Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
A95 angle 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] | 6.8 | 6.80 2 | 47.4 70 | 3.53 1 | 5.31 4 | 30.0 6 | 5.25 13 | 4.10 2 | 25.5 3 | 3.30 3 | 1.60 1 | 47.6 12 | 1.34 1 | 9.19 1 | 12.0 1 | 4.78 1 | 4.00 1 | 18.0 4 | 3.50 1 | 3.21 2 | 8.07 14 | 1.99 5 | 2.08 5 | 4.16 7 | 1.38 4 |
RAFT-it [194] | 10.8 | 7.67 6 | 49.9 88 | 4.13 6 | 5.85 10 | 29.7 5 | 5.30 15 | 4.37 3 | 33.2 13 | 3.45 4 | 1.89 2 | 11.6 2 | 1.66 3 | 9.86 4 | 13.5 9 | 5.91 8 | 5.05 3 | 12.3 2 | 5.18 4 | 4.94 25 | 8.90 32 | 1.93 4 | 2.03 3 | 3.50 2 | 1.73 6 |
NNF-Local [75] | 14.5 | 7.47 4 | 40.1 10 | 3.98 5 | 6.49 18 | 30.3 7 | 5.60 23 | 5.82 7 | 26.1 4 | 4.68 22 | 3.86 14 | 53.5 13 | 2.99 23 | 9.77 3 | 12.4 3 | 5.36 5 | 8.67 10 | 31.8 11 | 7.03 8 | 5.10 33 | 10.1 70 | 3.70 21 | 2.31 14 | 5.34 18 | 1.21 2 |
MS_RAFT+_RVC [195] | 14.5 | 7.63 5 | 48.2 75 | 3.68 2 | 9.18 53 | 26.2 1 | 9.78 100 | 5.20 5 | 40.1 27 | 4.83 27 | 1.92 3 | 25.7 6 | 1.64 2 | 9.37 2 | 12.3 2 | 5.13 3 | 4.72 2 | 10.3 1 | 4.70 3 | 2.88 1 | 8.57 21 | 1.59 1 | 1.86 2 | 2.98 1 | 1.33 3 |
NN-field [71] | 18.2 | 8.38 16 | 43.1 28 | 4.19 7 | 7.34 31 | 28.7 4 | 6.26 34 | 5.82 7 | 28.9 8 | 4.68 22 | 2.94 5 | 54.1 14 | 2.16 6 | 10.4 7 | 13.2 6 | 5.24 4 | 6.12 4 | 17.5 3 | 4.46 2 | 6.24 71 | 10.6 88 | 4.10 23 | 2.35 18 | 6.44 29 | 1.14 1 |
MDP-Flow2 [68] | 22.5 | 8.02 10 | 38.6 6 | 5.75 26 | 5.17 2 | 31.1 8 | 4.55 3 | 5.48 6 | 30.8 11 | 4.22 13 | 4.49 25 | 99.9 96 | 3.27 33 | 11.3 18 | 13.4 8 | 8.04 28 | 10.8 22 | 54.4 48 | 10.5 29 | 4.84 18 | 9.33 46 | 4.31 29 | 2.69 34 | 4.85 12 | 2.20 9 |
PMMST [112] | 24.2 | 8.63 20 | 31.3 1 | 6.03 31 | 8.51 44 | 26.8 3 | 8.18 69 | 7.50 16 | 28.0 7 | 6.07 44 | 4.26 22 | 34.8 9 | 3.29 34 | 10.9 11 | 13.2 6 | 6.26 10 | 10.4 20 | 29.9 10 | 9.42 18 | 5.00 28 | 10.1 70 | 4.37 30 | 3.25 48 | 4.40 9 | 3.36 20 |
OFLAF [78] | 24.6 | 7.70 8 | 39.8 8 | 4.74 12 | 6.40 17 | 32.5 13 | 5.82 29 | 4.73 4 | 25.3 2 | 3.96 9 | 4.47 24 | 99.9 96 | 3.55 53 | 10.2 6 | 13.0 4 | 6.29 11 | 13.3 47 | 42.1 27 | 9.90 25 | 5.10 33 | 8.01 11 | 4.66 42 | 2.75 35 | 5.59 22 | 6.33 53 |
RAFT-TF_RVC [179] | 25.0 | 11.9 66 | 60.0 139 | 4.37 8 | 7.08 23 | 35.2 21 | 6.40 38 | 8.50 25 | 40.6 31 | 7.83 66 | 2.53 4 | 10.8 1 | 1.95 4 | 11.2 17 | 14.1 19 | 6.03 9 | 6.86 6 | 18.4 5 | 6.78 6 | 4.67 14 | 9.33 46 | 1.83 3 | 2.57 28 | 4.73 11 | 2.23 10 |
CoT-AMFlow [174] | 29.8 | 8.40 17 | 41.2 17 | 6.40 37 | 5.67 7 | 31.4 9 | 5.14 12 | 6.10 11 | 37.4 19 | 4.73 24 | 4.68 28 | 99.9 96 | 3.35 40 | 11.3 18 | 13.6 11 | 9.40 59 | 10.2 17 | 54.9 50 | 9.76 24 | 5.14 36 | 9.97 66 | 4.51 36 | 2.79 36 | 5.28 17 | 3.75 29 |
nLayers [57] | 33.7 | 8.19 13 | 45.3 55 | 4.62 10 | 9.65 69 | 31.7 11 | 8.88 90 | 8.87 27 | 33.6 14 | 8.22 73 | 3.62 10 | 99.9 96 | 2.93 20 | 10.5 8 | 13.6 11 | 6.52 12 | 11.3 29 | 33.4 12 | 9.45 20 | 6.02 66 | 8.56 20 | 4.99 49 | 2.31 14 | 6.80 34 | 5.53 46 |
NNF-EAC [101] | 35.9 | 8.80 22 | 40.8 14 | 6.14 34 | 6.13 12 | 39.3 36 | 5.36 16 | 6.97 13 | 35.1 16 | 4.73 24 | 5.83 51 | 87.9 77 | 3.49 49 | 12.1 37 | 14.6 27 | 8.87 40 | 12.5 43 | 41.2 23 | 11.8 49 | 5.35 45 | 10.1 70 | 4.61 39 | 3.19 45 | 7.62 46 | 3.99 34 |
UnDAF [187] | 36.6 | 8.95 25 | 46.1 59 | 6.07 33 | 5.77 9 | 32.1 12 | 4.85 7 | 8.11 20 | 34.6 15 | 4.52 17 | 4.79 33 | 99.9 96 | 3.31 37 | 11.4 21 | 13.6 11 | 8.98 45 | 11.9 37 | 55.4 52 | 10.2 27 | 5.18 38 | 10.0 68 | 4.57 38 | 5.19 80 | 10.4 68 | 3.76 30 |
PRAFlow_RVC [177] | 36.9 | 12.3 72 | 53.1 102 | 6.42 38 | 9.74 71 | 34.8 18 | 8.93 93 | 13.5 56 | 41.8 34 | 9.99 77 | 3.59 8 | 99.9 96 | 3.06 25 | 11.7 26 | 14.8 36 | 6.69 13 | 6.64 5 | 20.5 8 | 6.99 7 | 3.90 4 | 9.57 53 | 1.60 2 | 2.49 25 | 4.60 10 | 1.77 7 |
ComponentFusion [94] | 37.4 | 8.30 15 | 49.1 81 | 5.87 29 | 5.69 8 | 35.4 23 | 5.40 17 | 7.24 14 | 35.3 17 | 4.99 30 | 3.69 11 | 99.9 96 | 2.32 9 | 11.7 26 | 14.1 19 | 8.75 38 | 15.8 80 | 66.6 77 | 15.0 92 | 5.71 55 | 8.88 31 | 5.09 57 | 2.64 31 | 5.25 16 | 3.68 26 |
FC-2Layers-FF [74] | 38.6 | 8.26 14 | 41.4 19 | 6.27 35 | 8.85 48 | 37.9 30 | 7.81 53 | 6.02 10 | 31.8 12 | 6.25 46 | 3.91 16 | 88.8 80 | 2.86 18 | 11.0 14 | 13.7 15 | 7.20 16 | 16.5 88 | 40.4 19 | 16.3 106 | 7.14 92 | 10.7 92 | 6.61 81 | 2.15 7 | 3.87 4 | 2.77 12 |
LME [70] | 39.8 | 7.85 9 | 42.7 26 | 6.01 30 | 5.33 5 | 34.6 16 | 4.91 9 | 14.6 61 | 54.5 66 | 40.7 129 | 4.66 27 | 73.0 21 | 3.25 30 | 11.5 23 | 13.8 17 | 9.65 68 | 11.6 30 | 70.4 88 | 12.1 54 | 5.14 36 | 9.97 66 | 4.51 36 | 2.86 37 | 6.45 30 | 4.29 40 |
FESL [72] | 39.8 | 7.69 7 | 40.2 11 | 4.90 13 | 11.0 95 | 48.5 69 | 9.07 95 | 10.5 37 | 42.1 36 | 6.42 48 | 3.60 9 | 99.9 96 | 2.55 12 | 10.9 11 | 13.6 11 | 8.86 39 | 11.1 27 | 36.4 14 | 10.6 30 | 6.73 86 | 10.2 74 | 5.95 69 | 2.51 27 | 5.37 20 | 3.35 19 |
HAST [107] | 40.7 | 6.42 1 | 43.9 37 | 3.97 4 | 7.16 26 | 33.1 14 | 5.92 31 | 3.76 1 | 23.5 1 | 2.83 1 | 3.36 6 | 99.9 96 | 2.08 5 | 10.0 5 | 13.0 4 | 4.83 2 | 16.7 93 | 59.3 57 | 19.4 127 | 11.3 138 | 12.9 126 | 17.6 148 | 2.67 33 | 4.13 6 | 2.93 15 |
TC/T-Flow [77] | 41.1 | 9.01 27 | 38.1 4 | 3.81 3 | 6.64 20 | 55.1 91 | 4.62 4 | 8.13 21 | 46.4 52 | 4.20 12 | 5.32 43 | 99.9 96 | 2.88 19 | 11.5 23 | 14.1 19 | 7.28 18 | 8.85 11 | 38.5 17 | 9.44 19 | 5.85 62 | 10.7 92 | 10.0 124 | 3.61 57 | 10.0 64 | 8.53 88 |
Layers++ [37] | 43.5 | 9.07 28 | 44.4 40 | 8.41 73 | 8.47 43 | 31.5 10 | 8.03 62 | 5.85 9 | 37.9 21 | 6.02 43 | 3.76 13 | 62.6 15 | 2.79 15 | 10.5 8 | 13.5 9 | 8.22 33 | 17.6 101 | 55.0 51 | 14.5 89 | 7.44 99 | 10.9 96 | 5.70 68 | 2.27 12 | 4.86 13 | 9.14 92 |
PMF [73] | 43.8 | 9.38 35 | 48.9 79 | 4.67 11 | 7.10 24 | 37.5 27 | 5.58 22 | 7.91 18 | 30.0 10 | 4.06 10 | 4.89 39 | 99.9 96 | 3.29 34 | 10.6 10 | 14.0 18 | 5.76 7 | 12.4 42 | 54.8 49 | 11.5 42 | 11.2 137 | 17.9 157 | 11.1 129 | 2.06 4 | 4.95 15 | 4.00 35 |
WLIF-Flow [91] | 44.0 | 8.04 11 | 40.7 12 | 5.53 22 | 7.98 39 | 34.6 16 | 7.20 46 | 8.75 26 | 40.5 29 | 5.74 41 | 4.27 23 | 96.8 93 | 2.94 21 | 13.4 99 | 16.1 105 | 9.77 72 | 13.5 51 | 41.3 25 | 11.8 49 | 5.65 52 | 9.12 38 | 5.96 70 | 2.29 13 | 7.30 39 | 6.96 64 |
