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        
SD
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]14.9 7.07 25 15.8 45 3.85 3 5.66 3 14.3 38 2.52 1 6.62 1 12.1 36 2.00 2 8.50 13 26.8 55 0.84 4 4.25 1 5.11 2 2.91 3 5.15 4 13.5 7 1.70 1 1.32 2 2.86 20 0.75 2 6.39 43 12.1 43 1.53 4
RAFT-it [194]18.2 7.37 46 16.2 64 4.05 7 6.39 10 16.4 48 2.68 2 7.32 5 13.3 41 2.92 9 5.13 5 16.7 5 0.60 1 4.40 4 5.28 3 3.01 5 4.44 2 11.3 2 1.97 4 1.66 23 3.07 37 0.96 8 6.88 50 13.1 54 0.79 1
PMMST [112]19.6 6.46 4 14.1 4 3.23 1 5.42 1 12.7 36 3.51 19 8.20 12 14.7 47 3.66 16 7.46 6 17.8 6 4.34 10 4.79 19 5.67 14 3.91 29 6.77 10 15.2 11 3.61 7 1.74 32 3.36 72 1.34 23 5.95 42 11.3 42 2.25 7
NNF-Local [75]20.8 6.84 16 15.1 25 4.48 14 6.28 8 15.5 43 3.00 7 7.42 6 13.5 42 2.39 4 7.71 10 22.7 45 2.48 8 4.26 2 5.09 1 2.83 2 6.52 9 14.9 9 4.55 11 1.74 32 3.32 69 1.23 18 5.63 37 10.7 37 2.48 43
NN-field [71]25.0 7.29 37 16.0 54 4.74 29 6.15 4 15.2 42 3.02 10 7.77 10 14.1 46 2.71 7 7.56 7 22.8 46 1.96 7 4.49 6 5.36 6 3.09 6 5.72 7 14.1 8 1.96 3 1.96 54 3.34 70 1.32 21 5.70 38 10.8 38 2.49 44
MS_RAFT+_RVC [195]26.5 7.34 44 16.2 64 4.48 14 6.79 14 15.1 41 4.91 47 9.79 25 17.8 62 3.94 24 7.61 9 24.6 50 0.66 2 4.37 3 5.30 4 2.81 1 4.37 1 11.2 1 1.85 2 1.26 1 2.93 27 0.76 3 7.98 63 12.5 46 9.73 87
OFLAF [78]29.1 6.75 12 14.9 18 4.44 12 7.07 19 17.5 59 3.10 11 8.45 14 15.5 52 2.50 6 13.0 56 35.0 131 6.38 27 4.57 7 5.57 11 3.12 7 7.63 15 15.9 14 5.90 23 1.68 25 2.86 20 1.43 34 5.83 41 11.0 40 2.79 45
RAFT-TF_RVC [179]30.5 9.23 107 19.6 164 5.17 49 6.20 6 15.5 43 3.18 12 8.42 13 14.9 48 5.99 64 3.94 1 12.7 3 0.70 3 4.47 5 5.32 5 3.17 9 5.11 3 12.5 4 2.67 5 1.63 15 3.15 52 0.83 4 7.27 57 13.8 58 1.43 3
GMFlow_RVC [196]34.3 8.18 84 15.3 32 6.14 88 5.61 2 12.7 36 4.03 29 7.25 4 12.6 39 4.09 27 9.25 14 24.0 48 5.01 14 4.98 42 5.87 39 4.21 56 5.30 5 11.7 3 3.42 6 2.36 84 3.30 67 1.40 30 5.55 36 10.5 36 1.24 2
MDP-Flow2 [68]37.5 6.66 7 14.7 14 4.53 17 6.79 14 17.0 53 3.23 13 8.68 15 15.8 53 2.90 8 13.4 67 33.7 116 6.89 54 4.95 37 5.84 34 4.15 52 8.49 27 18.7 39 7.72 56 1.64 19 3.08 38 1.27 20 6.77 47 12.8 50 3.33 51
