Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R10.0
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 [194]4.2 3.53 3 15.5 4 1.05 2 2.34 7 12.3 2 1.50 14 2.56 3 9.15 3 0.54 3 0.49 2 5.44 2 0.00 1 4.90 4 7.33 4 1.58 3 0.96 2 5.98 2 0.63 3 0.26 1 2.59 6 0.05 16 0.47 7 1.72 7 0.00 1
RAFT-it+_RVC [198]4.8 3.28 2 14.9 3 1.01 1 2.31 6 11.5 1 1.75 22 2.49 2 8.90 2 0.20 1 0.71 4 7.49 4 0.00 1 4.33 1 6.51 1 1.26 1 1.04 3 7.65 3 0.04 1 0.31 9 3.06 18 0.02 3 0.57 11 2.08 14 0.01 2
NNF-Local [75]14.2 3.83 7 16.9 12 1.87 11 2.64 11 16.1 17 1.33 11 3.02 5 10.7 5 1.33 22 2.79 26 18.9 33 1.11 27 4.82 3 6.85 3 1.73 5 4.13 9 14.6 8 2.27 7 0.52 35 5.08 70 0.00 1 0.28 3 1.04 3 0.04 6
OFLAF [78]14.5 3.84 8 17.2 14 1.99 17 2.48 8 14.1 9 1.41 12 2.96 4 10.1 4 1.17 16 2.36 17 14.7 17 0.82 17 5.15 6 7.90 10 2.15 7 6.43 46 18.2 20 4.98 25 0.27 3 2.42 4 0.07 21 0.79 16 1.88 11 1.81 35
MS_RAFT+_RVC [195]14.7 3.64 5 14.7 2 1.07 3 4.39 50 13.7 7 4.81 100 3.05 6 10.8 6 0.81 9 0.66 3 7.11 3 0.03 4 4.43 2 6.57 2 1.41 2 0.78 1 5.06 1 0.49 2 0.47 29 4.27 47 0.22 43 0.39 6 1.12 4 0.39 15
MDP-Flow2 [68]16.2 3.86 9 17.2 14 1.90 13 2.06 1 12.6 3 1.04 2 3.22 8 11.0 7 1.16 14 3.27 38 21.7 45 1.19 32 6.35 22 8.86 18 3.12 17 5.40 22 15.7 10 5.11 28 0.38 18 3.75 33 0.02 3 0.49 9 1.80 10 0.13 12
NN-field [71]18.7 4.31 21 18.6 26 2.22 27 3.13 21 18.3 32 1.79 25 3.16 7 11.1 8 1.40 23 2.08 14 16.7 20 0.78 15 5.28 7 7.44 6 2.25 8 2.53 6 8.92 5 0.92 4 0.89 63 6.39 97 0.02 3 0.27 2 0.98 2 0.04 6
PMMST [112]19.9 4.02 12 16.5 10 1.46 4 3.86 39 16.9 23 3.33 55 3.91 14 12.6 13 2.82 48 2.18 16 9.47 8 1.30 39 5.68 12 7.88 9 2.78 13 5.25 20 13.7 7 4.29 15 0.53 38 5.11 71 0.02 3 0.26 1 0.94 1 0.04 6
RAFT-TF_RVC [179]19.9 5.96 64 22.7 60 2.14 24 2.86 16 14.7 10 1.95 29 4.38 21 14.7 21 3.62 64 0.46 1 5.16 1 0.00 1 5.99 17 8.91 19 2.28 9 2.04 5 9.20 6 1.67 5 0.44 24 3.97 38 0.05 16 0.55 10 2.01 12 0.02 4
CoT-AMFlow [174]25.5 4.12 16 18.0 20 2.78 45 2.19 5 13.2 6 1.28 7 3.44 12 11.9 12 1.47 24 3.42 43 22.5 52 1.30 39 6.47 26 8.96 20 4.11 46 5.11 18 17.0 15 4.89 24 0.52 35 4.96 66 0.07 21 0.80 17 2.26 18 1.39 24
nLayers [57]31.8 4.08 15 16.2 8 2.80 48 4.71 65 19.3 40 3.82 85 4.64 28 15.2 27 3.96 71 1.99 12 13.2 12 0.80 16 5.34 9 7.57 8 3.22 19 5.85 35 16.8 14 4.64 19 0.87 61 3.68 31 0.96 77 0.84 18 2.94 26 0.75 18
ComponentFusion [94]33.0 4.03 13 17.7 17 2.19 26 2.17 4 13.1 5 1.26 6 3.86 13 13.2 15 1.58 26 2.85 30 18.0 25 1.03 24 6.68 32 9.59 31 4.14 47 8.35 89 27.3 87 8.34 104 0.60 43 4.03 41 0.52 63 0.76 15 2.22 17 1.09 20
LME [70]33.2 3.70 6 16.1 7 1.69 5 2.13 2 13.0 4 1.19 4 5.91 56 15.4 29 7.43 104 3.23 34 22.4 50 1.19 32 6.60 31 9.12 24 4.39 57 6.11 38 20.8 29 6.60 66 0.52 35 4.96 66 0.07 21 1.09 23 3.28 34 1.86 39
SVFilterOh [109]34.2 4.36 23 15.9 6 2.01 20 3.04 19 16.3 19 1.78 24 3.31 9 11.3 9 1.20 17 2.02 13 13.6 14 0.57 10 5.94 16 8.69 16 2.12 6 6.61 49 19.3 22 6.32 61 5.10 130 12.9 144 10.0 141 0.75 14 2.20 16 1.32 22
UnDAF [187]34.2 4.48 28 20.3 34 2.27 30 2.54 9 16.0 15 1.20 5 4.39 22 15.2 27 1.30 20 3.50 47 23.8 70 1.24 34 6.52 29 9.01 22 3.87 40 6.33 42 24.7 67 5.08 27 0.53 38 5.06 69 0.02 3 1.64 53 5.40 67 1.33 23
FC-2Layers-FF [74]34.7 4.03 13 16.3 9 2.39 36 4.23 48 20.9 52 3.21 51 3.40 11 11.4 10 2.64 41 2.74 23 17.1 22 1.03 24 5.73 13 8.29 13 3.31 21 7.49 64 20.5 28 6.66 71 1.30 82 6.84 103 0.34 56 0.64 12 1.78 9 1.20 21
NNF-EAC [101]35.4 4.32 22 18.6 26 2.18 25 2.69 13 15.1 12 1.64 18 3.93 15 13.1 14 1.27 19 4.17 74 23.0 60 1.95 70 7.09 46 9.97 39 3.89 41 6.33 42 17.4 17 5.53 31 0.55 40 5.18 72 0.02 3 1.60 51 4.32 55 1.93 44
HAST [107]36.2 2.98 1 12.9 1 1.71 6 3.63 35 15.0 11 2.78 43 2.46 1 8.38 1 0.25 2 2.84 29 18.0 25 0.67 11 5.02 5 7.35 5 1.66 4 8.83 100 22.4 45 8.37 105 6.13 136 12.0 139 18.0 150 0.31 4 1.13 5 0.03 5
PRAFlow_RVC [177]37.5 7.13 81 23.4 62 3.06 54 4.78 68 19.8 43 4.04 88 6.49 62 20.6 63 4.99 77 1.08 5 8.77 7 0.14 5 6.26 20 8.82 17 3.07 16 1.85 4 8.89 4 2.04 6 0.48 31 4.59 52 0.17 37 1.46 41 2.87 23 1.81 35
WLIF-Flow [91]38.2 3.97 11 17.0 13 2.12 22 3.53 29 18.5 34 2.37 36 4.60 27 15.1 25 2.34 37 3.40 41 20.3 40 1.50 45 7.69 71 11.4 82 4.79 72 6.67 50 17.8 19 5.53 31 0.40 21 3.68 31 0.07 21 1.59 50 3.82 45 2.63 64
3DFlow [133]39.9 4.65 32 19.4 30 1.86 10 3.01 18 18.5 34 1.32 10 4.17 16 14.5 18 0.62 4 1.38 7 7.93 6 0.72 13 6.90 36 10.3 54 3.76 36 11.3 122 30.0 103 10.5 125 1.63 95 4.03 41 5.22 126 0.35 5 1.27 6 0.06 10
FESL [72]40.6 3.91 10 16.6 11 2.13 23 5.68 95 23.5 72 4.23 94 5.17 39 16.8 36 2.99 51 2.41 19 15.8 19 0.89 21 5.76 14 8.62 15 4.05 44 5.81 31 17.6 18 5.32 30 1.09 73 5.68 87 1.21 84 1.35 32 2.89 25 1.72 31
Layers++ [37]40.6 4.39 25 17.8 18 3.14 57 3.70 36 18.0 29 2.84 44 3.37 10 11.5 11 2.65 42 2.38 18 14.1 16 0.82 17 5.33 8 7.52 7 3.78 38 7.58 67 22.0 40 6.13 53 1.81 100 7.08 108 0.54 64 1.45 40 2.46 20 4.56 107