3DFlow [133] | 44.1 | 9.37 33 | 41.4 19 | 5.02 15 | 7.10 24 | 38.0 31 | 5.51 21 | 7.41 15 | 53.2 64 | 3.81 8 | 4.74 29 | 14.8 4 | 4.00 66 | 12.0 35 | 15.2 54 | 8.89 42 | 19.9 120 | 60.3 58 | 18.1 123 | 8.06 107 | 9.24 43 | 10.1 125 | 2.26 10 | 4.12 5 | 2.04 8 |
ALD-Flow [66] | 44.7 | 8.18 12 | 41.6 24 | 4.51 9 | 6.32 15 | 54.8 89 | 5.03 11 | 10.7 41 | 61.8 74 | 4.24 14 | 4.24 21 | 99.9 96 | 2.61 13 | 11.7 26 | 14.3 22 | 7.21 17 | 10.8 22 | 61.4 60 | 9.93 26 | 5.96 65 | 9.55 52 | 9.77 123 | 3.87 63 | 15.7 77 | 9.38 100 |
Efficient-NL [60] | 46.5 | 8.40 17 | 43.6 34 | 5.38 20 | 9.12 52 | 37.4 26 | 7.83 55 | 11.1 45 | 56.6 68 | 6.16 45 | 5.71 48 | 99.9 96 | 3.32 38 | 11.3 18 | 14.7 31 | 7.66 20 | 16.6 92 | 37.6 15 | 12.7 64 | 6.93 90 | 10.8 94 | 5.98 73 | 2.89 39 | 5.47 21 | 2.90 14 |
SVFilterOh [109] | 47.2 | 8.96 26 | 55.2 116 | 5.63 23 | 7.20 27 | 37.8 29 | 6.39 37 | 6.18 12 | 43.0 40 | 5.02 31 | 3.71 12 | 99.9 96 | 2.49 11 | 11.1 16 | 14.3 22 | 5.54 6 | 13.5 51 | 50.6 42 | 14.1 82 | 10.1 129 | 16.8 152 | 12.4 140 | 2.20 8 | 4.91 14 | 2.50 11 |
RNLOD-Flow [119] | 47.5 | 7.26 3 | 38.7 7 | 5.25 19 | 7.65 35 | 43.0 46 | 6.20 33 | 12.7 52 | 75.2 82 | 4.59 19 | 3.52 7 | 99.9 96 | 2.46 10 | 11.4 21 | 14.9 41 | 7.74 22 | 16.2 82 | 40.2 18 | 16.2 103 | 8.20 109 | 12.2 116 | 7.63 101 | 2.49 25 | 5.98 25 | 7.10 68 |
ProFlow_ROB [142] | 48.0 | 10.5 50 | 51.4 91 | 5.14 18 | 7.28 28 | 50.8 76 | 5.66 25 | 17.6 65 | 65.7 78 | 5.43 36 | 3.88 15 | 98.0 94 | 2.18 7 | 12.3 46 | 15.2 54 | 7.81 24 | 12.1 40 | 52.1 44 | 12.9 67 | 4.24 8 | 9.88 63 | 3.68 19 | 3.79 62 | 19.4 84 | 6.62 58 |
AGIF+OF [84] | 48.2 | 8.89 24 | 44.1 38 | 6.77 42 | 10.2 78 | 44.4 53 | 8.51 85 | 10.2 34 | 43.5 42 | 6.63 52 | 4.80 34 | 99.9 96 | 3.25 30 | 11.7 26 | 14.7 31 | 9.52 63 | 13.7 54 | 40.9 20 | 12.6 61 | 5.73 58 | 8.99 33 | 5.96 70 | 2.36 20 | 7.50 42 | 7.55 72 |
TC-Flow [46] | 49.9 | 8.59 19 | 41.0 16 | 5.12 16 | 5.47 6 | 45.6 57 | 4.31 2 | 10.2 34 | 94.7 128 | 3.49 5 | 6.08 57 | 99.9 96 | 3.50 50 | 11.9 33 | 14.5 25 | 7.90 26 | 11.9 37 | 61.7 63 | 11.5 42 | 5.72 56 | 9.85 61 | 11.5 134 | 4.02 67 | 15.0 75 | 9.14 92 |
PH-Flow [99] | 50.3 | 10.2 44 | 44.6 44 | 7.86 55 | 9.41 60 | 42.0 42 | 8.11 65 | 8.41 24 | 38.9 23 | 7.40 62 | 6.39 64 | 99.9 96 | 3.93 63 | 11.8 31 | 14.5 25 | 7.72 21 | 13.8 56 | 42.9 31 | 13.1 69 | 7.21 93 | 10.3 77 | 7.61 100 | 2.34 17 | 4.20 8 | 4.20 38 |
IROF++ [58] | 50.5 | 9.29 32 | 45.0 52 | 6.30 36 | 9.55 65 | 43.0 46 | 8.20 70 | 10.8 42 | 43.1 41 | 7.57 63 | 6.28 62 | 99.9 96 | 3.90 61 | 12.2 41 | 14.8 36 | 9.41 61 | 15.2 75 | 44.1 36 | 14.5 89 | 5.27 40 | 9.48 50 | 3.69 20 | 2.62 30 | 6.48 31 | 4.14 37 |
PWC-Net_RVC [143] | 51.2 | 17.5 106 | 49.3 84 | 9.65 98 | 9.55 65 | 42.8 44 | 8.41 75 | 19.6 69 | 46.1 51 | 10.6 81 | 6.18 61 | 74.3 23 | 3.39 42 | 12.4 49 | 15.4 67 | 8.92 43 | 11.8 34 | 45.5 37 | 11.5 42 | 4.32 10 | 9.79 57 | 2.49 10 | 3.08 41 | 6.38 28 | 2.86 13 |
Correlation Flow [76] | 52.0 | 9.27 31 | 38.3 5 | 5.40 21 | 6.33 16 | 36.7 24 | 4.85 7 | 18.4 67 | 99.9 138 | 3.58 6 | 4.87 37 | 35.8 10 | 3.47 46 | 12.9 74 | 15.8 86 | 9.17 53 | 16.0 81 | 68.6 81 | 16.5 113 | 6.59 82 | 9.85 61 | 7.93 109 | 2.88 38 | 7.57 45 | 3.06 16 |
GMFlow_RVC [196] | 52.2 | 19.5 109 | 45.1 53 | 13.9 123 | 9.94 75 | 26.3 2 | 10.2 104 | 9.46 30 | 27.3 6 | 7.68 65 | 6.61 69 | 39.2 11 | 5.12 93 | 13.1 85 | 16.4 118 | 9.40 59 | 10.0 15 | 20.2 7 | 9.27 17 | 7.28 96 | 10.5 85 | 4.10 23 | 1.84 1 | 3.73 3 | 1.45 5 |
Classic+CPF [82] | 52.3 | 9.64 38 | 43.4 30 | 7.93 58 | 9.43 61 | 46.1 60 | 7.82 54 | 10.6 40 | 51.0 59 | 6.68 53 | 5.09 41 | 99.9 96 | 3.22 29 | 12.0 35 | 15.2 54 | 9.15 51 | 14.7 67 | 34.4 13 | 13.4 74 | 6.42 76 | 10.1 70 | 6.89 86 | 2.26 10 | 6.77 33 | 7.08 67 |
JOF [136] | 53.8 | 8.67 21 | 45.9 57 | 6.43 39 | 10.3 81 | 48.5 69 | 8.94 94 | 8.37 23 | 39.4 25 | 7.19 57 | 4.81 35 | 99.9 96 | 2.79 15 | 11.9 33 | 14.6 27 | 8.03 27 | 13.9 59 | 43.0 32 | 10.8 31 | 9.32 122 | 11.4 104 | 11.3 133 | 2.21 9 | 7.25 37 | 7.07 66 |
CostFilter [40] | 54.5 | 10.5 50 | 46.8 67 | 6.98 46 | 7.51 32 | 38.1 32 | 6.31 36 | 9.22 28 | 29.7 9 | 4.74 26 | 5.86 53 | 99.9 96 | 3.97 65 | 10.9 11 | 14.3 22 | 6.77 14 | 13.4 48 | 56.1 53 | 12.3 57 | 11.6 141 | 20.5 161 | 14.2 142 | 2.12 6 | 8.52 53 | 6.71 60 |
ProbFlowFields [126] | 55.5 | 16.3 96 | 53.8 106 | 10.9 114 | 7.72 36 | 40.6 40 | 7.12 43 | 14.1 59 | 45.2 50 | 10.5 79 | 6.67 70 | 62.6 15 | 4.39 81 | 12.9 74 | 15.4 67 | 9.64 67 | 10.1 16 | 63.2 69 | 10.8 31 | 4.86 20 | 8.16 17 | 4.69 44 | 3.36 50 | 9.23 60 | 3.72 28 |
VCN_RVC [178] | 56.0 | 17.3 104 | 47.3 69 | 10.1 105 | 10.3 81 | 43.6 50 | 9.46 99 | 15.8 64 | 37.4 19 | 12.4 89 | 8.26 83 | 73.5 22 | 4.90 91 | 12.2 41 | 15.3 62 | 8.42 35 | 11.7 32 | 53.2 46 | 12.2 55 | 4.55 12 | 8.36 19 | 3.12 16 | 3.52 52 | 8.67 57 | 4.35 41 |
HCFN [157] | 56.4 | 8.86 23 | 40.7 12 | 5.67 24 | 5.27 3 | 43.8 51 | 4.64 5 | 7.53 17 | 39.4 25 | 3.23 2 | 4.87 37 | 99.9 96 | 3.58 54 | 11.0 14 | 13.7 15 | 7.15 15 | 15.4 77 | 53.4 47 | 16.3 106 | 14.7 154 | 16.8 152 | 17.8 149 | 5.63 88 | 12.6 70 | 10.6 117 |
IIOF-NLDP [129] | 57.3 | 12.0 67 | 43.5 32 | 5.86 28 | 9.35 56 | 35.0 19 | 6.81 41 | 11.2 46 | 88.4 123 | 4.51 16 | 6.09 58 | 28.8 7 | 4.09 73 | 14.6 132 | 18.4 146 | 9.71 69 | 14.6 66 | 66.2 76 | 14.7 91 | 4.90 24 | 9.54 51 | 4.82 47 | 3.09 42 | 7.73 49 | 3.18 17 |
Sparse-NonSparse [56] | 57.9 | 9.96 39 | 44.2 39 | 8.85 82 | 9.39 59 | 50.6 75 | 8.08 64 | 10.1 33 | 43.7 44 | 7.21 58 | 6.10 59 | 88.2 78 | 3.41 44 | 12.5 55 | 15.5 77 | 8.96 44 | 16.3 84 | 41.9 26 | 16.2 103 | 6.48 78 | 9.05 35 | 6.27 77 | 2.33 16 | 7.33 40 | 7.76 80 |
MLDP_OF [87] | 58.2 | 11.8 65 | 41.7 25 | 8.40 72 | 6.97 21 | 35.2 21 | 5.88 30 | 11.3 49 | 65.3 77 | 5.23 34 | 4.76 32 | 99.9 96 | 3.09 26 | 12.2 41 | 14.8 36 | 8.87 40 | 13.4 48 | 48.1 39 | 17.2 119 | 10.0 128 | 10.9 96 | 18.1 150 | 3.58 56 | 8.07 52 | 4.53 44 |
