.03 163 | 3.93 165 | 2.37 165 | 4.62 165 | 11.8 162 | 16.0 162 | 11.0 159 |
FOLKI [16] | 164.8 | 1.10 153 | 2.44 161 | 0.96 157 | 6.01 196 | 6.49 161 | 6.33 196 | 6.80 154 | 8.01 188 | 3.62 160 | 4.98 157 | 7.71 151 | 4.88 157 | 5.98 161 | 6.25 160 | 7.48 161 | 12.2 141 | 14.8 197 | 5.96 159 | 1.11 158 | 0.59 151 | 2.88 159 | 11.0 161 | 11.9 160 | 11.5 195 |
Pyramid LK [2] | 167.6 | 1.25 157 | 1.79 149 | 1.67 197 | 5.06 160 | 5.74 160 | 5.11 160 | 7.76 197 | 8.24 194 | 4.54 162 | 6.31 161 | 6.43 111 | 6.90 163 | 12.3 162 | 13.8 162 | 10.9 162 | 17.4 154 | 9.60 191 | 6.83 161 | 0.94 156 | 0.60 152 | 3.13 160 | 12.6 197 | 16.8 197 | 11.7 197 |
Periodicity [79] | 176.5 | 1.29 159 | 3.11 198 | 0.66 148 | 8.81 198 | 9.31 198 | 9.57 198 | 7.66 195 | 7.36 160 | 6.46 198 | 6.64 162 | 9.79 197 | 6.12 161 | 22.6 199 | 24.0 199 | 21.6 199 | 20.0 159 | 15.2 198 | 12.8 199 | 0.27 17 | 0.53 143 | 2.84 158 | 13.6 198 | 17.6 198 | 13.3 198 |
AVG_FLOW_ROB [137] | 192.4 | 8.07 199 | 5.66 199 | 8.58 199 | 10.8 199 | 9.78 199 | 10.7 199 | 8.83 198 | 8.36 197 | 9.38 199 | 9.30 199 | 10.4 198 | 9.46 199 | 16.1 198 | 17.1 198 | 15.3 198 | 19.8 158 | 14.7 196 | 12.1 198 | 3.47 164 | 1.43 163 | 3.85 164 | 16.8 199 | 20.4 199 | 14.7 199 |
Method | time* | frames | color | Reference and notes | |
[1] 2D-CLG | 844 | 2 | gray | The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences. | |
[2] Pyramid LK | 12 | 2 | color | A modification of Bouguet's pyramidal implementation of Lucas-Kanade. | |
[3] Horn & Schunck | 49 | 2 | gray | A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data. | |
[4] Black & Anandan | 328 | 2 | gray | A modern Matlab implementation of the Black & Anandan method by Deqing Sun. | |
[5] Brox et al. | 18 | 2 | color | T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.) | |
[6] Fusion | 2,666 | 2 | color | V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008. | |
[7] Dynamic MRF | 366 | 2 | gray | B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.) | |
[8] Second-order prior | 14 | 2 | gray | W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[9] GroupFlow | 600 | 2 | gray | X. Ren. Local Grouping for Optical Flow. CVPR 2008. | |
[10] SegOF | 60 | 2 | color | L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available. | |
[11] Learning Flow | 825 | 2 | gray | D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008. | |
[12] CBF | 69 | 2 | color | W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[13] SPSA-learn | 200 | 2 | color | Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008. | |
[14] GraphCuts | 1,200 | 2 | color | T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008. | |
[15] F-TV-L1 | 8 | 2 | gray | A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008. | |
[16] FOLKI | 1.4 | 2 | gray | G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005. | |
[17] TV-L1-improved | 2.9 | 2 | gray | A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision. | |
[18] DPOF | 287 | 2 | color | C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.) | |
[19] Filter Flow | 34,000 | 2 | color | S. Seitz and S. Baker. Filter flow. ICCV 2009. | |
[20] Adaptive | 9.2 | 2 | gray | A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009. | |
[21] Complementary OF | 44 | 2 | color | H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009. | |
[22] Aniso. Huber-L1 | 2 | 2 | gray | M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision. | |
[23] Rannacher | 0.12 | 2 | gray | J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009. | |
[24] TI-DOFE | 260 | 2 | gray | C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009. | |
[25] NL-TV-NCC | 20 | 2 | color | M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010. | |
[26] MDP-Flow | 188 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010. | |
[27] ACK-Prior | 5872 | 2 | color | K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010. | |
[28] LDOF | 122 | 2 | color | T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011. | |
[29] p-harmonic | 565 | 2 | gray | J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010. | |
[30] TriangleFlow | 4200 | 2 | gray | B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010. | |
[31] Classic+NL | 972 | 2 | color | D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code. | |
[32] Classic++ | 486 | 2 | gray | A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010. | |
[33] Nguyen | 33 | 2 | gray | D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011. | |
[34] Modified CLG | 133 | 2 | gray | R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010. | |
[35] ComplOF-FED-GPU | 0.97 | 2 | color | P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010. | |
[36] Ad-TV-NDC | 35 | 2 | gray | M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010. | |
[37] Layers++ | 18206 | 2 | color | D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010. | |