nLayers [57]41.2 7.20 32 16.0 54 4.66 26 6.25 7 14.7 39 3.70 24 7.72 9 13.7 44 4.81 40 13.1 60 34.8 129 6.69 39 4.76 16 5.75 22 4.12 49 7.19 12 14.9 9 4.40 10 1.99 56 3.10 43 1.80 61 8.22 66 15.6 68 6.10 73
FC-2Layers-FF [74]41.6 7.07 25 15.5 37 4.91 36 8.30 43 19.7 80 4.30 31 7.61 8 13.6 43 4.29 30 11.8 28 30.2 74 6.20 25 4.60 8 5.54 8 3.52 12 9.20 44 18.3 33 6.27 33 2.20 75 3.42 83 1.85 62 7.54 58 14.3 61 4.12 61
VCN_RVC [178]45.5 7.92 66 15.5 37 6.25 91 8.26 40 20.0 89 4.69 41 8.79 17 15.0 49 5.78 61 12.1 32 27.2 59 7.16 67 4.89 29 5.78 27 4.19 55 8.39 26 19.7 83 5.93 25 1.58 10 2.74 7 1.19 14 7.05 54 13.2 55 3.74 59
3DFlow [133]46.4 6.97 19 15.1 25 3.90 4 8.12 35 19.7 80 3.79 26 13.6 99 24.2 109 3.63 14 4.18 2 12.4 1 1.73 6 4.97 39 5.98 60 3.83 26 10.5 68 18.9 77 8.87 77 2.38 85 3.11 45 2.45 89 5.82 40 11.1 41 3.00 47
CoT-AMFlow [174]46.6 6.75 12 14.8 16 4.81 31 6.34 9 15.8 45 3.00 7 9.74 23 17.7 60 4.29 30 13.5 73 34.1 122 6.99 59 5.00 46 5.91 44 4.50 71 8.63 29 19.2 80 7.92 61 1.76 35 3.38 75 1.43 34 6.72 46 12.7 49 4.19 62
UnDAF [187]48.6 7.32 41 16.0 54 4.65 25 6.75 13 16.9 51 2.97 6 9.89 27 17.9 63 3.80 19 13.6 75 33.8 118 6.95 56 4.99 45 5.86 36 4.41 66 8.74 30 19.1 79 7.86 60 1.77 37 3.38 75 1.42 32 6.89 51 12.9 52 3.66 56
PRAFlow_RVC [177]48.8 7.95 72 16.9 120 5.13 47 6.83 16 16.2 47 3.98 28 11.0 71 19.3 72 5.54 59 11.3 24 29.8 69 4.91 13 4.82 20 5.73 19 3.69 19 5.59 6 13.4 6 3.70 8 1.50 6 3.02 31 0.83 4 17.8 133 22.5 112 21.6 170
ComponentFusion [94]49.0 7.22 33 15.9 50 4.61 21 7.60 25 19.2 74 3.30 14 9.70 22 17.6 58 3.77 18 11.1 22 31.0 83 4.45 11 4.96 38 5.88 41 4.25 58 10.9 74 23.7 110 9.40 86 1.90 51 3.08 38 1.69 55 8.00 64 15.1 65 4.57 65
FESL [72]51.7 6.97 19 15.3 32 4.47 13 9.74 72 21.4 103 5.49 66 11.4 73 20.2 75 4.25 29 12.5 39 31.5 90 6.81 44 4.72 12 5.71 17 3.72 22 7.03 11 16.0 15 4.81 12 2.21 78 3.49 90 1.94 67 11.1 90 17.6 82 10.1 90
NNF-EAC [101]52.5 6.83 15 14.9 18 4.80 30 7.59 24 18.0 61 4.31 32 9.03 18 16.1 54 3.09 11 13.2 63 32.2 100 7.10 63 5.06 59 5.96 51 4.02 39 8.19 22 17.1 19 6.04 29 1.79 40 3.30 67 1.38 29 17.0 130 27.6 136 18.0 150