Ramp [62] | 58.6 | 10.2 44 | 44.4 40 | 8.09 67 | 9.47 62 | 46.1 60 | 8.17 68 | 9.51 31 | 42.4 38 | 6.88 56 | 5.40 44 | 99.9 96 | 3.53 51 | 12.5 55 | 15.2 54 | 9.71 69 | 16.7 93 | 42.1 27 | 16.5 113 | 6.76 87 | 10.0 68 | 7.07 90 | 2.46 24 | 5.84 24 | 5.24 45 |
LSM [39] | 58.8 | 10.0 42 | 42.9 27 | 8.48 74 | 9.36 58 | 49.6 73 | 7.99 59 | 10.5 37 | 43.6 43 | 6.80 54 | 5.80 49 | 88.6 79 | 3.38 41 | 12.5 55 | 15.4 67 | 9.03 47 | 16.5 88 | 42.3 29 | 16.3 106 | 6.94 91 | 9.84 58 | 6.71 82 | 2.42 23 | 7.96 51 | 7.72 77 |
WRT [146] | 58.9 | 10.9 55 | 48.8 77 | 5.12 16 | 10.2 78 | 39.2 34 | 8.48 81 | 39.5 116 | 99.9 138 | 4.62 20 | 4.75 31 | 14.6 3 | 3.39 42 | 11.7 26 | 15.0 45 | 9.93 81 | 21.2 124 | 64.7 74 | 17.5 121 | 5.35 45 | 8.80 28 | 5.37 63 | 3.22 47 | 7.63 47 | 3.38 22 |
OAR-Flow [123] | 59.0 | 11.1 59 | 48.8 77 | 5.85 27 | 9.88 72 | 82.9 163 | 6.47 39 | 27.3 91 | 99.9 138 | 8.06 69 | 6.75 71 | 99.9 96 | 2.80 17 | 12.4 49 | 15.1 52 | 8.20 32 | 10.3 18 | 58.1 55 | 8.37 13 | 4.07 5 | 8.06 13 | 5.45 65 | 4.81 77 | 9.74 63 | 6.36 54 |
MCPFlow_RVC [197] | 61.1 | 22.3 128 | 57.7 129 | 14.2 126 | 15.2 109 | 40.3 38 | 14.0 117 | 22.2 77 | 42.4 38 | 19.2 109 | 5.49 46 | 32.3 8 | 4.07 71 | 12.7 66 | 16.2 110 | 7.35 19 | 9.94 14 | 19.3 6 | 9.67 22 | 4.77 16 | 10.3 77 | 2.34 9 | 3.72 60 | 7.07 35 | 4.12 36 |
Classic+NL [31] | 62.5 | 10.1 43 | 44.9 50 | 8.90 83 | 9.49 63 | 51.6 79 | 7.87 56 | 9.93 32 | 43.9 46 | 7.31 61 | 6.07 56 | 99.9 96 | 3.78 59 | 12.5 55 | 15.3 62 | 9.06 48 | 17.1 97 | 41.0 21 | 15.8 100 | 7.32 97 | 10.8 94 | 6.80 85 | 2.35 18 | 5.62 23 | 7.69 76 |
FMOF [92] | 62.6 | 9.17 29 | 43.6 34 | 8.04 64 | 10.0 76 | 48.1 66 | 8.48 81 | 8.35 22 | 38.3 22 | 6.49 50 | 5.08 40 | 99.9 96 | 3.45 45 | 12.6 61 | 15.4 67 | 9.19 54 | 18.1 108 | 41.2 23 | 15.5 97 | 6.67 85 | 10.6 88 | 7.47 97 | 3.00 40 | 16.1 79 | 7.74 78 |
MDP-Flow [26] | 62.8 | 11.2 60 | 43.1 28 | 9.86 102 | 8.14 42 | 35.1 20 | 8.21 71 | 11.2 46 | 42.1 36 | 9.44 76 | 6.41 65 | 99.9 96 | 4.20 77 | 12.2 41 | 14.6 27 | 10.0 84 | 11.7 32 | 63.6 70 | 9.60 21 | 5.56 50 | 10.9 96 | 4.39 31 | 5.78 89 | 99.9 158 | 8.99 89 |
TV-L1-MCT [64] | 63.2 | 9.57 36 | 44.7 46 | 8.66 77 | 10.9 94 | 48.1 66 | 9.11 96 | 11.8 50 | 58.1 70 | 6.61 51 | 4.74 29 | 99.9 96 | 3.34 39 | 12.9 74 | 15.2 54 | 9.89 77 | 17.8 105 | 47.8 38 | 16.0 102 | 5.28 41 | 8.09 15 | 7.71 102 | 3.33 49 | 7.26 38 | 7.53 71 |
IROF-TV [53] | 63.5 | 10.4 48 | 44.5 43 | 8.16 68 | 9.69 70 | 51.1 78 | 8.44 76 | 12.6 51 | 46.8 53 | 7.27 60 | 6.80 72 | 87.5 76 | 3.93 63 | 13.0 79 | 15.7 82 | 10.4 89 | 18.3 110 | 86.9 151 | 13.7 78 | 4.44 11 | 7.40 5 | 3.05 14 | 2.60 29 | 7.55 44 | 7.56 73 |
CombBMOF [111] | 63.8 | 12.5 73 | 41.3 18 | 6.50 41 | 8.58 46 | 36.9 25 | 6.88 42 | 10.9 43 | 35.9 18 | 5.21 33 | 10.4 93 | 85.0 74 | 5.90 103 | 11.6 25 | 15.2 54 | 8.15 30 | 27.3 136 | 60.9 59 | 35.6 149 | 9.20 120 | 14.7 141 | 6.75 84 | 3.17 44 | 7.53 43 | 4.20 38 |
NL-TV-NCC [25] | 64.5 | 10.7 53 | 40.8 14 | 6.45 40 | 8.52 45 | 41.1 41 | 6.30 35 | 11.2 46 | 93.6 127 | 4.18 11 | 5.99 55 | 75.9 27 | 4.02 67 | 13.2 88 | 16.2 110 | 10.1 86 | 16.7 93 | 70.9 90 | 16.3 106 | 6.56 81 | 9.91 65 | 7.05 89 | 4.76 75 | 16.9 80 | 3.56 24 |
COFM [59] | 65.0 | 9.37 33 | 55.5 118 | 6.86 44 | 7.28 28 | 44.2 52 | 6.17 32 | 14.3 60 | 47.6 56 | 8.22 73 | 4.15 19 | 99.9 96 | 2.23 8 | 13.2 88 | 16.2 110 | 12.2 123 | 17.6 101 | 75.4 98 | 15.5 97 | 6.20 70 | 8.77 27 | 7.35 94 | 3.62 58 | 5.35 19 | 6.43 56 |
OFH [38] | 65.8 | 12.6 74 | 43.4 30 | 9.45 91 | 7.30 30 | 64.4 102 | 5.27 14 | 27.6 92 | 99.9 138 | 4.87 29 | 6.60 68 | 99.9 96 | 3.74 57 | 12.4 49 | 14.7 31 | 9.62 65 | 15.5 78 | 74.1 95 | 15.6 99 | 4.60 13 | 9.39 48 | 4.64 40 | 5.39 84 | 26.0 96 | 6.68 59 |
FlowFields+ [128] | 66.4 | 20.3 113 | 52.0 95 | 10.3 110 | 10.3 81 | 44.8 55 | 8.44 76 | 19.5 68 | 40.2 28 | 14.1 96 | 10.2 91 | 66.6 17 | 6.28 108 | 12.8 70 | 15.4 67 | 9.97 82 | 10.3 18 | 61.8 64 | 10.2 27 | 4.85 19 | 10.9 96 | 4.79 46 | 3.97 65 | 12.8 71 | 3.85 31 |
Adaptive [20] | 66.7 | 10.2 44 | 46.1 59 | 4.95 14 | 9.63 67 | 55.4 92 | 7.80 52 | 36.7 111 | 99.9 138 | 7.64 64 | 6.15 60 | 78.7 30 | 2.96 22 | 12.1 37 | 14.8 36 | 9.09 49 | 12.3 41 | 85.8 149 | 6.06 5 | 8.72 114 | 12.5 122 | 4.97 48 | 3.55 55 | 34.8 100 | 9.13 91 |
S2F-IF [121] | 67.1 | 20.0 112 | 51.4 91 | 9.91 103 | 9.64 68 | 48.3 68 | 7.93 57 | 19.7 70 | 41.7 33 | 13.6 95 | 9.98 89 | 84.3 70 | 5.40 97 | 12.8 70 | 15.3 62 | 9.92 80 | 10.9 25 | 62.4 67 | 10.9 35 | 5.00 28 | 10.4 82 | 5.30 62 | 3.71 59 | 8.55 55 | 3.87 32 |
AggregFlow [95] | 67.6 | 13.2 76 | 62.1 144 | 6.79 43 | 14.9 108 | 73.1 113 | 10.6 107 | 26.8 90 | 55.1 67 | 20.5 111 | 5.48 45 | 99.9 96 | 3.67 55 | 12.5 55 | 15.0 45 | 7.76 23 | 8.55 9 | 38.2 16 | 8.90 15 | 5.78 59 | 10.6 88 | 4.74 45 | 5.43 85 | 8.53 54 | 7.58 74 |
FlowFields [108] | 68.0 | 20.3 113 | 52.3 97 | 10.2 106 | 10.2 78 | 49.0 71 | 8.46 79 | 20.3 71 | 40.5 29 | 14.7 98 | 10.8 98 | 76.6 28 | 6.16 106 | 12.9 74 | 15.4 67 | 10.0 84 | 11.1 27 | 69.9 85 | 11.0 37 | 4.97 27 | 8.63 24 | 5.12 59 | 4.04 69 | 14.0 72 | 3.98 33 |
S2D-Matching [83] | 68.7 | 9.96 39 | 53.0 101 | 8.51 75 | 9.53 64 | 53.0 81 | 7.94 58 | 20.5 72 | 99.9 138 | 6.80 54 | 5.30 42 | 83.0 33 | 3.53 51 | 12.4 49 | 15.2 54 | 9.16 52 | 17.3 98 | 41.1 22 | 16.8 117 | 7.75 103 | 10.5 85 | 7.90 108 | 2.36 20 | 6.34 27 | 9.58 105 |
Complementary OF [21] | 69.3 | 13.6 80 | 46.2 61 | 9.35 88 | 6.20 13 | 50.4 74 | 4.92 10 | 12.8 54 | 58.8 72 | 5.45 37 | 7.89 79 | 99.9 96 | 5.59 99 | 12.3 46 | 14.6 27 | 9.99 83 | 18.9 115 | 69.9 85 | 14.3 86 | 5.44 47 | 7.80 7 | 7.78 104 | 6.13 95 | 26.9 97 | 9.66 108 |
Sparse Occlusion [54] | 69.6 | 9.98 41 | 41.5 23 | 7.82 54 | 9.00 51 | 40.5 39 | 8.28 73 | 13.5 56 | 85.5 120 | 5.96 42 | 5.82 50 | 99.9 96 | 3.90 61 | 13.0 79 | 15.9 89 | 9.77 72 | 13.8 56 | 49.9 41 | 12.3 57 | 13.6 152 | 15.7 148 | 7.81 106 | 3.51 51 | 9.05 58 | 6.42 55 |