[38] OFH | 620 | 3 | color | H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011. | |
[39] LSM | 1615 | 2 | color | K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011. | |
[40] CostFilter | 55 | 2 | color | C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011. | |
[41] Bartels | 0.15 | 2 | gray | C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU. | |
[42] Shiralkar | 600 | 2 | gray | M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242. | |
[43] HBpMotionGpu | 1000 | 5 | gray | S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.) | |
[44] StereoFlow | 7200 | 2 | color | G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772. | |
[45] Adaptive flow | 121 | 2 | gray | Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012. | |
[46] TC-Flow | 2500 | 5 | color | S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011. | |
[47] SLK | 300 | 2 | gray | T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011. | |
[48] CLG-TV | 29 | 2 | gray | M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code. | |
[49] SimpleFlow | 1.7 | 2 | color | M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012. | |
[50] IAOF | 57 | 2 | gray | D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011. | |
[51] IAOF2 | 56 | 2 | gray | Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153. | |
[52] LocallyOriented | 9541 | 2 | gray | Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012. | |
[53] IROF-TV | 261 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop. | |
[54] Sparse Occlusion | 2312 | 2 | color | Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012. | |
[55] PGAM+LK | 0.37 | 2 | gray | A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010. | |
[56] Sparse-NonSparse | 713 | 2 | color | Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012. | |
[57] nLayers | 36150 | 4 | color | D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012. | |
[58] IROF++ | 187 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013. | |
[59] COFM | 600 | 3 | color | M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013. | |
[60] Efficient-NL | 400 | 2 | color | P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012. | |
[61] BlockOverlap | 2 | 2 | gray | Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. MMSP 2012. | |
[62] Ramp | 1200 | 2 | color | A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012. | |
[63] Occlusion-TV-L1 | 538 | 3 | gray | C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012. | |
[64] TV-L1-MCT | 90 | 2 | color | M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012. | |
[65] Local-TV-L1 | 500 | 2 | gray | L. Raket. Local smoothness for global optical flow. ICIP 2012. | |
[66] ALD-Flow | 61 | 2 | color | M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012. | |
[67] SIOF | 234 | 2 | color | L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012. | |
[68] MDP-Flow2 | 342 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available. | |
[69] TCOF | 1421 | all | gray | J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013. | |
[70] LME | 476 | 2 | color | W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013. | |
[71] NN-field | 362 | 2 | color | L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[72] FESL | 3310 | 2 | color | Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014. | |
[73] PMF | 35 | 2 | color | J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013. | |
[74] FC-2Layers-FF | 2662 | 4 | color | D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013. | |
[75] NNF-Local | 673 | 2 | color | Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[76] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code. | |
[77] TC/T-Flow | 341 | 5 | color | M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013. | |
[78] OFLAF | 1530 | 2 | color | T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013. | |
[79] Periodicity | 8000 | 4 | color | Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014. | |
[80] SILK | 572 | 2 | gray | Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014. | |
[81] CRTflow | 13 | 3 | color | O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013. | |
[82] Classic+CPF | 640 | 2 | gray | Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014. | |
[83] S2D-Matching | 1200 | 2 | color | Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013. | |
[84] AGIF+OF | 438 | 2 | gray | Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016. | |
[85] DeepFlow | 13 | 2 | color | P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[86] EPPM w/o HM | 2.5 | 2 | color | L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014. | |
[87] MLDP_OF | 165 | 2 | gray | M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014. | |
[88] RFlow | 20 | 2 | gray | S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014. | |
[89] SRR-TVOF-NL | 32 | all | color | P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014. | |