AGIF+OF [84]52.9 7.17 30 15.6 40 4.93 37 10.2 83 22.1 112 5.16 53 12.5 87 21.2 88 4.88 42 12.5 39 31.7 95 6.76 41 4.78 18 5.73 19 3.91 29 7.85 18 16.3 17 5.20 14 1.83 44 3.10 43 1.71 57 10.8 87 17.6 82 11.0 94
Layers++ [37]53.3 7.19 31 15.7 42 5.08 43 6.15 4 14.8 40 3.42 17 7.83 11 14.0 45 4.84 41 10.9 19 26.9 57 6.19 24 4.83 24 5.84 34 4.36 63 12.4 95 25.2 123 10.5 100 2.43 87 3.56 95 1.92 65 8.66 69 16.1 70 7.77 80
PWC-Net_RVC [143]53.5 8.30 89 16.2 64 6.58 100 8.56 48 20.6 90 4.38 33 12.3 84 21.4 90 6.00 65 10.8 17 27.0 58 6.88 53 4.94 35 5.79 29 3.98 35 8.37 25 19.3 81 5.42 18 1.65 22 3.29 66 1.02 9 7.86 62 14.2 60 3.37 52
Correlation Flow [76]54.8 6.66 7 14.5 9 3.81 2 7.78 30 17.5 59 2.85 4 18.0 136 29.0 146 4.31 33 9.28 15 22.1 44 5.57 17 5.12 63 6.13 85 3.98 35 11.0 77 23.3 105 10.5 100 2.07 65 3.08 38 2.32 84 6.79 48 12.5 46 4.83 66
Efficient-NL [60]54.9 7.43 54 16.2 64 4.85 32 7.73 28 18.1 62 4.58 36 14.0 105 23.6 105 4.47 35 13.1 60 32.9 109 7.50 78 4.77 17 5.77 26 3.65 17 8.08 20 16.1 16 5.25 15 2.48 91 3.37 74 3.12 107 6.91 52 12.1 43 5.78 71
PH-Flow [99]55.6 7.38 48 15.9 50 5.22 52 9.30 62 19.5 76 5.71 69 9.62 20 17.2 56 5.09 43 13.4 67 34.5 124 7.10 63 4.82 20 5.73 19 3.82 25 8.36 24 17.1 19 5.35 17 2.66 97 3.43 85 3.42 116 7.13 56 13.3 57 5.33 70
MCPFlow_RVC [197]57.9 9.33 109 17.5 134 6.85 103 8.26 40 16.8 50 6.09 76 9.63 21 15.3 50 7.65 95 8.49 12 23.9 47 5.92 20 4.61 9 5.41 7 3.21 11 5.79 8 12.8 5 3.84 9 1.85 45 3.94 112 1.33 22 17.3 131 21.5 103 21.6 170
IROF++ [58]58.0 7.44 55 16.1 60 5.11 45 8.61 50 19.4 75 5.12 51 12.3 84 21.0 86 5.12 44 12.8 50 32.1 97 7.13 65 4.88 27 5.76 24 3.89 28 9.01 34 18.9 77 6.76 41 1.78 39 3.22 60 1.23 18 10.4 84 18.5 89 13.3 110
HAST [107]58.2 7.11 28 16.0 54 4.27 8 8.90 54 17.4 58 7.54 101 6.79 2 12.4 37 1.56 1 14.8 92 37.2 154 6.63 32 4.68 11 5.70 16 2.91 3 10.5 68 20.7 86 11.1 109 3.74 132 4.39 127 5.40 141 5.74 39 10.9 39 2.09 5