HBM-GC [103] | 69.9 | 10.9 55 | 57.5 128 | 7.03 48 | 9.35 56 | 40.2 37 | 8.80 88 | 8.09 19 | 52.3 62 | 6.42 48 | 6.91 74 | 84.3 70 | 6.17 107 | 11.8 31 | 14.7 31 | 8.40 34 | 14.7 67 | 43.2 33 | 12.6 61 | 9.81 127 | 17.8 156 | 8.50 114 | 3.54 54 | 10.1 65 | 10.1 113 |
2DHMM-SAS [90] | 71.5 | 10.3 47 | 44.8 48 | 8.03 63 | 10.5 89 | 52.4 80 | 8.21 71 | 21.6 74 | 97.4 133 | 8.20 72 | 6.88 73 | 99.9 96 | 3.86 60 | 12.4 49 | 15.0 45 | 9.87 75 | 17.7 103 | 43.3 34 | 15.9 101 | 6.81 88 | 10.2 74 | 7.15 93 | 2.65 32 | 7.68 48 | 7.29 69 |
PBOFVI [189] | 71.6 | 10.9 55 | 47.7 74 | 8.77 79 | 6.98 22 | 53.2 83 | 5.50 20 | 12.7 52 | 99.9 138 | 3.61 7 | 4.15 19 | 78.8 31 | 3.02 24 | 14.4 128 | 17.6 137 | 11.3 108 | 18.0 106 | 51.9 43 | 18.5 126 | 5.67 54 | 12.2 116 | 7.80 105 | 3.11 43 | 10.1 65 | 8.10 83 |
ACK-Prior [27] | 72.8 | 10.7 53 | 37.9 3 | 7.90 57 | 6.01 11 | 38.5 33 | 4.80 6 | 10.2 34 | 41.5 32 | 4.35 15 | 4.56 26 | 99.9 96 | 3.75 58 | 13.2 88 | 15.9 89 | 11.3 108 | 27.3 136 | 82.2 108 | 23.1 136 | 11.6 141 | 14.9 145 | 16.2 146 | 6.43 100 | 15.5 76 | 6.11 50 |
SimpleFlow [49] | 72.8 | 11.3 62 | 46.6 63 | 9.79 101 | 10.7 92 | 45.0 56 | 9.15 97 | 23.1 79 | 99.9 138 | 8.38 75 | 8.00 81 | 99.9 96 | 3.72 56 | 12.7 66 | 15.5 77 | 9.36 58 | 16.3 84 | 42.6 30 | 15.3 96 | 5.91 64 | 9.61 54 | 5.39 64 | 2.39 22 | 7.08 36 | 9.41 101 |
EPPM w/o HM [86] | 72.9 | 15.3 91 | 41.4 19 | 8.08 66 | 7.60 33 | 33.9 15 | 5.66 25 | 13.0 55 | 47.0 54 | 5.57 38 | 8.73 86 | 99.9 96 | 4.81 90 | 12.6 61 | 15.7 82 | 10.8 98 | 18.6 112 | 62.9 68 | 16.4 111 | 11.9 146 | 12.5 122 | 17.2 147 | 3.20 46 | 7.49 41 | 6.00 48 |
RFlow [88] | 73.1 | 11.5 63 | 45.3 55 | 8.80 81 | 6.22 14 | 49.2 72 | 5.41 18 | 26.2 88 | 99.9 138 | 5.04 32 | 4.14 18 | 99.9 96 | 3.11 27 | 12.6 61 | 15.0 45 | 9.87 75 | 16.5 88 | 83.2 144 | 13.8 81 | 6.62 83 | 8.58 22 | 6.16 74 | 6.33 98 | 99.9 158 | 12.0 123 |
PGM-C [118] | 73.2 | 20.6 117 | 54.2 109 | 9.59 96 | 10.1 77 | 60.8 96 | 8.47 80 | 22.3 78 | 44.3 49 | 14.8 101 | 10.7 97 | 99.9 96 | 4.15 75 | 13.1 85 | 15.4 67 | 9.90 78 | 11.8 34 | 64.6 73 | 12.0 53 | 4.86 20 | 7.96 9 | 5.01 52 | 4.78 76 | 14.4 73 | 7.01 65 |
SegFlow [156] | 73.2 | 20.5 115 | 54.3 110 | 9.56 93 | 10.3 81 | 62.6 100 | 8.50 83 | 21.9 75 | 44.1 48 | 14.7 98 | 10.6 95 | 99.9 96 | 4.05 69 | 13.2 88 | 15.3 62 | 10.1 86 | 11.8 34 | 65.3 75 | 12.3 57 | 5.03 31 | 8.62 23 | 5.06 56 | 4.18 70 | 10.1 65 | 5.68 47 |
Occlusion-TV-L1 [63] | 73.3 | 10.4 48 | 44.9 50 | 6.90 45 | 8.77 47 | 53.3 84 | 7.54 48 | 33.8 106 | 99.9 138 | 7.96 67 | 5.88 54 | 99.9 96 | 3.48 48 | 13.6 108 | 16.3 114 | 10.6 94 | 9.50 12 | 80.1 105 | 8.60 14 | 6.12 68 | 8.69 25 | 4.39 31 | 6.52 103 | 99.9 158 | 9.37 97 |
ROF-ND [105] | 75.6 | 12.0 67 | 39.9 9 | 8.22 71 | 6.49 18 | 45.6 57 | 5.49 19 | 13.5 56 | 92.7 124 | 4.83 27 | 8.05 82 | 23.7 5 | 5.54 98 | 14.2 124 | 17.5 133 | 11.2 106 | 20.1 122 | 72.0 92 | 15.0 92 | 13.0 150 | 13.3 131 | 10.5 128 | 3.52 52 | 6.67 32 | 3.36 20 |
CPM-Flow [114] | 78.5 | 20.6 117 | 54.3 110 | 9.58 94 | 10.3 81 | 62.5 99 | 8.50 83 | 21.9 75 | 43.8 45 | 14.7 98 | 10.6 95 | 99.9 96 | 4.06 70 | 13.2 88 | 15.4 67 | 9.85 74 | 12.6 44 | 68.9 82 | 13.3 71 | 5.02 30 | 9.16 40 | 5.04 54 | 5.27 81 | 19.2 82 | 9.63 107 |
ComplOF-FED-GPU [35] | 79.3 | 13.2 76 | 44.7 46 | 7.95 59 | 9.18 53 | 82.6 162 | 5.63 24 | 15.3 62 | 58.5 71 | 5.67 39 | 7.59 77 | 99.9 96 | 4.68 86 | 12.3 46 | 14.8 36 | 9.20 55 | 18.2 109 | 83.8 145 | 16.4 111 | 7.54 101 | 9.84 58 | 11.1 129 | 5.44 86 | 31.6 99 | 7.74 78 |
SRR-TVOF-NL [89] | 79.9 | 14.4 87 | 46.7 64 | 8.18 70 | 13.1 102 | 74.0 115 | 8.44 76 | 24.1 83 | 63.2 76 | 11.9 88 | 6.51 67 | 85.1 75 | 3.25 30 | 12.1 37 | 15.0 45 | 10.3 88 | 17.5 99 | 61.6 61 | 13.4 74 | 10.4 133 | 12.3 119 | 8.92 117 | 5.52 87 | 7.83 50 | 7.58 74 |
EpicFlow [100] | 80.1 | 20.6 117 | 54.1 108 | 9.59 96 | 10.3 81 | 62.9 101 | 8.55 86 | 26.3 89 | 99.4 137 | 15.1 103 | 10.4 93 | 99.9 96 | 4.07 71 | 13.1 85 | 15.4 67 | 9.90 78 | 11.6 30 | 67.3 79 | 11.9 52 | 4.86 20 | 7.97 10 | 4.99 49 | 5.34 83 | 19.2 82 | 9.74 110 |
Steered-L1 [116] | 80.8 | 9.19 30 | 36.3 2 | 6.06 32 | 4.59 1 | 39.2 34 | 4.30 1 | 9.30 29 | 52.3 62 | 4.57 18 | 4.86 36 | 99.9 96 | 3.30 36 | 13.6 108 | 15.9 89 | 12.3 124 | 24.7 135 | 77.0 101 | 20.2 128 | 15.1 156 | 13.7 136 | 40.0 158 | 14.7 135 | 91.5 156 | 20.9 137 |
C-RAFT_RVC [181] | 80.9 | 31.8 143 | 61.9 143 | 12.9 118 | 21.3 124 | 42.6 43 | 20.0 128 | 25.0 86 | 44.0 47 | 19.5 110 | 12.4 104 | 72.6 19 | 7.52 117 | 13.9 117 | 16.8 125 | 11.8 114 | 10.9 25 | 28.8 9 | 11.3 39 | 6.25 73 | 11.9 112 | 4.64 40 | 3.76 61 | 6.24 26 | 3.26 18 |
TCOF [69] | 81.7 | 13.6 80 | 44.8 48 | 8.02 62 | 9.90 73 | 54.6 88 | 8.02 61 | 31.3 102 | 99.9 138 | 15.4 105 | 6.49 66 | 82.4 32 | 4.76 88 | 14.9 136 | 18.0 143 | 9.50 62 | 9.71 13 | 48.3 40 | 12.6 61 | 10.1 129 | 12.7 124 | 8.96 118 | 4.29 71 | 9.21 59 | 6.80 61 |
DMF_ROB [135] | 82.0 | 16.2 95 | 49.6 86 | 9.96 104 | 9.93 74 | 75.9 117 | 7.56 49 | 30.5 99 | 99.9 138 | 11.8 86 | 16.5 116 | 99.9 96 | 4.36 80 | 12.6 61 | 14.9 41 | 9.62 65 | 12.9 46 | 76.3 100 | 11.5 42 | 4.68 15 | 8.80 28 | 5.10 58 | 7.02 111 | 91.0 155 | 9.62 106 |
DPOF [18] | 82.2 | 17.4 105 | 49.1 81 | 7.77 53 | 12.3 98 | 45.6 57 | 8.91 92 | 10.9 43 | 26.6 5 | 8.09 70 | 7.81 78 | 99.3 95 | 5.31 94 | 13.5 104 | 16.0 100 | 11.0 101 | 17.5 99 | 61.8 64 | 12.2 55 | 13.1 151 | 10.9 96 | 18.1 150 | 5.04 78 | 9.50 62 | 4.49 42 |
DeepFlow2 [106] | 83.1 | 14.3 85 | 47.4 70 | 7.03 48 | 10.4 87 | 77.1 120 | 8.01 60 | 23.3 80 | 99.9 138 | 11.8 86 | 16.1 112 | 99.9 96 | 4.41 82 | 12.4 49 | 15.0 45 | 8.16 31 | 13.4 48 | 68.4 80 | 14.2 83 | 5.65 52 | 9.07 37 | 8.50 114 | 8.52 118 | 92.9 157 | 10.6 117 |
LiteFlowNet [138] | 84.5 | 24.0 132 | 51.5 93 | 13.3 120 | 11.7 96 | 43.1 48 | 9.98 102 | 21.5 73 | 47.6 56 | 13.0 91 | 10.9 100 | 71.9 18 | 6.87 111 | 13.3 97 | 16.2 110 | 11.5 112 | 18.7 113 | 52.2 45 | 16.7 115 | 6.18 69 | 9.32 45 | 4.21 26 | 5.83 91 | 24.4 94 | 7.46 70 |