RNLOD-Flow [119]41.0 3.58 4 15.7 5 1.83 9 3.60 33 19.9 45 2.06 30 5.53 50 18.1 52 2.42 39 2.75 24 17.7 23 1.01 23 6.01 18 9.09 23 3.98 43 7.21 56 20.0 24 6.87 80 2.59 106 9.67 122 1.95 96 1.06 22 2.66 22 1.79 34
ALD-Flow [66]42.8 4.22 17 18.2 22 1.93 15 3.20 25 16.8 22 1.59 17 5.21 40 17.4 43 1.13 13 3.70 53 22.9 58 1.26 35 6.54 30 9.31 27 3.14 18 5.25 20 21.5 35 4.98 25 0.88 62 4.67 57 4.48 122 2.69 82 6.66 79 4.79 109
TC/T-Flow [77]43.0 4.57 30 20.6 36 2.00 18 3.45 28 18.7 36 1.52 15 4.30 19 14.3 17 0.67 6 3.97 69 23.1 61 1.80 61 6.35 22 9.50 30 3.36 24 4.48 11 15.7 10 4.78 21 1.30 82 6.94 105 5.07 125 2.08 69 5.10 66 2.83 70
PMF [73]43.1 4.65 32 18.3 25 2.34 31 3.37 26 18.2 31 1.92 27 4.20 17 14.6 20 1.01 10 3.24 36 18.6 29 1.11 27 5.50 10 8.09 11 2.43 10 6.99 53 24.8 69 6.27 58 6.87 139 17.3 154 8.77 140 0.91 19 2.06 13 2.06 47
AGIF+OF [84]44.8 4.39 25 18.0 20 2.80 48 5.10 79 23.7 76 3.70 79 5.06 35 16.8 36 3.11 52 3.29 39 20.1 38 1.45 44 6.45 25 9.31 27 4.62 63 6.77 52 19.7 23 5.86 41 0.37 17 3.60 27 0.25 48 1.79 60 3.68 41 3.12 79
Correlation Flow [76]44.9 4.57 30 20.5 35 1.87 11 2.71 14 16.2 18 1.16 3 5.74 54 17.9 50 0.66 5 1.91 10 13.5 13 0.85 20 8.00 82 12.0 94 4.57 61 8.69 95 23.8 57 8.93 111 0.84 58 4.74 58 0.96 77 1.38 35 3.81 44 1.91 42
Efficient-NL [60]45.1 4.24 18 17.4 16 2.24 28 4.30 49 21.8 55 2.75 41 5.26 43 16.9 38 2.67 43 3.43 44 21.0 42 1.74 56 6.02 19 9.16 25 3.31 21 7.84 77 21.7 37 6.26 56 1.36 85 6.79 102 1.03 80 1.48 45 3.08 29 1.77 33
TC-Flow [46]47.0 4.27 19 19.0 29 1.91 14 2.85 15 16.6 21 1.45 13 5.05 34 16.9 38 0.80 8 4.05 70 23.9 71 1.74 56 6.73 33 9.68 33 2.93 15 5.83 32 22.9 51 5.68 38 1.39 87 4.87 63 7.32 136 2.46 76 6.13 74 4.49 103
OAR-Flow [123]47.1 5.41 53 21.6 49 2.61 41 4.96 75 22.3 58 2.88 45 7.90 75 23.8 73 4.19 75 4.45 82 22.7 57 1.90 65 7.03 43 10.1 44 3.39 25 5.10 17 22.3 43 4.56 18 0.29 5 2.64 9 0.17 37 1.58 49 4.89 63 1.68 29
ProFlow_ROB [142]47.4 5.24 50 22.0 52 2.36 34 3.71 38 20.5 49 2.17 33 6.59 64 21.5 67 2.88 50 3.48 45 22.0 47 1.14 31 6.88 35 9.84 36 3.61 28 5.84 33 23.0 52 6.06 48 0.50 34 4.91 64 0.15 35 2.29 72 6.62 78 2.50 62
GMFlow_RVC [196]47.8 20.9 140 31.5 97 12.4 134 4.94 73 17.6 25 5.15 104 4.52 26 14.7 21 2.67 43 1.49 8 11.8 10 0.48 8 7.73 72 11.2 77 4.24 52 5.08 16 16.2 12 3.53 12 1.13 75 6.89 104 0.07 21 0.47 7 1.74 8 0.01 2
Classic+CPF [82]49.5 4.77 37 19.7 32 2.99 51 4.59 56 23.3 70 3.08 49 5.24 41 17.2 41 2.81 47 3.32 40 21.3 43 1.57 50 6.51 28 9.49 29 4.24 52 7.39 61 21.5 35 6.27 58 1.02 68 5.33 77 1.40 88 1.47 44 3.19 32 2.47 60
IROF++ [58]51.4 4.68 34 19.4 30 2.70 44 4.66 60 23.1 65 3.42 65 5.25 42 17.2 41 3.79 67 3.95 67 23.2 63 2.05 76 6.97 39 9.84 36 4.64 64 7.99 81 24.6 64 7.05 84 0.44 24 4.30 50 0.00 1 1.37 34 3.26 33 2.83 70
ProbFlowFields [126]51.6 8.29 95 31.1 93 5.73 114 3.54 30 18.0 29 2.75 41 6.07 59 18.9 57 5.22 79 3.54 49 17.7 23 1.91 66 7.66 70 10.8 66 4.59 62 5.06 15 20.0 24 5.58 35 0.38 18 3.08 19 0.07 21 1.70 56 4.56 59 2.41 59
PH-Flow [99]52.1 5.11 44 21.0 40 3.62 71 4.59 56 22.4 59 3.37 59 4.37 20 14.5 18 3.45 58 3.93 66 22.5 52 2.07 79 6.34 21 9.00 21 3.74 34 7.28 59 21.7 37 6.39 63 1.61 94 5.58 85 1.58 90 1.15 25 2.12 15 3.39 85
COFM [59]52.5 4.75 36 20.2 33 2.63 43 3.40 27 18.3 32 2.14 31 6.19 60 19.3 58 4.00 72 3.04 32 18.8 30 1.11 27 7.45 59 10.1 44 7.01 112 8.80 99 20.9 30 6.68 72 1.41 88 3.66 30 2.76 108 1.22 26 2.28 19 3.72 91
HCFN [157]52.7 4.29 20 20.6 36 1.71 6 2.64 11 15.1 12 1.69 19 4.21 18 14.8 23 1.26 18 2.81 28 19.5 35 0.84 19 5.93 15 8.53 14 2.64 11 7.75 73 26.3 81 7.82 97 12.7 158 17.7 155 17.4 149 2.56 78 6.04 73 5.29 115
HBM-GC [103]53.1 5.82 61 18.2 22 2.00 18 4.47 54 18.7 36 3.80 84 4.39 22 15.1 25 1.73 30 2.42 20 13.8 15 0.72 13 6.77 34 9.60 32 4.08 45 7.61 69 19.0 21 5.76 39 4.61 126 12.6 141 2.83 110 2.39 75 5.72 69 5.01 113
PWC-Net_RVC [143]53.4 9.12 104 32.2 100 4.81 99 4.68 62 22.6 60 3.66 76 7.60 72 25.0 83 5.34 80 2.47 21 15.4 18 0.97 22 7.07 44 9.98 40 3.95 42 6.32 41 25.4 75 6.26 56 0.47 29 4.66 55 0.17 37 0.98 20 3.17 31 0.31 14
WRT [146]54.2 5.66 60 21.6 49 1.98 16 5.17 84 23.5 72 3.40 62 7.54 71 21.3 66 1.16 14 1.32 6 7.54 5 0.47 7 6.97 39 10.2 48 4.90 78 11.5 124 27.6 89 8.28 103 0.45 28 3.92 37 0.22 43 2.30 73 4.18 52 2.94 75
Sparse-NonSparse [56]54.6 4.98 40 20.8 39 4.09 80 4.63 59 22.9 61 3.41 64 5.02 33 16.7 35 3.47 61 3.89 62 22.6 56 1.91 66 7.17 49 10.2 48 4.30 55 7.66 71 22.3 43 6.80 76 0.69 50 3.53 26 0.89 74 1.52 47 3.56 40 2.97 76
CostFilter [40]54.7 5.29 51 22.0 52 2.85 50 3.54 30 17.7 27 2.16 32 4.64 28 16.0 30 1.75 31 3.68 52 22.5 52 1.27 37 5.67 11 8.14 12 2.85 14 7.76 74 25.9 77 6.80 76 6.98 142 24.2 160 12.9 144 1.43 37 4.11 48 2.02 46
MLDP_OF [87]56.2 6.35 71 26.0 73 3.41 62 2.97 17 16.4 20 1.76 23 5.47 48 17.8 48 1.30 20 2.79 26 19.7 36 1.12 30 7.13 48 10.0 41 3.75 35 7.49 64 21.4 34 9.75 119 5.04 128 6.22 94 17.0 148 1.79 60 4.28 53 2.14 50