[90] 2DHMM-SAS | 157 | 2 | color | M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission. | |
[91] WLIF-Flow | 700 | 2 | color | Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014. | |
[92] FMOF | 215 | 2 | color | N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014. | |
[93] TriFlow | 150 | 2 | color | TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914. | |
[94] ComponentFusion | 6.5 | 2 | color | Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941. | |
[95] AggregFlow | 1642 | 2 | color | D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759. | |
[96] 2bit-BM-tele | 124 | 2 | gray | R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013. | |
[97] HCIC-L | 330 | 2 | color | Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114. | |
[98] TF+OM | 600 | 2 | color | R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015. | |
[99] PH-Flow | 800 | 2 | color | J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015. | |
[100] EpicFlow | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015. | |
[101] NNF-EAC | 380 | 2 | color | Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336. | |
[102] Heeger++ | 6600 | 5 | gray | Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238. | |
[103] HBM-GC | 330 | 2 | color | A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015. | |
[104] FFV1MT | 358 | 5 | gray | F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015. | |
[105] ROF-ND | 4 | 2 | color | S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015. | |
[106] DeepFlow2 | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015. | |
[107] HAST | 2667 | 2 | color | Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221. | |
[108] FlowFields | 15 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015. | |
[109] SVFilterOh | 1.56 | 2 | color | Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788. | |
[110] FlowNetS+ft+v | 0.5 | 2 | color | Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235. | |
[111] CombBMOF | 51 | 2 | color | M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.) | |
[112] PMMST | 182 | 2 | color | F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015. | |
[113] DF-Auto | 70 | 2 | color | N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015. | |
[114] CPM-Flow | 3 | 2 | color | Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241. | |
[115] CNN-flow-warp+ref | 1.4 | 3 | color | D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016. | |
[116] Steered-L1 | 804 | 2 | color | Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016. | |
[117] StereoOF-V1MT | 343 | 2 | gray | Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132. | |
[118] PGM-C | 5 | 2 | color | Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016. | |
[119] RNLOD-Flow | 1040 | 2 | gray | C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017. | |
[120] FlowNet2 | 0.091 | 2 | color | Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900. | |
[121] S2F-IF | 20 | 2 | color | Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765. | |
[122] BriefMatch | 0.068 | 2 | gray | G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62. | |
[123] OAR-Flow | 60 | 2 | color | Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20. | |
[124] AdaConv-v1 | 2.8 | 2 | color | Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017. | |
[125] SepConv-v1 | 0.2 | 2 | color | Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017. | |
[126] ProbFlowFields | 37 | 2 | color | A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017. | |
[127] UnFlow | 0.12 | 2 | color | Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018. | |
[128] FlowFields+ | 10.5 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017. | |
[129] IIOF-NLDP | 150 | 2 | color | D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017. | |
[130] SuperSlomo | 0.5 | 2 | color | Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325. | |
[131] EPMNet | 0.061 | 2 | color | Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119. | |
[132] OFRF | 90 | 2 | color | Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020. | |
[133] 3DFlow | 328 | 2 | color | J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018. | |
[134] CtxSyn | 0.07 | 2 | color | Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018. | |
[135] DMF_ROB | 10 | 2 | color | ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[136] JOF | 657 | 2 | gray | C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018. | |
[137] AVG_FLOW_ROB | N/A | 2 | N/A | Average flow field of ROB 2018 training set. | |
[138] LiteFlowNet | 0.06 | 2 | color | T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018. | |
[139] AugFNG_ROB | 0.10 | all | color | Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834. | |
[140] ResPWCR_ROB | 0.2 | 2 | color | Anonymous. Learning optical flow with residual connections. ROB 2018 submission. | |