Aniso. Huber-L1 [22] | 84.5 | 11.7 64 | 43.8 36 | 8.16 68 | 13.6 104 | 66.3 104 | 12.0 110 | 35.9 109 | 99.9 138 | 10.5 79 | 10.0 90 | 72.9 20 | 5.00 92 | 13.4 99 | 16.3 114 | 9.61 64 | 15.1 73 | 63.7 71 | 7.96 12 | 8.96 117 | 11.6 108 | 7.95 110 | 4.02 67 | 26.9 97 | 7.97 82 |
FF++_ROB [141] | 85.2 | 21.4 123 | 55.5 118 | 10.2 106 | 10.6 91 | 54.1 86 | 8.70 87 | 24.1 83 | 59.5 73 | 16.2 107 | 11.5 102 | 74.8 25 | 7.42 115 | 13.0 79 | 15.7 82 | 10.6 94 | 14.7 67 | 70.0 87 | 13.7 78 | 5.31 44 | 8.76 26 | 7.53 99 | 4.57 73 | 14.8 74 | 13.9 127 |
TF+OM [98] | 86.1 | 12.1 69 | 51.3 90 | 7.13 50 | 8.92 50 | 44.4 53 | 8.13 67 | 33.8 106 | 54.4 65 | 45.8 133 | 6.28 62 | 90.1 82 | 4.63 85 | 12.7 66 | 15.2 54 | 10.6 94 | 18.9 115 | 99.9 166 | 11.3 39 | 7.81 104 | 14.2 138 | 6.33 78 | 7.09 112 | 43.5 103 | 8.22 85 |
F-TV-L1 [15] | 87.2 | 15.6 92 | 47.4 70 | 13.4 121 | 18.8 119 | 99.1 172 | 11.6 108 | 43.1 127 | 99.9 138 | 11.3 85 | 14.7 108 | 99.9 96 | 7.03 112 | 12.2 41 | 14.9 41 | 9.00 46 | 13.5 51 | 99.9 166 | 7.56 11 | 6.41 75 | 10.5 85 | 4.23 27 | 3.91 64 | 80.3 115 | 3.38 22 |
CVENG22+RIC [199] | 91.0 | 19.5 109 | 55.1 115 | 8.94 84 | 11.8 97 | 71.1 110 | 8.89 91 | 29.2 93 | 99.9 138 | 14.1 96 | 10.3 92 | 99.9 96 | 4.03 68 | 14.5 131 | 17.7 139 | 11.0 101 | 12.0 39 | 90.1 154 | 11.7 47 | 4.86 20 | 7.94 8 | 4.99 49 | 5.98 93 | 35.9 101 | 9.94 112 |
TV-L1-improved [17] | 91.3 | 10.9 55 | 45.2 54 | 7.42 51 | 8.12 40 | 54.0 85 | 6.79 40 | 36.5 110 | 99.9 138 | 7.26 59 | 5.84 52 | 99.9 96 | 3.15 28 | 13.2 88 | 15.9 89 | 9.11 50 | 22.1 129 | 99.9 166 | 20.8 129 | 9.59 125 | 13.3 131 | 9.04 119 | 6.19 96 | 88.8 152 | 9.71 109 |
SIOF [67] | 91.8 | 10.6 52 | 49.7 87 | 7.01 47 | 14.8 107 | 85.9 165 | 8.40 74 | 49.7 135 | 98.3 134 | 49.2 136 | 12.0 103 | 99.9 96 | 5.88 102 | 13.5 104 | 15.9 89 | 10.8 98 | 16.3 84 | 74.2 96 | 13.6 77 | 5.51 49 | 9.02 34 | 4.42 34 | 6.52 103 | 19.5 87 | 9.85 111 |
CompactFlow_ROB [155] | 92.0 | 34.2 147 | 63.6 147 | 16.6 134 | 19.0 121 | 46.3 62 | 18.4 125 | 37.1 112 | 62.7 75 | 45.3 132 | 15.6 111 | 99.9 96 | 10.6 126 | 13.6 108 | 16.3 114 | 11.1 104 | 14.1 61 | 64.2 72 | 12.8 65 | 4.96 26 | 8.13 16 | 2.28 8 | 5.98 93 | 22.2 90 | 6.91 62 |
Brox et al. [5] | 92.5 | 16.0 93 | 49.2 83 | 12.0 116 | 12.3 98 | 80.4 125 | 10.3 105 | 23.7 82 | 73.1 81 | 13.2 92 | 24.2 125 | 99.9 96 | 4.23 78 | 14.7 133 | 16.8 125 | 15.4 146 | 10.7 21 | 96.7 159 | 9.71 23 | 5.88 63 | 9.05 35 | 3.01 13 | 8.78 119 | 67.7 111 | 9.37 97 |
DeepFlow [85] | 93.3 | 14.7 88 | 49.0 80 | 9.78 100 | 12.9 100 | 79.3 124 | 9.80 101 | 30.1 96 | 96.1 131 | 24.4 117 | 21.4 123 | 99.9 96 | 5.36 96 | 12.5 55 | 15.1 52 | 8.59 36 | 14.0 60 | 71.9 91 | 15.1 95 | 5.46 48 | 8.01 11 | 8.73 116 | 14.2 133 | 99.9 158 | 15.7 133 |
CRTflow [81] | 93.8 | 15.0 89 | 46.3 62 | 7.89 56 | 8.87 49 | 54.9 90 | 7.15 44 | 30.1 96 | 99.9 138 | 8.03 68 | 9.30 88 | 99.9 96 | 4.50 84 | 13.0 79 | 15.7 82 | 8.05 29 | 32.5 141 | 99.9 166 | 34.3 148 | 6.62 83 | 9.72 56 | 7.52 98 | 9.30 122 | 99.9 158 | 14.7 129 |
LocallyOriented [52] | 94.9 | 17.0 103 | 55.7 120 | 8.00 61 | 17.0 116 | 82.3 161 | 12.1 111 | 42.4 125 | 99.9 138 | 14.8 101 | 9.13 87 | 89.2 81 | 4.79 89 | 13.4 99 | 16.1 105 | 9.20 55 | 10.8 22 | 58.1 55 | 11.8 49 | 6.89 89 | 10.6 88 | 7.14 92 | 7.78 117 | 74.9 112 | 9.42 102 |
BriefMatch [122] | 96.0 | 9.63 37 | 44.4 40 | 5.74 25 | 7.64 34 | 51.0 77 | 5.70 27 | 10.5 37 | 39.2 24 | 4.63 21 | 3.95 17 | 99.9 96 | 2.72 14 | 16.2 147 | 17.6 137 | 33.0 159 | 41.4 153 | 99.4 165 | 43.4 155 | 12.7 149 | 13.2 129 | 67.6 162 | 79.5 153 | 99.9 158 | 99.9 189 |
ContinualFlow_ROB [148] | 98.1 | 30.9 140 | 63.0 146 | 13.9 123 | 22.3 126 | 47.9 65 | 20.9 129 | 34.2 108 | 99.9 138 | 31.9 123 | 13.3 105 | 99.9 96 | 7.83 119 | 13.7 114 | 16.5 122 | 11.4 110 | 21.5 126 | 70.6 89 | 21.3 132 | 4.20 7 | 10.3 77 | 2.80 11 | 4.01 66 | 8.59 56 | 3.70 27 |
ResPWCR_ROB [140] | 98.5 | 23.4 130 | 46.7 64 | 16.7 136 | 14.7 106 | 42.9 45 | 13.2 113 | 23.4 81 | 48.7 58 | 22.0 114 | 16.4 115 | 84.5 72 | 11.3 130 | 13.2 88 | 15.8 86 | 12.6 129 | 15.2 75 | 72.1 93 | 16.3 106 | 9.13 119 | 12.3 119 | 7.37 95 | 7.09 112 | 17.6 81 | 9.31 96 |
Classic++ [32] | 98.6 | 11.2 60 | 49.4 85 | 9.13 85 | 9.34 55 | 68.4 107 | 8.11 65 | 30.7 100 | 95.1 130 | 10.2 78 | 5.59 47 | 99.9 96 | 3.47 46 | 13.5 104 | 16.1 105 | 10.4 89 | 19.7 119 | 99.9 166 | 17.6 122 | 8.38 110 | 11.5 107 | 8.30 113 | 7.20 115 | 99.9 158 | 9.54 104 |
Dynamic MRF [7] | 98.6 | 14.0 84 | 50.7 89 | 9.58 94 | 7.75 37 | 85.7 164 | 5.76 28 | 31.5 103 | 99.9 138 | 5.23 34 | 7.97 80 | 99.9 96 | 4.10 74 | 13.0 79 | 15.6 80 | 10.7 97 | 30.4 140 | 99.9 166 | 29.5 145 | 5.64 51 | 7.52 6 | 9.61 122 | 67.3 151 | 99.9 158 | 66.7 151 |
CBF [12] | 99.8 | 12.2 71 | 41.4 19 | 8.65 76 | 16.5 113 | 47.1 64 | 16.6 121 | 24.7 85 | 88.1 122 | 12.9 90 | 11.0 101 | 99.9 96 | 4.18 76 | 14.9 136 | 17.5 133 | 14.0 141 | 15.0 72 | 79.8 104 | 8.97 16 | 14.9 155 | 15.1 146 | 15.9 145 | 5.78 89 | 63.0 110 | 10.1 113 |
Rannacher [23] | 99.9 | 13.8 83 | 47.5 73 | 10.8 113 | 10.5 89 | 62.0 98 | 8.84 89 | 41.1 122 | 99.9 138 | 11.0 83 | 8.49 84 | 99.9 96 | 4.28 79 | 13.5 104 | 16.1 105 | 9.72 71 | 22.5 131 | 99.9 166 | 17.0 118 | 7.66 102 | 9.88 63 | 7.82 107 | 4.72 74 | 75.1 113 | 9.37 97 |
IRR-PWC_RVC [180] | 100.9 | 41.0 153 | 70.3 194 | 16.1 131 | 29.3 134 | 56.2 94 | 26.3 137 | 42.9 126 | 92.7 124 | 53.0 138 | 28.8 133 | 77.5 29 | 23.8 139 | 13.0 79 | 15.8 86 | 10.5 93 | 13.7 54 | 61.6 61 | 11.5 42 | 7.43 98 | 11.9 112 | 4.00 22 | 6.43 100 | 22.6 91 | 6.22 52 |
AugFNG_ROB [139] | 101.5 | 34.3 149 | 65.6 151 | 20.9 142 | 25.8 130 | 66.4 105 | 24.3 133 | 40.9 120 | 99.9 138 | 40.6 128 | 15.2 110 | 96.0 90 | 9.61 122 | 13.4 99 | 15.6 80 | 12.3 124 | 15.1 73 | 73.5 94 | 14.2 83 | 5.29 42 | 11.2 102 | 2.87 12 | 5.30 82 | 19.4 84 | 4.51 43 |
TriFlow [93] | 102.8 | 16.1 94 | 57.1 126 | 7.97 60 | 13.3 103 | 65.2 103 | 12.3 112 | 48.8 132 | 99.9 138 | 61.8 143 | 7.03 75 | 91.4 84 | 5.33 95 | 13.4 99 | 15.3 62 | 11.4 110 | 14.3 65 | 76.1 99 | 13.3 71 | 22.7 161 | 14.3 140 | 26.7 154 | 5.93 92 | 11.8 69 | 7.86 81 |