LME [70]58.5 7.04 23 15.6 40 4.53 17 6.68 11 16.9 51 2.85 4 13.6 99 22.6 97 12.0 156 11.5 26 27.8 60 6.39 28 5.03 52 5.93 48 4.52 73 12.4 95 27.0 136 10.9 108 1.76 35 3.38 75 1.43 34 6.62 45 12.5 46 2.86 46
CombBMOF [111]58.6 7.30 38 15.1 25 4.61 21 8.08 34 18.2 64 3.69 23 10.2 29 18.1 64 2.47 5 11.2 23 28.1 61 6.67 36 4.82 20 5.76 24 4.13 50 13.3 108 22.1 95 14.1 135 2.90 108 4.33 124 2.14 74 11.8 96 21.0 100 3.23 50
Classic+CPF [82]59.0 7.31 39 15.8 45 5.09 44 9.93 78 22.1 112 5.05 49 13.3 96 22.4 96 4.64 38 12.5 39 32.0 96 6.79 43 4.87 26 5.83 33 3.99 37 7.43 13 15.6 13 5.32 16 2.26 80 3.21 58 2.78 99 9.89 80 16.5 72 13.8 113
MLDP_OF [87]59.0 7.02 21 14.5 9 4.89 35 7.00 18 17.0 53 3.34 15 14.3 107 24.0 106 3.73 17 12.9 53 34.8 129 5.88 19 4.89 29 5.69 15 3.92 32 8.18 21 17.4 23 7.22 53 3.64 128 3.68 100 5.99 143 13.2 106 20.5 98 9.16 86
NL-TV-NCC [25]59.3 6.92 18 14.6 13 3.96 6 8.32 44 19.8 84 2.84 3 15.4 116 26.0 121 3.92 22 10.8 17 26.6 53 5.58 18 5.09 60 6.00 64 4.07 42 11.1 80 23.5 106 10.5 100 2.09 66 3.06 35 2.27 82 11.6 93 20.4 96 9.14 85
LSM [39]59.4 7.06 24 15.2 30 5.21 51 9.65 70 21.2 102 5.48 65 11.9 79 20.2 75 5.33 49 12.0 29 30.0 72 6.84 48 5.14 69 6.13 85 4.62 79 9.12 40 18.1 29 6.53 37 2.13 71 3.11 45 2.11 73 8.09 65 14.3 61 6.76 77
TC/T-Flow [77]59.8 6.31 2 13.3 2 4.85 32 11.5 137 23.6 126 6.67 88 13.4 98 23.2 103 3.00 10 14.2 86 36.9 153 6.33 26 4.72 12 5.64 12 3.64 15 7.70 16 17.1 19 5.61 22 2.00 57 3.45 88 2.86 101 10.9 89 18.2 87 3.59 55
WLIF-Flow [91]60.0 6.80 14 14.9 18 4.60 20 6.93 17 16.7 49 4.11 30 10.3 30 18.2 65 4.11 28 12.7 48 30.9 81 6.67 36 6.60 148 7.87 152 5.60 122 8.54 28 17.4 23 6.03 28 1.85 45 3.18 55 1.67 53 14.4 112 23.2 115 15.3 122
HCFN [157]60.0 6.51 5 14.1 4 4.64 23 8.25 38 20.6 90 4.51 34 10.1 28 18.2 65 4.68 39 13.4 67 35.1 133 6.09 22 4.73 15 5.55 9 3.64 15 8.77 32 18.6 37 7.20 51 4.73 148 5.10 143 5.62 142 11.6 93 19.6 92 14.0 115
Sparse-NonSparse [56]60.2 7.26 36 15.7 42 5.22 52 9.83 75 21.6 106 5.45 64 12.2 81 20.8 82 5.35 52 12.1 32 30.0 72 6.86 50 5.14 69 6.13 85 4.58 76 9.16 42 18.5 36 6.58 38 2.05 63 3.03 32 2.06 72 7.62 59 13.8 58 5.98 72