LSM [39]56.6 5.00 42 21.2 46 3.93 77 4.62 58 22.9 61 3.37 59 5.13 37 17.1 40 3.26 55 3.80 57 22.9 58 1.87 63 6.92 37 9.78 34 4.41 59 7.71 72 22.4 45 6.74 75 1.00 67 4.76 60 1.16 82 1.68 55 3.94 46 2.90 73
Classic+NL [31]56.8 5.07 43 21.0 40 4.22 84 4.70 64 23.4 71 3.27 53 4.98 32 16.5 33 3.48 62 3.75 56 22.5 52 1.68 53 7.21 52 10.2 48 4.32 56 7.82 75 22.4 45 6.71 74 1.47 89 6.39 97 1.18 83 1.12 24 2.87 23 2.27 54
FMOF [92]57.0 4.42 27 17.8 18 3.06 54 5.03 76 23.1 65 3.63 73 4.45 25 14.8 23 2.80 46 2.94 31 18.8 30 1.26 35 7.00 42 10.2 48 4.71 67 8.92 101 20.9 30 7.13 86 1.06 71 6.34 96 1.85 95 2.58 80 5.80 71 3.06 77
JOF [136]57.0 4.36 23 18.2 22 2.55 39 5.21 87 23.2 67 4.14 91 4.40 24 14.2 16 3.37 57 3.66 51 21.4 44 1.95 70 6.49 27 9.25 26 3.76 36 7.05 55 21.0 32 5.58 35 4.19 123 8.20 114 6.97 134 1.84 64 4.37 56 2.92 74
Ramp [62]57.2 5.12 45 21.1 44 3.82 76 4.68 62 23.2 67 3.47 68 4.89 31 16.3 31 3.46 59 3.83 59 22.3 49 1.93 69 7.23 53 10.2 48 4.80 73 7.61 69 22.1 41 6.80 76 1.20 78 5.04 68 1.43 89 1.36 33 2.98 27 2.31 58
PBOFVI [189]57.7 5.88 63 20.7 38 3.60 69 3.16 22 19.6 41 1.31 8 5.28 45 16.3 31 1.11 12 1.69 9 12.0 11 0.46 6 8.70 99 12.3 102 6.18 103 8.56 92 22.1 41 9.08 113 0.91 64 7.30 110 1.23 85 2.03 67 5.09 65 3.49 89
IIOF-NLDP [129]58.2 6.16 67 25.7 71 2.54 38 4.55 55 23.7 76 2.40 37 5.35 47 17.6 46 1.06 11 2.78 25 17.0 21 1.54 46 8.90 105 13.4 128 4.73 68 8.04 82 22.8 49 7.69 96 0.64 48 4.61 53 0.25 48 1.81 63 4.16 51 2.72 66
S2D-Matching [83]59.6 4.97 39 21.3 48 3.55 67 4.74 66 23.6 74 3.35 57 6.50 63 20.9 64 3.46 59 3.49 46 20.4 41 1.60 51 7.07 44 10.0 41 4.22 50 7.82 75 23.1 53 6.87 80 1.78 99 5.90 90 2.12 98 1.30 29 3.14 30 2.74 67
NL-TV-NCC [25]59.9 5.44 54 21.7 51 2.24 28 4.00 43 21.9 56 1.69 19 5.27 44 17.8 48 0.67 6 2.52 22 19.1 34 0.67 11 8.37 93 12.5 105 5.12 87 11.5 124 32.0 116 9.19 115 0.86 59 4.93 65 1.35 87 2.16 70 6.46 75 1.63 26
IROF-TV [53]60.9 5.22 48 22.6 58 3.59 68 4.80 69 24.2 82 3.73 83 5.71 53 18.4 55 3.64 65 4.19 75 25.7 90 1.92 68 7.63 69 10.7 63 5.26 88 9.22 107 30.2 104 6.60 66 0.30 8 2.86 12 0.02 3 1.32 31 3.76 43 2.27 54
TV-L1-MCT [64]60.9 4.69 35 18.9 28 3.60 69 5.64 94 25.6 90 4.21 92 5.53 50 18.1 52 3.23 53 3.04 32 19.9 37 1.35 41 7.49 60 10.6 59 4.91 80 8.34 87 22.8 49 7.50 95 0.79 57 2.61 7 3.57 116 1.73 58 3.45 38 3.26 83
MDP-Flow [26]61.0 5.65 58 24.7 68 4.93 101 3.70 36 17.6 25 3.40 62 5.47 48 18.7 56 4.66 76 3.87 60 24.3 74 1.88 64 7.12 47 9.89 38 5.00 84 6.17 40 25.9 77 4.66 20 0.61 44 5.65 86 0.05 16 3.28 98 8.39 98 3.45 88
AggregFlow [95]62.0 6.17 68 23.3 61 2.58 40 7.01 106 28.0 109 5.29 107 8.46 80 24.2 75 7.66 107 3.73 54 20.2 39 1.73 55 7.25 54 10.6 59 3.52 26 4.43 10 16.4 13 4.80 23 0.75 54 5.43 81 0.25 48 1.92 65 4.46 58 4.12 96
VCN_RVC [178]63.6 10.2 118 37.7 121 5.05 105 5.20 85 22.9 61 4.53 99 7.40 70 23.4 72 5.74 85 4.38 80 24.8 77 2.02 75 6.98 41 10.0 41 3.68 30 6.06 37 24.4 62 6.29 60 0.33 14 2.99 15 0.22 43 1.41 36 4.15 50 2.10 49
CombBMOF [111]64.9 6.51 73 28.6 82 2.61 41 3.98 42 18.7 36 2.29 35 5.29 46 17.4 43 2.33 36 5.12 92 26.1 97 3.28 99 6.35 22 9.81 35 3.34 23 12.0 129 28.4 94 15.1 142 3.73 118 12.8 143 0.76 71 0.98 20 3.00 28 0.09 11
OFH [38]65.7 6.38 72 25.7 71 4.69 94 3.90 40 20.6 50 2.24 34 7.85 74 24.2 75 2.27 33 4.11 73 25.1 81 1.72 54 7.44 58 10.4 55 4.69 65 8.13 83 28.9 96 8.44 108 0.44 24 4.25 46 0.12 32 2.80 84 8.82 108 2.74 67
Adaptive [20]66.1 5.12 45 22.0 52 2.34 31 4.82 71 23.2 67 3.50 69 8.67 86 24.5 80 3.56 63 4.19 75 25.3 87 1.83 62 7.40 57 10.6 59 3.63 29 5.84 33 23.2 55 3.75 13 3.25 114 8.86 117 0.89 74 2.87 87 6.69 80 3.14 81
Sparse Occlusion [54]66.2 4.99 41 21.1 44 2.79 47 4.13 46 20.1 48 3.00 48 5.94 58 19.4 59 2.15 32 3.41 42 21.8 46 1.35 41 8.17 88 12.1 97 4.74 69 7.87 79 25.6 76 6.34 62 11.4 153 17.7 155 2.71 107 1.64 53 4.70 62 1.81 35
Occlusion-TV-L1 [63]66.5 5.23 49 22.2 55 2.36 34 4.40 52 21.2 53 3.39 61 8.46 80 24.8 81 3.83 69 3.92 64 24.8 77 1.74 56 9.11 108 13.1 122 5.75 96 4.65 12 23.9 58 3.52 11 1.27 81 3.13 20 0.44 58 3.56 107 8.92 109 3.28 84
MCPFlow_RVC [197]67.5 15.6 128 35.7 109 8.09 124 10.6 119 30.0 118 10.2 121 14.0 117 32.8 116 18.1 123 1.97 11 10.4 9 1.08 26 7.61 68 11.5 85 2.70 12 4.90 13 15.5 9 4.48 17 0.62 46 5.26 74 0.25 48 1.61 52 3.43 35 1.90 41
RFlow [88]68.2 5.85 62 24.8 70 4.44 90 3.18 23 17.9 28 1.88 26 7.81 73 24.4 79 2.32 35 3.25 37 23.4 66 1.55 47 7.94 76 11.6 87 4.86 75 8.23 84 28.0 93 6.64 70 1.16 77 2.13 2 1.13 81 4.10 117 9.22 116 6.81 123
2DHMM-SAS [90]68.5 5.14 47 21.0 40 3.79 75 5.26 88 25.2 87 3.45 66 6.97 69 20.2 60 4.18 74 4.06 71 23.3 65 2.10 80 7.18 50 10.2 48 4.92 81 8.29 85 23.7 56 7.16 87 1.26 79 5.41 80 1.63 91 1.71 57 3.75 42 2.74 67
SimpleFlow [49]69.1 5.65 58 22.4 57 4.93 101 5.47 93 24.5 85 4.28 95 6.88 68 21.0 65 3.95 70 4.74 85 25.2 83 3.02 92 7.19 51 10.1 44 4.70 66 8.34 87 23.1 53 7.16 87 1.02 68 4.61 53 0.89 74 1.29 28 3.44 36 2.47 60