EAI-Flow [147] | 102.9 | 25.2 133 | 57.0 125 | 16.6 134 | 19.3 122 | 76.7 118 | 14.1 118 | 29.6 95 | 51.5 61 | 22.8 115 | 23.6 124 | 93.8 87 | 10.3 124 | 12.8 70 | 16.0 100 | 10.4 89 | 15.6 79 | 74.4 97 | 14.4 88 | 12.6 148 | 11.3 103 | 6.90 87 | 5.08 79 | 20.5 89 | 8.20 84 |
p-harmonic [29] | 103.4 | 15.1 90 | 48.5 76 | 14.1 125 | 10.4 87 | 53.1 82 | 9.31 98 | 41.9 123 | 99.9 138 | 15.1 103 | 19.4 122 | 99.9 96 | 10.6 126 | 12.7 66 | 14.9 41 | 11.8 114 | 18.0 106 | 85.6 148 | 18.4 125 | 7.85 105 | 10.4 82 | 5.46 66 | 6.98 110 | 99.9 158 | 9.28 95 |
FlowNet2 [120] | 103.5 | 32.0 144 | 68.0 157 | 14.9 128 | 35.2 138 | 77.9 123 | 29.8 143 | 32.9 104 | 51.2 60 | 35.4 126 | 16.3 113 | 99.9 96 | 10.5 125 | 13.2 88 | 15.9 89 | 12.0 117 | 14.1 61 | 99.9 166 | 10.8 31 | 8.84 116 | 20.1 158 | 4.66 42 | 4.49 72 | 9.46 61 | 3.65 25 |
SegOF [10] | 104.4 | 22.8 129 | 54.8 112 | 15.4 130 | 27.9 133 | 56.0 93 | 27.4 138 | 39.3 115 | 87.9 121 | 33.2 125 | 37.5 138 | 75.4 26 | 22.3 137 | 14.4 128 | 16.3 114 | 14.7 144 | 21.7 127 | 99.9 166 | 24.5 138 | 4.09 6 | 7.28 2 | 2.18 7 | 6.79 108 | 48.3 106 | 6.93 63 |
CLG-TV [48] | 104.5 | 12.1 69 | 43.5 32 | 9.42 90 | 14.1 105 | 60.9 97 | 13.2 113 | 33.2 105 | 99.9 138 | 11.2 84 | 10.8 98 | 84.7 73 | 5.82 101 | 14.8 135 | 17.9 141 | 12.1 121 | 13.8 56 | 99.9 166 | 11.3 39 | 10.9 135 | 14.2 138 | 9.22 120 | 6.69 107 | 99.9 158 | 8.52 87 |
DF-Auto [113] | 104.5 | 20.5 115 | 55.9 122 | 9.21 86 | 22.7 127 | 74.8 116 | 19.3 127 | 44.7 129 | 93.5 126 | 57.8 141 | 27.1 130 | 99.9 96 | 5.70 100 | 15.0 139 | 18.9 153 | 11.8 114 | 7.13 7 | 57.9 54 | 7.09 9 | 10.2 132 | 13.9 137 | 4.23 27 | 8.94 120 | 54.0 108 | 9.21 94 |
OFRF [132] | 104.8 | 13.1 75 | 58.6 133 | 9.77 99 | 49.6 151 | 99.9 173 | 43.7 152 | 49.2 133 | 99.9 138 | 32.0 124 | 16.3 113 | 96.4 91 | 10.0 123 | 12.1 37 | 14.7 31 | 7.87 25 | 14.9 71 | 43.6 35 | 13.3 71 | 8.66 113 | 12.0 115 | 11.8 137 | 21.9 141 | 19.7 88 | 36.6 145 |
Local-TV-L1 [65] | 104.8 | 16.5 98 | 52.3 97 | 11.7 115 | 27.7 132 | 96.9 169 | 22.5 131 | 68.8 143 | 99.9 138 | 47.5 134 | 34.6 137 | 99.9 96 | 7.04 113 | 12.6 61 | 15.0 45 | 9.25 57 | 17.7 103 | 84.7 146 | 13.7 78 | 5.09 32 | 7.36 4 | 5.03 53 | 20.7 138 | 88.8 152 | 29.4 143 |
TriangleFlow [30] | 105.4 | 13.2 76 | 46.8 67 | 9.41 89 | 10.8 93 | 73.2 114 | 7.30 47 | 26.1 87 | 99.9 138 | 5.70 40 | 7.23 76 | 99.9 96 | 4.46 83 | 17.0 152 | 21.3 158 | 15.2 145 | 23.0 132 | 69.8 84 | 22.9 135 | 9.71 126 | 16.1 149 | 9.40 121 | 6.89 109 | 23.8 92 | 11.5 121 |
LSM_FLOW_RVC [182] | 106.2 | 34.2 147 | 59.8 138 | 25.5 148 | 21.5 125 | 99.9 173 | 18.4 125 | 37.6 113 | 99.9 138 | 29.5 119 | 26.8 129 | 99.9 96 | 16.7 136 | 13.3 97 | 16.4 118 | 11.1 104 | 21.3 125 | 67.0 78 | 21.3 132 | 5.21 39 | 8.80 28 | 3.50 17 | 6.38 99 | 15.8 78 | 6.00 48 |
Bartels [41] | 106.3 | 13.3 79 | 55.0 113 | 10.2 106 | 8.13 41 | 43.2 49 | 7.67 50 | 18.1 66 | 69.0 80 | 6.30 47 | 8.49 84 | 99.9 96 | 6.05 105 | 13.9 117 | 16.1 105 | 13.9 139 | 21.8 128 | 99.9 166 | 21.5 134 | 10.6 134 | 13.5 133 | 20.3 152 | 12.3 128 | 99.9 158 | 26.9 141 |
Fusion [6] | 106.4 | 16.3 96 | 53.8 106 | 12.5 117 | 7.93 38 | 37.7 28 | 7.75 51 | 15.6 63 | 41.8 34 | 13.2 92 | 13.5 106 | 83.1 34 | 7.77 118 | 15.4 141 | 18.5 147 | 14.2 143 | 33.1 142 | 89.0 152 | 24.8 140 | 11.8 144 | 14.7 141 | 8.27 112 | 11.4 126 | 99.9 158 | 13.3 125 |
EPMNet [131] | 106.8 | 29.4 139 | 62.1 144 | 16.4 133 | 36.2 139 | 95.3 168 | 29.0 142 | 30.2 98 | 47.4 55 | 30.9 122 | 18.3 119 | 99.9 96 | 11.1 128 | 13.2 88 | 15.9 89 | 12.0 117 | 14.1 61 | 99.9 166 | 10.8 31 | 8.19 108 | 16.9 154 | 4.18 25 | 6.63 106 | 19.4 84 | 6.18 51 |
WOLF_ROB [144] | 108.2 | 21.5 124 | 55.2 116 | 10.2 106 | 37.6 141 | 99.9 173 | 17.3 122 | 54.7 138 | 99.9 138 | 23.9 116 | 25.1 126 | 99.9 96 | 12.8 131 | 12.8 70 | 15.4 67 | 11.2 106 | 18.5 111 | 61.8 64 | 17.2 119 | 5.80 61 | 9.26 44 | 6.20 76 | 11.4 126 | 24.3 93 | 15.7 133 |
LFNet_ROB [145] | 112.8 | 28.9 138 | 53.4 104 | 17.2 137 | 15.3 111 | 46.9 63 | 13.7 116 | 31.0 101 | 96.3 132 | 21.7 113 | 18.4 120 | 92.1 85 | 14.4 133 | 13.7 114 | 16.6 123 | 12.0 117 | 18.8 114 | 90.4 155 | 16.7 115 | 6.48 78 | 10.9 96 | 5.97 72 | 6.22 97 | 99.9 158 | 10.3 115 |
LDOF [28] | 114.2 | 17.9 108 | 53.5 105 | 8.72 78 | 18.7 118 | 92.6 167 | 11.8 109 | 29.5 94 | 67.1 79 | 20.9 112 | 29.0 134 | 99.9 96 | 8.92 121 | 14.2 124 | 16.4 118 | 13.7 136 | 18.9 115 | 97.5 163 | 15.0 92 | 6.26 74 | 10.3 77 | 10.1 125 | 10.4 124 | 99.9 158 | 10.3 115 |
StereoFlow [44] | 114.2 | 48.0 159 | 74.6 197 | 41.1 160 | 61.0 156 | 99.9 173 | 51.6 155 | 71.4 144 | 99.9 138 | 63.9 145 | 65.6 153 | 99.9 96 | 61.2 153 | 16.2 147 | 15.9 89 | 22.6 153 | 7.22 8 | 77.8 103 | 7.39 10 | 3.38 3 | 7.35 3 | 1.99 5 | 7.18 114 | 99.9 158 | 11.4 120 |
CNN-flow-warp+ref [115] | 114.6 | 21.3 122 | 57.3 127 | 15.1 129 | 16.8 115 | 54.4 87 | 15.9 120 | 41.0 121 | 99.9 138 | 28.8 118 | 28.6 132 | 99.9 96 | 7.45 116 | 14.0 121 | 15.9 89 | 14.0 141 | 16.5 88 | 84.8 147 | 10.9 35 | 5.30 43 | 8.23 18 | 8.13 111 | 99.9 189 | 99.9 158 | 99.9 189 |
FlowNetS+ft+v [110] | 114.8 | 16.5 98 | 52.1 96 | 8.06 65 | 17.4 117 | 76.9 119 | 13.4 115 | 46.3 130 | 99.9 138 | 30.4 121 | 29.8 135 | 99.9 96 | 13.8 132 | 15.5 142 | 18.5 147 | 13.8 138 | 12.7 45 | 89.5 153 | 11.7 47 | 9.24 121 | 13.5 133 | 12.1 138 | 7.39 116 | 57.9 109 | 9.52 103 |
Filter Flow [19] | 115.8 | 21.6 126 | 57.7 129 | 14.4 127 | 24.6 129 | 77.5 122 | 18.1 123 | 54.3 137 | 80.8 83 | 66.3 149 | 52.8 146 | 91.0 83 | 46.5 147 | 13.6 108 | 16.0 100 | 12.3 124 | 17.0 96 | 69.6 83 | 14.2 83 | 12.0 147 | 16.1 149 | 7.39 96 | 6.58 105 | 37.5 102 | 8.36 86 |
Shiralkar [42] | 115.9 | 16.8 101 | 44.6 44 | 9.46 92 | 16.5 113 | 98.8 171 | 8.05 63 | 42.0 124 | 99.9 138 | 10.8 82 | 18.4 120 | 99.9 96 | 8.02 120 | 12.9 74 | 15.5 77 | 10.4 89 | 30.2 139 | 99.9 166 | 25.1 141 | 11.4 140 | 11.8 111 | 15.8 144 | 22.2 142 | 99.9 158 | 17.5 136 |