[141] FF++_ROB | 17.43 | 2 | color | R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018. | |
[142] ProFlow_ROB | 76 | 3 | color | Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277. | |
[143] PWC-Net_RVC | 0.069 | 2 | color | D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018. Also RVC 2020 baseline submission. | |
[144] WOLF_ROB | 0.02 | 2 | color | Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission. | |
[145] LFNet_ROB | 0.068 | 2 | color | Anonymous. Learning a flow network. ROB 2018 submission. | |
[146] WRT | 9 | 2 | color | L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018. | |
[147] EAI-Flow | 2.1 | 2 | color | Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678. | |
[148] ContinualFlow_ROB | 0.5 | all | color | Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018. | |
[149] CyclicGen | 0.088 | 2 | color | Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323. | |
[150] TOF-M | 0.393 | 2 | color | Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017. | |
[151] MPRN | 0.32 | 4 | color | Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361. | |
[152] DAIN | 0.13 | 2 | color | Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019. | |
[153] FRUCnet | 0.65 | 2 | color | Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019. | |
[154] OFRI | 0.31 | 2 | color | Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743. | |
[155] CompactFlow_ROB | 0.05 | 2 | color | Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387. | |
[156] SegFlow | 3.2 | 2 | color | Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018. | |
[157] HCFN | 0.18 | 2 | color | Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116. | |
[158] FGME | 0.23 | 2 | color | Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020. | |
[159] MS-PFT | 0.44 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020. | |
[160] MEMC-Net+ | 0.12 | 2 | color | Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018. | |
[161] ADC | 0.01 | 2 | color | Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424. | |
[162] DSepConv | 0.3 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020. | |
[163] MAF-net | 0.3 | 2 | color | Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021. | |
[164] STAR-Net | 0.049 | 2 | color | Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430. | |
[165] AdaCoF | 0.03 | 2 | color | Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available. | |
[166] TC-GAN | 0.13 | 2 | color | Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111. | |
[167] FeFlow | 0.52 | 2 | color | Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) |
|
[168] DAI | 0.23 | 2 | color | Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404. | |
[169] SoftSplat | 0.1 | 2 | color | Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020. | |
[170] STSR | 5.35 | 2 | color | Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340. | |
[171] BMBC | 0.77 | 2 | color | Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095. | |
[172] GDCN | 1.0 | 2 | color | Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347. | |
[173] EDSC | 0.56 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020. | |
[174] CoT-AMFlow | 0.04 | 2 | color | Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36. | |
[175] TVL1_RVC | 11.6 | 2 | color | RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013. | |
[176] H+S_RVC | 44.7 | 2 | color | RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013. | |
[177] PRAFlow_RVC | 0.34 | 2 | color | Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission. | |
[178] VCN_RVC | 0.84 | 2 | color | Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission. | |
[179] RAFT-TF_RVC | 1.51 | 2 | color | Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission. | |
[180] IRR-PWC_RVC | 0.18 | 2 | color | Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission. | |
[181] C-RAFT_RVC | 0.60 | 2 | color | Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission. | |
[182] LSM_FLOW_RVC | 0.2 | 2 | color | Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission. | |
[183] MV_VFI | 0.23 | 2 | color | Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission. | |
[184] DistillNet | 0.12 | 2 | color | Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534. | |
[185] SepConv++ | 0.1 | 2 | color | Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021. | |
[186] EAFI | 0.18 | 2 | color | Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020. | |
[187] UnDAF | 0.04 | 2 | color | Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236. | |
[188] FLAVR | 0.029 | all | color | Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300. | |
[189] PBOFVI | 150 | 2 | color | Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021. | |
[190] SoftsplatAug | 0.17 | 2 | color | Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245. |