ACK-Prior [27]70.2 5.49 56 24.0 65 1.81 8 2.55 10 15.7 14 0.83 1 5.07 36 17.7 47 1.52 25 2.14 15 18.1 27 0.50 9 8.64 96 11.6 87 7.10 115 14.6 142 30.7 107 11.7 130 8.46 148 11.5 135 19.5 152 3.68 110 7.25 84 2.64 65
S2F-IF [121]71.1 9.49 110 37.6 118 4.93 101 4.81 70 25.6 90 3.34 56 8.25 78 26.1 85 6.40 90 4.99 89 25.6 89 2.93 90 7.80 73 11.0 71 4.90 78 5.61 25 24.9 72 5.83 40 0.62 46 5.35 79 0.22 43 1.43 37 4.11 48 1.67 28
Complementary OF [21]72.8 7.27 82 30.0 87 4.31 85 3.18 23 18.9 39 1.52 15 5.91 56 20.2 60 2.31 34 4.22 78 24.8 77 2.05 76 7.50 63 10.4 55 4.99 83 12.3 133 31.7 115 8.87 110 0.61 44 2.69 10 1.72 93 3.33 100 9.22 116 4.88 112
PGM-C [118]73.7 9.47 108 37.1 114 4.81 99 5.08 77 26.1 97 3.63 73 8.75 88 27.6 92 7.02 96 5.65 105 28.1 117 3.63 110 7.99 79 11.3 79 4.88 76 5.71 28 24.5 63 5.97 44 0.31 9 3.01 16 0.02 3 2.07 68 6.50 77 2.14 50
ROF-ND [105]73.8 6.70 74 27.6 78 3.53 65 3.08 20 16.0 15 1.73 21 5.81 55 18.3 54 1.58 26 3.81 58 18.4 28 2.20 81 9.45 115 14.0 139 6.31 104 11.3 122 29.6 101 7.27 91 9.92 151 10.8 127 7.29 135 1.53 48 3.44 36 1.64 27
SegFlow [156]74.5 9.46 107 37.1 114 4.79 96 5.13 80 26.3 100 3.65 75 8.62 85 27.1 89 7.00 94 5.59 101 28.1 117 3.52 106 8.07 85 11.4 82 5.09 86 5.72 29 24.6 64 6.10 51 0.35 16 3.43 24 0.02 3 1.76 59 5.06 64 2.50 62
TCOF [69]74.6 7.04 80 26.9 76 3.54 66 4.93 72 23.7 76 3.45 66 9.94 101 27.8 94 7.40 103 3.74 55 23.7 69 1.55 47 10.0 131 14.3 141 4.40 58 4.91 14 17.0 15 5.53 31 5.08 129 9.68 123 4.19 120 1.43 37 4.44 57 1.69 30
FlowFields [108]76.1 9.65 112 37.6 118 5.13 107 5.09 78 25.9 94 3.72 81 8.92 90 28.3 98 7.07 98 5.45 97 26.0 95 3.82 111 7.95 77 11.2 77 5.01 85 5.75 30 26.1 80 6.01 45 0.40 21 3.29 23 0.12 32 1.92 65 5.99 72 1.89 40
TF+OM [98]77.0 6.03 66 23.7 64 2.78 45 4.39 50 19.9 45 3.57 70 8.73 87 23.0 71 11.2 113 3.57 50 23.2 63 1.36 43 7.98 78 11.1 75 5.89 98 8.95 102 25.3 74 7.06 85 1.68 97 11.2 131 0.20 40 3.56 107 8.35 97 4.18 97
DMF_ROB [135]77.2 8.16 93 33.3 103 4.93 101 4.95 74 23.7 76 3.23 52 9.38 94 28.5 100 5.85 89 5.64 104 27.3 106 3.41 104 7.49 60 10.6 59 4.44 60 6.49 47 25.9 77 6.07 49 0.40 21 3.65 28 0.07 21 3.81 113 9.06 113 4.63 108
Steered-L1 [116]77.6 4.54 29 21.2 46 2.09 21 2.13 2 13.9 8 1.31 8 4.80 30 16.5 33 1.64 28 3.87 60 25.1 81 1.60 51 8.62 95 11.5 85 7.01 112 11.1 119 28.7 95 10.4 124 12.0 157 12.3 140 34.9 160 5.90 129 9.03 112 11.6 137
CPM-Flow [114]78.2 9.47 108 37.1 114 4.79 96 5.15 82 26.3 100 3.67 77 8.59 84 27.1 89 7.00 94 5.59 101 27.8 113 3.57 108 7.99 79 11.3 79 4.74 69 5.70 27 24.1 60 6.05 47 0.48 31 4.29 49 0.02 3 2.76 83 7.63 89 4.11 95
FlowFields+ [128]78.2 9.76 114 38.1 123 5.31 110 5.14 81 26.2 99 3.72 81 8.99 91 28.6 101 7.15 101 5.09 91 25.9 94 3.29 100 7.82 74 11.0 71 4.94 82 5.22 19 24.7 67 5.18 29 0.70 52 5.85 89 0.30 54 1.79 60 5.77 70 1.45 25
DeepFlow2 [106]78.5 6.80 76 28.5 81 2.99 51 5.20 85 22.9 61 3.60 72 8.88 89 26.2 86 5.75 86 5.76 107 26.8 104 3.41 104 7.34 56 10.7 63 3.58 27 5.86 36 24.8 69 6.22 55 1.02 68 3.78 35 3.08 114 4.35 120 9.84 121 5.80 118
EPPM w/o HM [86]78.8 8.62 99 33.5 104 3.62 71 3.58 32 19.7 42 1.93 28 6.19 60 20.5 62 1.64 28 4.64 84 25.2 83 2.54 84 7.60 67 10.4 55 5.81 97 11.2 120 31.6 113 9.82 120 6.91 141 8.93 118 15.9 147 1.48 45 4.06 47 2.01 45
EpicFlow [100]78.9 9.44 106 37.1 114 4.80 98 5.15 82 26.4 102 3.70 79 9.58 96 30.0 104 7.07 98 5.38 96 27.8 113 3.29 100 8.01 83 11.3 79 4.88 76 5.67 26 24.6 64 6.12 52 0.32 12 3.13 20 0.02 3 3.10 95 7.52 87 4.79 109
ComplOF-FED-GPU [35]82.1 6.96 78 30.7 90 3.33 60 4.74 66 24.9 86 2.66 39 6.71 66 22.4 68 2.45 40 4.44 81 26.2 98 2.05 76 7.50 63 10.7 63 4.20 49 9.78 109 34.0 125 9.47 117 2.42 105 4.74 58 6.63 132 3.09 93 9.17 114 3.91 94
SRR-TVOF-NL [89]82.5 7.45 86 28.6 82 3.09 56 6.20 99 26.1 97 3.90 86 9.82 99 28.4 99 5.78 87 3.96 68 23.5 67 1.55 47 7.55 65 10.8 66 5.27 89 9.21 105 26.7 85 7.25 90 5.74 133 11.5 135 4.01 118 1.30 29 3.49 39 2.19 53
F-TV-L1 [15]83.7 8.70 100 31.4 95 8.47 125 7.61 110 27.3 107 5.86 108 11.0 105 28.0 95 5.73 84 5.75 106 28.7 122 3.32 103 7.28 55 10.8 66 3.72 31 6.59 48 26.4 82 4.38 16 1.26 79 5.30 76 0.44 58 3.04 91 7.76 90 2.29 57
SIOF [67]83.9 5.37 52 22.6 58 2.34 31 6.11 97 28.4 111 4.30 96 12.6 112 29.2 103 14.4 118 5.52 100 27.4 109 3.00 91 8.96 106 12.6 107 6.02 99 8.72 96 27.9 91 7.93 99 0.38 18 3.48 25 0.02 3 3.09 93 7.58 88 4.85 111
DPOF [18]84.5 9.01 103 34.7 106 3.68 74 6.16 98 25.4 89 4.32 97 5.55 52 17.9 50 3.36 56 3.92 64 25.3 87 2.00 73 8.14 87 11.0 71 6.05 100 10.5 114 27.9 91 8.16 101 9.33 149 6.19 93 21.0 154 1.46 41 4.57 60 0.80 19
TV-L1-improved [17]84.8 5.52 57 23.4 62 3.42 63 4.13 46 20.8 51 2.96 46 8.29 79 24.2 75 3.64 65 4.06 71 24.4 75 1.77 59 8.34 92 12.1 97 4.15 48 13.7 137 38.4 138 14.9 139 4.40 125 10.1 125 2.14 99 3.33 100 8.42 99 3.40 86
Aniso. Huber-L1 [22]85.5 5.98 65 24.2 66 3.23 59 8.53 114 27.3 107 7.91 113 9.64 97 25.6 84 5.52 82 5.00 90 25.7 90 2.75 87 8.66 98 12.8 113 4.74 69 7.60 68 24.8 69 3.51 10 3.65 117 7.24 109 3.00 113 2.57 79 6.69 80 2.86 72