Learning Flow [11] | 118.0 | 13.7 82 | 52.8 99 | 7.67 52 | 12.9 100 | 87.1 166 | 10.0 103 | 40.5 118 | 95.0 129 | 13.4 94 | 38.1 139 | 99.9 96 | 4.74 87 | 17.1 154 | 21.7 159 | 12.5 128 | 24.2 134 | 99.9 166 | 13.5 76 | 7.95 106 | 12.7 124 | 6.98 88 | 23.9 144 | 99.9 158 | 14.9 130 |
StereoOF-V1MT [117] | 118.2 | 16.5 98 | 46.0 58 | 9.27 87 | 18.9 120 | 99.9 173 | 7.16 45 | 40.5 118 | 99.9 138 | 8.18 71 | 14.7 108 | 96.4 91 | 6.30 109 | 14.1 123 | 16.8 125 | 12.9 131 | 29.9 138 | 91.4 156 | 27.0 143 | 5.78 59 | 10.4 82 | 10.4 127 | 99.9 189 | 99.9 158 | 99.9 189 |
Second-order prior [8] | 118.3 | 14.3 85 | 46.7 64 | 8.79 80 | 15.2 109 | 72.5 112 | 10.5 106 | 39.2 114 | 99.9 138 | 16.6 108 | 17.5 117 | 99.9 96 | 6.01 104 | 14.4 128 | 17.5 133 | 10.8 98 | 38.6 151 | 99.9 166 | 24.7 139 | 11.3 138 | 12.2 116 | 11.2 131 | 9.13 121 | 89.5 154 | 15.6 132 |
Ad-TV-NDC [36] | 118.5 | 31.0 141 | 53.3 103 | 33.1 156 | 70.2 157 | 99.9 173 | 49.0 154 | 93.2 190 | 99.9 138 | 54.0 139 | 38.9 140 | 95.0 88 | 29.4 141 | 13.8 116 | 17.3 132 | 8.71 37 | 14.7 67 | 77.1 102 | 13.0 68 | 6.24 71 | 9.84 58 | 5.19 61 | 46.4 149 | 76.4 114 | 54.0 149 |
GraphCuts [14] | 120.6 | 21.7 127 | 52.8 99 | 10.4 111 | 39.2 143 | 99.9 173 | 23.1 132 | 39.7 117 | 58.0 69 | 49.6 137 | 25.6 128 | 74.6 24 | 7.31 114 | 13.6 108 | 15.9 89 | 13.2 134 | 37.8 148 | 97.6 164 | 16.2 103 | 9.36 123 | 11.4 104 | 11.7 135 | 10.3 123 | 99.9 158 | 15.0 131 |
IAOF2 [51] | 121.3 | 16.8 101 | 59.5 136 | 10.5 112 | 20.1 123 | 69.0 109 | 18.1 123 | 53.3 136 | 99.9 138 | 56.8 140 | 55.3 150 | 95.0 88 | 54.7 151 | 14.2 124 | 17.2 131 | 11.0 101 | 19.2 118 | 81.1 106 | 14.3 86 | 11.8 144 | 13.2 129 | 13.0 141 | 13.5 130 | 45.0 104 | 9.00 90 |
TVL1_RVC [175] | 123.0 | 31.1 142 | 60.0 139 | 29.1 152 | 48.7 150 | 99.9 173 | 41.9 150 | 91.6 189 | 99.9 138 | 71.6 152 | 52.2 145 | 99.9 96 | 43.9 146 | 14.2 124 | 16.9 128 | 12.0 117 | 14.2 64 | 99.9 166 | 13.2 70 | 4.82 17 | 9.21 41 | 3.55 18 | 21.1 139 | 99.9 158 | 22.6 139 |
2D-CLG [1] | 124.0 | 46.1 157 | 67.5 156 | 28.2 151 | 39.5 144 | 77.3 121 | 38.9 146 | 93.9 192 | 99.9 138 | 74.9 156 | 53.6 147 | 99.9 96 | 51.0 149 | 13.9 117 | 15.9 89 | 13.5 135 | 24.0 133 | 99.9 166 | 21.2 130 | 4.28 9 | 7.24 1 | 4.50 35 | 12.7 129 | 99.9 158 | 11.6 122 |
HBpMotionGpu [43] | 125.8 | 19.5 109 | 63.6 147 | 13.5 122 | 31.0 135 | 99.9 173 | 27.4 138 | 99.9 195 | 99.9 138 | 59.3 142 | 18.2 118 | 99.9 96 | 6.69 110 | 13.6 108 | 16.0 100 | 12.4 127 | 16.2 82 | 91.5 157 | 11.1 38 | 11.1 136 | 13.0 128 | 6.73 83 | 21.3 140 | 99.9 158 | 21.6 138 |
SPSA-learn [13] | 127.0 | 23.6 131 | 55.7 120 | 20.1 141 | 32.9 137 | 99.9 173 | 25.2 134 | 91.2 188 | 99.9 138 | 64.5 147 | 49.6 143 | 99.9 96 | 31.2 142 | 14.0 121 | 16.0 100 | 13.0 133 | 19.9 120 | 99.9 166 | 23.3 137 | 6.53 80 | 9.13 39 | 4.40 33 | 15.8 136 | 99.9 158 | 16.5 135 |
Modified CLG [34] | 128.0 | 27.9 136 | 58.6 133 | 23.4 145 | 26.5 131 | 71.1 110 | 26.2 136 | 93.4 191 | 99.9 138 | 73.1 154 | 49.2 142 | 99.9 96 | 22.6 138 | 15.2 140 | 18.1 144 | 13.7 136 | 16.3 84 | 99.9 166 | 12.8 65 | 6.43 77 | 10.2 74 | 11.7 135 | 11.3 125 | 99.9 158 | 11.3 119 |
IAOF [50] | 129.6 | 20.6 117 | 55.0 113 | 17.4 138 | 36.6 140 | 99.9 173 | 27.6 140 | 99.9 195 | 99.9 138 | 75.5 157 | 32.7 136 | 93.3 86 | 25.5 140 | 13.9 117 | 16.6 123 | 12.1 121 | 36.5 146 | 92.3 158 | 12.3 57 | 9.40 124 | 11.7 109 | 7.13 91 | 26.2 145 | 47.4 105 | 28.8 142 |
UnFlow [127] | 129.9 | 49.8 160 | 69.9 193 | 23.3 144 | 32.8 136 | 57.8 95 | 33.0 144 | 49.4 134 | 98.6 135 | 39.8 127 | 53.6 147 | 99.9 96 | 52.1 150 | 16.2 147 | 18.5 147 | 20.6 150 | 35.3 145 | 99.9 166 | 38.4 151 | 8.81 115 | 11.4 104 | 3.08 15 | 6.46 102 | 99.9 158 | 6.47 57 |
GroupFlow [9] | 131.5 | 27.3 135 | 66.8 154 | 21.6 143 | 41.1 145 | 99.9 173 | 35.1 145 | 71.4 144 | 99.9 138 | 61.8 143 | 25.1 126 | 99.9 96 | 14.4 133 | 14.7 133 | 17.9 141 | 11.7 113 | 40.6 152 | 97.2 162 | 40.6 153 | 5.72 56 | 11.7 109 | 6.48 79 | 16.4 137 | 53.8 107 | 23.0 140 |
Black & Anandan [4] | 132.9 | 21.5 124 | 51.7 94 | 19.8 140 | 38.6 142 | 99.9 173 | 25.8 135 | 81.3 148 | 99.9 138 | 65.5 148 | 50.4 144 | 99.9 96 | 31.6 143 | 15.5 142 | 19.1 154 | 12.8 130 | 22.4 130 | 96.8 161 | 18.2 124 | 10.1 129 | 12.4 121 | 5.16 60 | 13.9 132 | 99.9 158 | 12.9 124 |
BlockOverlap [61] | 134.4 | 17.6 107 | 56.5 124 | 13.1 119 | 24.0 128 | 66.9 106 | 21.5 130 | 67.6 142 | 99.9 138 | 49.0 135 | 28.2 131 | 99.9 96 | 15.2 135 | 17.6 157 | 18.3 145 | 32.7 158 | 38.1 149 | 81.6 107 | 26.6 142 | 14.5 153 | 15.5 147 | 67.6 162 | 39.8 147 | 82.5 116 | 84.7 152 |
Nguyen [33] | 134.5 | 27.2 134 | 56.2 123 | 18.7 139 | 46.7 149 | 99.9 173 | 44.1 153 | 97.7 194 | 99.9 138 | 74.1 155 | 45.7 141 | 99.9 96 | 38.0 144 | 16.4 150 | 17.7 139 | 21.8 152 | 20.8 123 | 99.9 166 | 21.2 130 | 7.21 93 | 9.42 49 | 5.61 67 | 14.6 134 | 99.9 158 | 14.2 128 |
2bit-BM-tele [96] | 134.8 | 20.8 121 | 59.0 135 | 16.3 132 | 16.4 112 | 68.5 108 | 15.3 119 | 43.9 128 | 99.9 138 | 15.4 105 | 14.6 107 | 99.9 96 | 11.2 129 | 15.6 144 | 17.5 133 | 16.8 148 | 34.9 144 | 99.9 166 | 31.1 146 | 18.8 159 | 20.4 160 | 30.8 155 | 23.7 143 | 99.9 158 | 61.9 150 |
Horn & Schunck [3] | 142.8 | 28.8 137 | 57.7 129 | 25.3 147 | 41.1 145 | 99.9 173 | 28.2 141 | 80.0 147 | 99.9 138 | 75.9 158 | 75.5 154 | 99.9 96 | 66.3 154 | 15.7 145 | 18.5 147 | 13.9 139 | 41.9 154 | 99.9 166 | 41.4 154 | 11.6 141 | 13.6 135 | 6.16 74 | 45.4 148 | 99.9 158 | 39.5 146 |
SILK [80] | 143.7 | 33.3 146 | 64.6 149 | 29.2 154 | 46.3 148 | 99.9 173 | 39.4 147 | 95.0 193 | 99.9 138 | 66.5 150 | 56.7 151 | 99.9 96 | 50.2 148 | 16.1 146 | 18.7 151 | 17.2 149 | 48.7 155 | 99.9 166 | 37.3 150 | 7.26 95 | 9.22 42 | 14.5 143 | 70.9 152 | 99.9 158 | 51.7 148 |
H+S_RVC [176] | 144.2 | 50.2 161 | 65.4 150 | 33.8 157 | 46.0 147 | 99.9 173 | 42.5 151 | 76.9 146 | 99.9 138 | 71.7 153 | 96.0 196 | 99.9 96 | 91.7 196 | 17.4 156 | 16.4 118 | 30.2 156 | 74.6 160 | 99.9 166 | 80.6 161 | 5.13 35 | 9.69 55 | 5.05 55 | 99.9 189 | 99.9 158 | 96.1 188 |