CVENG22+RIC [199]86.6 8.94 102 35.0 108 4.44 90 5.79 96 28.2 110 4.12 90 10.1 103 31.2 108 7.17 102 5.15 94 27.8 113 2.85 88 9.35 114 12.8 113 6.35 105 6.37 44 27.3 87 6.60 66 0.32 12 3.03 17 0.02 3 3.32 99 9.17 114 4.37 101
Classic++ [32]87.5 5.46 55 22.2 55 4.35 87 4.66 60 22.1 57 3.57 70 8.00 76 24.3 78 5.06 78 4.21 77 25.2 83 2.01 74 8.77 102 12.7 111 5.47 90 9.03 104 30.2 104 7.29 92 2.92 112 7.73 112 3.10 115 3.83 114 8.53 100 3.87 93
LocallyOriented [52]87.8 8.05 92 30.6 89 3.63 73 8.09 112 30.8 120 6.17 110 12.3 111 32.3 111 7.04 97 4.88 88 25.2 83 2.88 89 8.80 103 12.7 111 4.27 54 5.41 23 20.4 26 6.07 49 1.35 84 6.03 91 0.99 79 3.73 112 8.62 103 4.18 97
BriefMatch [122]88.2 4.78 38 21.0 40 2.40 37 4.00 43 19.8 43 2.68 40 5.13 37 17.5 45 2.41 38 3.23 34 22.1 48 1.28 38 9.81 125 12.0 94 13.1 149 17.2 144 33.8 121 17.8 146 7.84 144 12.7 142 22.3 155 8.01 141 10.5 127 16.1 148
DeepFlow [85]90.0 7.55 87 29.3 85 4.67 93 6.29 101 23.7 76 4.86 101 10.0 102 28.0 95 8.76 112 6.15 114 27.3 106 3.83 112 7.49 60 10.8 66 3.72 31 6.40 45 26.8 86 6.85 79 1.12 74 2.92 14 3.94 117 7.07 134 11.2 132 12.7 139
FF++_ROB [141]90.3 9.90 117 38.2 124 5.12 106 5.32 91 26.0 95 4.01 87 9.76 98 30.0 104 7.58 105 5.48 98 26.2 98 3.88 114 7.83 75 11.0 71 5.63 93 7.26 57 24.3 61 7.33 93 0.78 56 3.65 28 2.88 111 2.92 90 6.46 75 6.17 121
C-RAFT_RVC [181]90.3 17.2 132 40.2 127 7.62 121 16.2 133 39.0 141 16.0 132 16.0 125 39.3 128 19.2 125 5.95 111 18.8 30 3.23 96 9.48 117 13.2 123 7.53 120 6.16 39 22.6 48 6.57 65 0.96 65 6.07 92 0.44 58 0.70 13 2.54 21 0.04 6
CRTflow [81]90.8 7.63 89 31.8 99 3.42 63 4.40 52 21.2 53 2.97 47 8.99 91 26.6 87 4.11 73 4.86 87 26.5 101 2.57 85 7.99 79 11.7 89 3.26 20 18.0 148 40.2 142 22.2 151 1.47 89 4.45 51 2.51 105 4.73 122 11.4 133 7.30 124
TriFlow [93]91.1 7.87 91 30.1 88 3.19 58 7.12 107 24.4 84 7.15 112 13.9 116 31.4 109 20.0 126 3.50 47 22.4 50 1.77 59 8.70 99 11.7 89 7.03 114 7.51 66 21.9 39 6.63 69 28.6 161 14.7 151 78.3 163 2.16 70 5.57 68 2.14 50
Local-TV-L1 [65]92.9 9.60 111 30.8 91 7.89 123 12.7 124 30.2 119 13.3 124 15.9 124 32.3 111 17.3 121 6.19 115 28.0 116 3.84 113 7.55 65 10.9 70 4.22 50 7.48 63 26.4 82 6.02 46 0.28 4 1.87 1 0.15 35 9.10 143 10.8 129 20.5 149
Brox et al. [5]93.6 8.32 96 32.6 101 6.95 117 6.23 100 26.9 106 5.23 105 9.13 93 27.6 92 6.55 92 5.85 109 28.2 119 3.26 97 10.2 133 12.9 118 11.0 144 5.43 24 29.3 100 4.79 22 0.86 59 4.00 39 0.12 32 4.32 118 10.2 124 4.54 106
Rannacher [23]93.6 6.99 79 27.1 77 5.36 112 5.27 89 24.3 83 4.22 93 9.51 95 27.1 89 5.54 83 4.76 86 25.7 90 2.58 86 8.80 103 12.9 118 4.82 74 11.0 117 35.7 130 9.36 116 2.33 104 4.76 60 2.39 104 2.82 86 8.01 93 3.13 80
Dynamic MRF [7]94.2 7.74 90 31.6 98 4.44 90 4.12 45 23.6 74 2.47 38 8.49 82 28.0 95 2.83 49 4.25 79 27.4 109 2.41 82 8.61 94 12.0 94 6.08 101 14.5 141 43.2 146 14.9 139 0.64 48 2.35 3 4.51 123 9.85 146 15.6 149 15.3 146
Bartels [41]94.8 6.83 77 26.2 74 5.19 109 3.93 41 17.4 24 3.30 54 6.63 65 22.6 69 3.25 54 4.45 82 23.9 71 2.48 83 9.12 109 12.1 97 8.25 128 10.6 115 31.1 109 12.3 133 5.74 133 10.4 126 18.9 151 5.34 124 9.52 118 8.47 130
LiteFlowNet [138]97.4 15.0 126 50.3 144 7.15 118 6.37 102 25.8 93 4.98 102 11.5 108 36.2 123 6.96 93 5.48 98 23.1 61 3.06 95 9.02 107 12.3 102 7.10 115 11.7 128 33.8 121 9.65 118 0.44 24 4.00 39 0.20 40 3.07 92 6.97 83 4.52 105
OFRF [132]100.7 7.28 83 24.5 67 4.75 95 14.7 130 29.6 116 15.2 128 14.3 119 29.0 102 15.9 120 6.64 118 25.7 90 5.02 123 6.95 38 10.1 44 3.72 31 8.44 91 23.9 58 7.17 89 3.30 115 6.51 99 10.8 142 9.99 147 9.82 120 24.2 152
CBF [12]100.9 6.32 69 26.2 74 3.35 61 11.1 121 25.6 90 13.7 125 8.51 83 24.1 74 7.12 100 5.12 92 26.0 95 3.04 94 10.3 134 13.6 133 9.59 140 7.85 78 26.4 82 4.25 14 11.8 154 13.8 146 14.2 146 3.54 106 8.06 94 5.32 116
CLG-TV [48]102.2 6.33 70 24.7 68 4.13 81 9.08 117 26.6 103 9.31 119 9.85 100 26.8 88 5.82 88 5.30 95 26.5 101 3.03 93 10.4 136 14.6 145 7.57 121 7.95 80 31.1 109 6.51 64 5.92 135 11.4 132 4.36 121 3.41 103 8.81 107 3.06 77
TriangleFlow [30]102.7 7.35 84 28.2 80 4.31 85 5.35 92 25.2 87 3.36 58 8.00 76 24.8 81 2.70 45 3.90 63 24.1 73 1.97 72 12.9 150 17.8 157 10.7 142 13.1 135 32.3 118 13.9 137 4.71 127 16.1 153 4.04 119 3.65 109 8.73 105 5.69 117
DF-Auto [113]104.1 9.74 113 34.1 105 4.36 88 14.1 129 31.9 125 15.4 130 15.6 123 33.1 118 23.6 130 5.94 110 27.3 106 3.59 109 10.4 136 14.8 148 6.97 111 3.80 8 21.1 33 2.46 8 5.25 132 11.4 132 0.49 61 4.33 119 10.4 125 4.33 99
CNN-flow-warp+ref [115]104.6 9.81 116 35.7 109 7.67 122 8.14 113 26.0 95 8.55 115 14.3 119 35.8 121 15.7 119 6.69 119 30.3 125 4.31 118 9.17 111 12.2 100 8.71 134 7.03 54 29.6 101 5.55 34 0.69 50 3.77 34 2.00 97 7.79 139 12.1 137 8.13 129
p-harmonic [29]105.0 8.47 97 36.3 112 7.17 119 5.27 89 24.1 81 4.39 98 11.2 107 31.4 109 8.13 111 7.18 123 32.4 130 5.24 125 8.04 84 11.1 75 6.89 109 9.82 110 36.4 133 10.6 126 2.61 107 5.51 83 0.54 64 4.07 116 9.01 111 4.34 100
ContinualFlow_ROB [148]106.1 15.9 131 42.0 128 9.15 128 15.5 132 32.1 126 16.9 133 19.1 130 43.0 135 24.3 131 6.50 117 26.2 98 3.53 107 9.84 127 13.0 120 6.92 110 13.8 138 33.9 124 17.4 145 0.57 42 5.33 77 0.32 55 1.46 41 4.29 54 0.68 17
FlowNet2 [120]108.7 21.7 143 43.8 131 13.5 136 24.6 147 42.3 145 27.3 147 19.8 131 40.5 129 29.9 139 8.21 130 23.6 68 5.39 127 9.85 128 12.6 107 8.54 130 8.76 97 28.9 96 5.89 42 2.77 109 15.5 152 0.81 73 1.28 27 4.68 61 0.26 13
CompactFlow_ROB [155]108.7 23.6 146 47.8 138 9.55 129 13.6 125 31.6 123 14.9 127 22.7 137 48.3 140 36.1 150 8.92 132 28.6 120 5.54 128 9.61 119 13.2 123 6.45 106 8.97 103 34.7 127 8.76 109 0.29 5 2.81 11 0.10 30 3.17 97 7.86 91 3.76 92
FlowNetS+ft+v [110]109.2 7.57 88 29.4 86 3.96 78 7.50 109 26.6 103 6.48 111 14.3 119 32.7 115 17.5 122 7.55 124 31.3 127 5.28 126 10.5 138 14.7 146 7.49 119 6.75 51 27.8 90 6.97 83 4.01 122 8.84 116 6.77 133 3.52 105 9.71 119 3.61 90
EAI-Flow [147]110.2 18.4 134 42.5 129 11.6 132 10.8 120 32.2 127 9.62 120 14.3 119 38.9 127 14.0 116 7.07 122 28.6 120 5.13 124 8.20 89 11.9 92 5.47 90 9.21 105 30.7 107 9.05 112 9.33 149 6.96 106 0.49 61 2.48 77 7.31 85 3.20 82
SegOF [10]110.2 12.6 122 34.9 107 7.20 120 21.3 141 36.9 135 25.3 145 21.6 135 40.5 129 31.8 143 14.1 143 37.7 140 10.8 138 10.3 134 12.5 105 12.6 148 10.2 112 40.2 142 11.2 128 0.29 5 2.91 13 0.07 21 2.90 88 8.68 104 2.07 48
LDOF [28]110.3 8.22 94 31.4 95 4.08 79 7.64 111 29.4 113 5.87 109 10.7 104 30.3 106 7.99 110 7.80 127 36.8 138 4.86 122 9.14 110 12.4 104 8.24 127 8.58 93 32.0 116 8.38 106 1.75 98 5.26 74 5.02 124 5.52 126 12.9 141 6.04 120
LSM_FLOW_RVC [182]110.8 23.2 145 60.7 152 17.3 142 14.0 128 37.5 136 13.9 126 24.5 143 59.3 152 22.3 128 9.50 136 35.6 137 7.85 135 9.18 112 12.8 113 6.70 107 12.0 129 38.7 139 12.9 135 0.33 14 3.26 22 0.07 21 2.62 81 8.17 95 1.74 32
Fusion [6]110.9 8.51 98 37.6 118 6.69 116 3.62 34 20.0 47 3.08 49 6.82 67 22.6 69 6.47 91 5.78 108 31.3 127 4.29 117 11.2 146 14.7 146 10.6 141 14.0 139 35.2 128 15.0 141 7.88 145 14.3 149 2.22 100 5.35 125 11.0 130 8.56 131
IRR-PWC_RVC [180]111.5 25.6 148 49.2 143 10.6 130 21.0 140 42.3 145 23.2 141 24.1 142 49.4 142 34.4 146 13.3 139 24.5 76 10.7 137 8.64 96 11.8 91 5.63 93 8.35 89 30.2 104 6.70 73 1.49 91 9.40 121 0.57 66 2.91 89 7.90 92 1.91 42
AugFNG_ROB [139]111.9 18.1 133 47.6 137 10.8 131 23.9 145 39.8 143 28.6 148 22.8 139 49.1 141 29.3 137 7.57 125 25.0 80 4.54 121 9.90 130 12.8 113 8.92 135 8.31 86 33.8 121 8.19 102 0.76 55 7.01 107 0.25 48 2.80 84 7.45 86 1.85 38
EPMNet [131]113.0 21.3 142 48.9 142 14.5 138 23.2 144 44.2 148 25.1 144 18.8 129 37.9 125 28.4 135 8.92 132 27.5 112 5.90 130 9.85 128 12.6 107 8.54 130 8.76 97 28.9 96 5.89 42 1.98 101 11.4 132 0.59 67 2.36 74 8.59 102 0.63 16
WOLF_ROB [144]113.9 11.7 119 48.4 139 5.18 108 12.5 123 38.6 139 8.94 116 18.0 128 43.3 136 13.5 115 7.96 128 30.5 126 5.97 132 8.25 90 11.4 82 6.75 108 10.9 116 36.1 132 10.2 121 0.72 53 4.15 44 1.28 86 5.67 127 11.0 130 10.2 135
Learning Flow [11]114.1 6.74 75 28.1 79 3.03 53 6.37 102 28.7 112 5.02 103 11.8 109 32.6 114 7.93 109 6.87 121 33.2 134 4.32 119 12.5 149 17.4 155 7.78 122 9.98 111 35.2 128 8.41 107 2.66 108 10.9 129 2.24 101 6.76 133 13.7 143 6.41 122
ResPWCR_ROB [140]114.4 18.8 135 53.9 147 13.5 136 8.80 115 29.4 113 8.15 114 12.6 112 36.0 122 12.1 114 7.61 126 32.2 129 5.71 129 8.07 85 10.4 55 8.08 124 9.68 108 34.5 126 10.3 122 3.74 120 9.01 119 1.82 94 3.35 102 8.20 96 4.45 102
StereoFlow [44]115.6 58.0 163 76.4 163 63.7 160 51.8 162 66.9 163 48.3 158 51.0 163 73.0 162 41.6 155 63.5 163 83.4 163 56.7 160 13.3 152 13.7 134 19.1 155 3.63 7 20.4 26 2.73 9 0.26 1 2.49 5 0.05 16 4.06 115 8.57 101 5.81 119
Second-order prior [8]116.4 7.35 84 31.2 94 4.16 82 6.80 105 29.5 115 5.27 106 11.8 109 33.3 119 7.78 108 6.05 112 27.2 105 3.90 115 9.67 122 13.8 137 5.74 95 14.0 139 41.8 145 11.7 130 6.86 138 9.72 124 7.61 138 4.72 121 10.1 123 7.78 127
Ad-TV-NDC [36]117.6 21.2 141 36.8 113 34.1 154 25.9 149 38.5 138 29.9 149 23.5 141 41.0 131 27.1 132 13.3 139 32.4 130 13.3 143 8.75 101 13.2 123 3.82 39 7.43 62 25.1 73 6.92 82 1.50 92 4.84 62 0.34 56 17.1 157 15.9 154 37.2 161
HBpMotionGpu [43]118.1 11.7 119 32.8 102 6.34 115 18.9 137 35.4 133 22.0 140 22.3 136 42.7 134 31.1 142 5.62 103 26.7 103 3.31 102 9.47 116 13.0 120 8.55 132 8.68 94 31.2 111 5.58 35 6.88 140 11.9 137 0.64 68 7.67 138 11.4 133 15.2 144
Shiralkar [42]119.4 9.76 114 46.6 135 4.40 89 6.53 104 31.3 122 4.04 88 12.7 114 37.5 124 5.34 80 6.47 116 32.9 133 4.34 120 8.33 91 11.9 92 5.58 92 17.4 147 43.3 148 15.5 143 6.82 137 8.77 115 14.0 145 7.36 136 15.7 153 7.83 128