Heeger++ [102] | 144.4 | 33.0 145 | 58.3 132 | 23.6 146 | 60.7 154 | 99.9 173 | 39.4 147 | 59.1 139 | 99.9 138 | 30.1 120 | 86.5 195 | 99.9 96 | 70.5 155 | 14.9 136 | 17.1 129 | 12.9 131 | 76.5 161 | 99.9 166 | 79.8 160 | 7.49 100 | 12.9 126 | 6.59 80 | 99.9 189 | 99.9 158 | 99.9 189 |
AdaConv-v1 [124] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
SepConv-v1 [125] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
SuperSlomo [130] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
CtxSyn [134] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
CyclicGen [149] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
TOF-M [150] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
MPRN [151] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
DAIN [152] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
FRUCnet [153] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
OFRI [154] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
FGME [158] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
MS-PFT [159] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
MEMC-Net+ [160] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
ADC [161] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
DSepConv [162] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
MAF-net [163] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
STAR-Net [164] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
AdaCoF [165] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
TC-GAN [166] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
FeFlow [167] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
DAI [168] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
SoftSplat [169] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
STSR [170] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
BMBC [171] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
GDCN [172] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
EDSC [173] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
MV_VFI [183] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
DistillNet [184] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
SepConv++ [185] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
EAFI [186] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
FLAVR [188] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
SoftsplatAug [190] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
ProBoost-Net [191] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
IDIAL [192] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
IFRNet [193] | 146.4 | 66.7 164 | 69.5 158 | 54.6 162 | 80.0 159 | 82.0 126 | 79.5 160 | 81.7 149 | 82.0 84 | 80.9 161 | 82.3 157 | 83.1 34 | 82.6 159 | 85.8 162 | 85.9 162 | 85.2 162 | 88.2 163 | 83.0 109 | 82.9 163 | 75.7 165 | 67.1 165 | 77.8 165 | 85.1 154 | 86.4 117 | 84.8 153 |
TI-DOFE [24] | 148.8 | 40.2 152 | 61.2 142 | 38.6 159 | 60.2 153 | 99.9 173 | 53.7 156 | 90.4 187 | 99.9 138 | 78.2 160 | 83.9 193 | 99.9 96 | 82.8 194 | 16.6 151 | 19.4 156 | 16.4 147 | 38.1 149 | 99.9 166 | 38.7 152 | 8.51 112 | 10.3 77 | 7.75 103 | 56.3 150 | 99.9 158 | 49.7 147 |
HCIC-L [97] | 148.8 | 44.4 156 | 66.7 153 | 29.1 152 | 99.9 196 | 99.9 173 | 99.9 196 | 47.8 131 | 99.9 138 | 44.6 131 | 58.5 152 | 99.9 96 | 55.7 152 | 20.3 159 | 20.6 157 | 24.0 155 | 33.9 143 | 86.5 150 | 33.6 147 | 38.0 163 | 49.5 163 | 36.0 156 | 13.7 131 | 25.8 95 | 13.7 126 |
PGAM+LK [55] | 154.2 | 43.6 154 | 67.1 155 | 43.7 161 | 73.8 158 | 99.9 173 | 77.5 158 | 61.9 140 | 82.9 119 | 63.9 145 | 76.6 155 | 99.9 96 | 72.5 156 | 17.1 154 | 17.1 129 | 31.6 157 | 66.2 158 | 99.9 166 | 64.8 158 | 18.9 160 | 20.3 159 | 22.1 153 | 99.9 189 | 99.9 158 | 99.9 189 |
Adaptive flow [45] | 155.5 | 34.4 150 | 59.7 137 | 29.7 155 | 84.5 194 | 99.9 173 | 77.7 159 | 87.6 184 | 99.9 138 | 92.8 197 | 54.9 149 | 99.9 96 | 39.3 145 | 20.6 160 | 23.8 161 | 20.9 151 | 37.5 147 | 96.7 159 | 29.2 144 | 35.2 162 | 30.1 162 | 58.6 161 | 38.1 146 | 99.9 158 | 33.0 144 |
FFV1MT [104] | 156.2 | 36.4 151 | 71.0 195 | 25.8 149 | 50.3 152 | 99.9 173 | 39.7 149 | 65.6 141 | 99.1 136 | 41.6 130 | 99.9 197 | 99.9 96 | 97.4 198 | 20.2 158 | 19.3 155 | 33.1 160 | 62.5 157 | 99.9 166 | 71.1 159 | 9.04 118 | 14.8 143 | 11.2 131 | 99.9 189 | 99.9 158 | 99.9 189 |
SLK [47] | 158.0 | 53.1 162 | 66.3 152 | 59.5 198 | 60.9 155 | 98.1 170 | 58.6 157 | 89.7 185 | 99.9 138 | 67.7 151 | 99.9 197 | 99.9 96 | 95.1 197 | 17.0 152 | 18.8 152 | 23.5 154 | 56.6 156 | 99.9 166 | 51.2 156 | 8.43 111 | 11.9 112 | 12.2 139 | 99.9 189 | 99.9 158 | 99.9 189 |
FOLKI [16] | 165.6 | 43.8 155 | 74.4 196 | 38.0 158 | 99.9 196 | 99.9 173 | 99.9 196 | 89.7 185 | 99.9 138 | 76.2 159 | 85.0 194 | 99.9 96 | 81.0 158 | 23.2 161 | 22.5 160 | 38.8 161 | 66.2 158 | 99.9 166 | 62.7 157 | 17.0 158 | 17.6 155 | 42.6 159 | 99.9 189 | 99.9 158 | 99.9 189 |
Periodicity [79] | 170.0 | 54.4 163 | 84.3 198 | 26.5 150 | 99.9 196 | 99.9 173 | 99.9 196 | 99.9 195 | 99.9 138 | 99.9 198 | 81.4 156 | 99.9 96 | 76.3 157 | 99.9 198 | 99.9 197 | 99.9 198 | 99.9 198 | 99.9 166 | 99.9 198 | 6.06 67 | 14.8 143 | 70.6 164 | 99.9 189 | 99.9 158 | 99.9 189 |
Pyramid LK [2] | 173.2 | 47.7 158 | 60.7 141 | 56.1 197 | 88.6 195 | 99.9 173 | 91.9 195 | 99.9 195 | 99.9 138 | 89.4 196 | 83.0 192 | 99.9 96 | 83.2 195 | 98.4 197 | 99.9 197 | 87.9 197 | 87.4 162 | 99.9 166 | 81.4 162 | 16.9 157 | 16.6 151 | 57.0 160 | 99.9 189 | 99.9 158 | 99.9 189 |
AVG_FLOW_ROB [137] | 181.7 | 99.9 199 | 99.9 199 | 99.9 199 | 99.9 196 | 99.9 173 | 99.9 196 | 99.9 195 | 99.9 138 | 99.9 198 | 99.9 197 | 99.9 96 | 99.9 199 | 99.9 198 | 99.9 197 | 99.9 198 | 99.9 198 | 99.9 166 | 99.9 198 | 48.6 164 | 52.0 164 | 38.2 157 | 99.9 189 | 99.9 158 | 99.9 189 |
Army - Ground-truth flow |
Color encoding of flow vectors |
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. |