StereoOF-V1MT [117]120.0 9.29 105 44.8 133 4.17 83 7.22 108 34.5 130 3.68 78 13.7 115 42.6 133 3.80 68 6.06 113 38.5 142 3.27 98 11.0 143 15.1 150 9.55 139 15.1 143 49.9 152 14.0 138 1.08 72 5.51 83 5.44 127 9.33 145 15.5 148 9.73 134
LFNet_ROB [145]121.3 20.5 139 60.8 153 12.8 135 10.1 118 31.7 124 9.00 117 20.6 133 53.4 145 14.0 116 9.26 134 32.6 132 7.53 133 9.83 126 13.2 123 8.22 126 11.5 124 37.7 135 11.3 129 1.13 75 6.72 100 0.74 70 3.50 104 8.77 106 5.19 114
SPSA-learn [13]121.9 15.7 129 48.8 140 16.5 140 16.6 134 35.0 132 17.5 135 21.4 134 42.3 132 29.7 138 12.6 137 37.4 139 12.3 141 9.64 120 12.8 113 9.16 136 11.0 117 37.9 137 12.2 132 0.98 66 3.88 36 0.05 16 8.38 142 11.6 135 15.2 144
Filter Flow [19]124.0 14.6 124 38.2 124 8.96 127 12.4 122 34.6 131 11.3 122 20.2 132 38.3 126 30.1 140 19.2 145 43.4 146 18.6 146 10.0 131 13.4 128 9.43 138 10.3 113 31.4 112 9.08 113 8.21 147 19.6 157 0.79 72 3.72 111 6.85 82 3.41 87
IAOF2 [51]124.9 8.72 101 30.9 92 5.32 111 13.9 127 31.1 121 15.4 130 14.1 118 33.0 117 18.2 124 30.8 154 42.2 145 36.4 156 9.74 124 13.8 137 6.09 102 12.0 129 33.4 119 7.96 100 7.92 146 13.9 147 7.49 137 5.69 128 10.6 128 4.51 104
GraphCuts [14]125.2 12.6 122 36.1 111 5.46 113 14.7 130 39.4 142 12.5 123 17.8 127 35.6 120 29.1 136 6.86 120 33.7 135 4.15 116 9.33 113 12.6 107 8.69 133 23.0 153 31.6 113 15.5 143 3.52 116 7.38 111 11.7 143 5.33 123 9.87 122 8.75 132
Modified CLG [34]125.3 15.7 129 43.7 130 12.2 133 19.1 138 33.3 129 23.7 142 25.1 144 47.4 139 35.6 149 13.2 138 35.5 136 11.1 139 10.7 140 14.4 143 9.36 137 7.26 57 35.8 131 6.19 54 1.66 96 5.21 73 6.43 130 5.94 130 13.8 145 7.73 126
2D-CLG [1]126.2 24.4 147 51.8 146 19.4 145 27.4 150 38.7 140 33.8 152 34.6 151 57.7 149 42.2 157 33.4 156 57.1 157 32.9 155 9.64 120 12.2 100 11.0 144 11.2 120 40.2 142 12.8 134 0.31 9 2.62 8 0.25 48 6.33 131 13.7 143 7.33 125
TVL1_RVC [175]127.7 36.8 155 55.3 148 54.0 159 36.6 154 40.3 144 46.0 156 36.5 153 59.3 152 43.5 160 29.9 153 49.4 151 31.7 153 9.71 123 13.7 134 7.21 118 7.34 60 33.6 120 7.88 98 0.55 40 4.03 41 0.10 30 15.1 154 15.6 149 33.3 159
BlockOverlap [61]128.5 12.3 121 29.2 84 8.49 126 13.7 126 29.6 116 15.3 129 16.2 126 32.5 113 20.0 126 8.87 131 27.4 109 7.62 134 10.9 142 13.4 128 12.5 147 13.3 136 29.1 99 10.3 122 11.8 154 14.4 150 23.8 156 10.6 148 8.92 109 24.8 153
IAOF [50]132.0 14.7 125 37.8 122 14.8 139 17.3 136 33.2 128 18.7 136 22.7 137 44.3 137 23.3 129 20.9 147 38.7 143 24.5 150 9.60 118 13.3 127 8.28 129 13.0 134 38.8 140 7.37 94 4.20 124 7.90 113 2.59 106 14.5 153 13.4 142 32.0 158
2bit-BM-tele [96]133.1 20.3 138 39.1 126 26.1 150 8.84 116 26.8 105 9.29 118 11.1 106 30.7 107 7.60 106 8.06 129 29.9 124 5.91 131 11.0 143 13.7 134 11.8 146 18.0 148 37.1 134 19.8 150 17.1 159 20.4 159 30.8 159 6.54 132 11.7 136 11.8 138
Black & Anandan [4]134.0 15.1 127 45.4 134 18.1 144 16.6 134 36.3 134 16.9 133 23.3 140 44.9 138 27.8 133 13.5 141 38.1 141 13.1 142 11.1 145 15.7 151 7.97 123 11.6 127 39.6 141 11.0 127 5.17 131 9.06 120 2.27 102 7.28 135 12.3 138 10.2 135
UnFlow [127]135.6 45.7 160 58.8 149 25.7 148 28.2 151 44.0 147 31.2 151 38.6 158 68.3 160 37.0 152 19.4 146 46.0 147 16.6 145 13.8 154 14.9 149 18.2 154 20.9 151 49.2 151 23.5 152 2.86 110 6.76 101 0.22 43 3.12 96 10.4 125 2.27 54
GroupFlow [9]136.2 22.9 144 47.1 136 26.7 152 28.4 152 50.0 154 30.8 150 25.4 145 52.4 144 30.6 141 9.32 135 29.6 123 8.14 136 10.7 140 13.4 128 7.16 117 23.0 153 46.3 149 27.8 156 1.56 93 5.72 88 2.76 108 8.00 140 12.5 139 15.3 146
Nguyen [33]136.2 20.0 137 44.7 132 17.4 143 39.5 158 37.5 136 52.5 159 34.0 150 56.0 148 38.8 153 35.6 157 47.9 149 41.1 157 12.1 147 14.3 141 16.5 152 12.0 129 37.8 136 13.8 136 1.37 86 4.27 47 0.71 69 11.6 151 14.5 147 20.8 150
SILK [80]142.0 26.9 149 51.7 145 36.6 156 22.3 143 45.5 150 24.5 143 28.8 146 54.7 147 34.2 144 18.4 144 41.6 144 15.8 144 13.1 151 16.5 152 16.1 151 19.1 150 47.8 150 19.3 149 2.87 111 4.22 45 6.53 131 15.9 155 19.1 155 25.8 154
H+S_RVC [176]143.0 34.7 153 64.9 159 25.7 148 38.1 157 57.7 161 43.6 155 45.9 162 73.7 163 43.0 159 60.1 161 66.0 160 64.3 162 14.4 156 14.2 140 26.2 160 31.3 159 60.7 160 34.7 159 0.49 33 4.66 55 0.20 40 22.2 161 23.3 158 21.4 151
Heeger++ [102]143.9 42.8 158 66.4 162 26.2 151 25.0 148 60.7 162 19.8 139 38.4 157 66.9 157 28.0 134 23.5 149 49.3 150 19.7 147 10.6 139 13.4 128 8.12 125 40.8 161 67.2 163 45.1 161 2.04 103 10.9 129 1.70 92 11.2 149 15.6 149 12.8 140
Horn & Schunck [3]145.0 19.9 136 61.0 155 23.3 146 19.4 139 44.3 149 19.1 137 29.5 147 58.8 151 34.9 147 21.0 148 49.9 152 21.2 148 12.3 148 16.5 152 10.8 143 17.3 146 50.6 154 18.0 147 7.23 143 11.9 137 2.34 103 13.4 152 22.2 157 14.9 143
Periodicity [79]149.2 30.6 152 48.8 140 16.7 141 24.1 146 49.8 152 26.2 146 39.1 159 54.5 146 39.5 154 13.6 142 47.1 148 12.0 140 37.5 163 48.2 163 33.6 162 38.5 160 66.9 162 36.0 160 2.02 102 10.8 127 8.18 139 20.8 158 35.9 162 30.1 156
FFV1MT [104]150.0 39.5 156 59.3 150 25.4 147 21.8 142 56.3 160 19.1 137 38.0 156 67.0 158 34.9 147 24.3 150 55.7 156 22.2 149 17.7 159 18.9 159 25.5 159 41.8 162 66.3 161 45.5 162 3.73 118 12.9 144 6.35 129 11.2 149 15.6 149 12.8 140
TI-DOFE [24]150.3 44.7 159 66.3 161 66.5 162 44.2 160 50.5 155 54.8 161 43.5 161 72.0 161 44.7 161 48.6 159 63.3 158 54.0 159 13.6 153 17.7 156 15.1 150 17.2 144 50.3 153 19.0 148 3.07 113 5.50 82 2.93 112 21.5 159 24.7 160 33.9 160
SLK [47]151.7 28.9 151 63.3 158 36.4 155 42.3 159 54.0 159 52.8 160 36.6 154 67.7 159 42.5 158 51.4 160 54.3 155 60.0 161 14.5 157 16.7 154 20.8 157 21.5 152 53.4 158 24.1 153 3.92 121 6.27 95 5.91 128 21.7 160 23.7 159 31.5 157
Adaptive flow [45]154.5 49.6 161 62.1 156 66.8 163 37.4 155 46.5 151 43.1 154 34.9 152 58.6 150 41.7 156 27.3 152 53.5 154 28.7 151 16.1 158 18.2 158 17.6 153 25.3 157 52.9 156 25.1 155 45.4 162 38.1 162 74.4 161 9.25 144 14.4 146 13.9 142
PGAM+LK [55]155.2 35.2 154 65.7 160 44.1 158 31.5 153 51.1 156 36.1 153 30.9 148 60.0 155 36.8 151 33.0 155 72.3 162 32.7 154 13.8 154 14.4 143 22.6 158 24.6 155 53.2 157 24.6 154 27.1 160 32.6 161 26.2 157 17.0 156 20.4 156 28.4 155
FOLKI [16]155.3 27.4 150 59.9 151 40.6 157 37.4 155 51.5 157 46.6 157 32.4 149 61.6 156 34.2 144 26.3 151 50.6 153 30.2 152 18.2 161 19.7 160 26.3 161 24.6 155 56.6 159 28.8 157 10.3 152 13.9 147 26.7 158 27.1 162 26.9 161 45.3 162
HCIC-L [97]155.9 51.6 162 60.9 154 30.9 153 58.4 163 53.4 158 73.0 163 39.8 160 50.8 143 52.8 163 63.4 162 71.0 161 69.9 163 18.1 160 20.6 161 20.5 156 29.9 158 43.2 146 34.1 158 73.0 163 62.0 163 76.4 162 7.45 137 12.5 139 8.87 133
Pyramid LK [2]159.1 41.0 157 62.5 157 66.4 161 47.2 161 49.9 153 59.7 162 37.5 155 59.5 154 45.5 162 43.8 158 65.1 159 49.5 158 36.5 162 43.8 162 42.6 163 43.3 163 52.8 155 45.9 163 11.8 154 20.2 158 20.7 153 40.0 163 46.5 163 59.5 163
AdaConv-v1 [124]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
SepConv-v1 [125]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
SuperSlomo [130]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
CtxSyn [134]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
CyclicGen [149]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
TOF-M [150]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
MPRN [151]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
DAIN [152]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
FRUCnet [153]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
OFRI [154]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
FGME [158]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
MS-PFT [159]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
MEMC-Net+ [160]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
ADC [161]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
DSepConv [162]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
MAF-net [163]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
STAR-Net [164]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
AdaCoF [165]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
TC-GAN [166]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
FeFlow [167]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
DAI [168]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
SoftSplat [169]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
STSR [170]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
BMBC [171]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
GDCN [172]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
EDSC [173]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
MV_VFI [183]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
DistillNet [184]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
SepConv++ [185]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
EAFI [186]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
FLAVR [188]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
SoftsplatAug [190]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
ProBoost-Net [191]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
IDIAL [192]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
IFRNet [193]164.8 99.3 164 97.8 164 99.8 165 99.9 165 100.0 164 99.8 165 99.9 164 99.9 164 99.9 164 99.5 165 99.9 165 99.9 165 99.9 165 99.9 165 99.9 165 99.1 165 98.9 165 99.7 165 98.5 165 93.0 165 100.0 165 99.9 165 99.9 165 99.9 165
AVG_FLOW_ROB [137]165.5 99.3 164 98.3 199 99.2 164 99.8 164 100.0 164 99.7 164 99.9 164 99.9 164 99.9 164 98.3 164 96.8 164 98.0 164 96.2 164 96.6 164 93.9 164 87.7 164 86.6 164 88.2 164 96.9 164 84.2 164 98.7 164 93.0 164 98.4 164 95.3 164
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor 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.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[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.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.