Ramp [62]61.9 7.32 41 15.8 45 5.20 50 8.74 51 19.8 84 5.27 59 11.4 73 19.7 74 5.40 55 12.5 39 31.6 93 6.86 50 4.97 39 5.88 41 4.08 44 9.04 35 18.3 33 7.00 48 2.65 96 3.36 72 4.00 130 8.65 68 15.3 67 11.7 99
PMF [73]62.6 7.59 61 16.5 110 4.94 38 7.64 26 18.3 67 3.66 21 7.48 7 13.2 40 2.31 3 14.7 91 36.3 148 6.84 48 4.66 10 5.64 12 3.18 10 9.85 50 21.3 89 9.22 81 3.62 127 5.25 149 3.70 126 7.12 55 13.2 55 6.82 78
Classic+NL [31]64.0 7.40 51 16.1 60 5.36 62 9.49 69 20.9 96 5.44 63 12.3 84 20.8 82 5.20 47 12.5 39 31.3 89 6.82 45 5.03 52 5.98 60 4.18 54 8.94 33 17.5 25 5.91 24 2.29 82 3.44 87 2.17 75 9.88 79 17.0 78 11.9 101
CostFilter [40]64.0 7.36 45 15.7 42 4.96 40 7.76 29 18.1 62 3.83 27 7.07 3 12.4 37 3.12 12 14.6 90 36.3 148 6.57 31 4.82 20 5.81 31 3.54 13 12.4 95 20.5 85 10.3 98 3.86 137 5.96 153 4.36 133 8.86 73 16.7 75 3.72 58
FlowFields+ [128]65.9 8.95 102 17.2 129 7.26 112 7.52 23 17.3 56 5.15 52 10.4 31 17.6 58 6.16 66 10.1 16 24.5 49 6.49 30 5.11 62 6.00 64 4.57 75 9.28 45 22.2 96 6.70 40 1.77 37 3.20 56 1.51 47 13.1 105 21.8 105 15.6 125
FMOF [92]67.5 7.14 29 15.5 37 5.28 56 10.4 122 22.7 118 5.42 60 10.8 67 19.0 71 3.90 21 12.2 35 31.0 83 6.63 32 4.98 42 5.97 54 4.10 45 10.0 59 17.2 22 6.98 46 2.46 89 3.40 80 4.60 134 14.7 114 23.2 115 10.1 90
WRT [146]67.7 7.40 51 15.9 50 3.93 5 9.33 63 21.1 100 3.42 17 21.1 161 31.0 167 6.88 78 4.33 3 13.0 4 1.43 5 4.84 25 5.80 30 4.44 69 13.6 112 21.4 91 10.8 106 1.71 30 2.85 17 1.65 52 16.7 127 20.4 96 20.8 166
RNLOD-Flow [119]68.4 6.72 10 14.9 18 4.39 10 9.09 57 21.0 98 5.06 50 15.2 114 25.8 117 5.42 56 12.6 46 32.2 100 6.64 34 5.46 108 6.48 120 4.34 62 8.35 23 17.8 27 6.16 31 2.82 103 3.90 111 3.36 114 9.02 74 16.1 70 9.83 88
TV-L1-MCT [64]69.0 7.42 53 16.1 60 5.22 52 9.84 76 21.6 106 5.20 55 14.3 107 24.7 112 5.27 48 12.5 39 31.2 88 7.21 69 5.01 48 5.90 43 4.41 66 9.10 38 18.8 76 7.14 50 2.17 74 2.78 9 4.69 135 9.81 78 16.8 77 11.5 96
IIOF-NLDP [129]69.1 7.31 39 15.4 34 4.42 11 8.37 45 19.9 87 3.01 9 15.4 116 25.9 119 4.00 25 7.56 7 18.6 42 4.73 12 6.04 133 7.28 146 5.15 109 10.1 60 21.3 89 9.54 88 1.74 32 2.90 24 1.50 44 15.8 119 21.6 104 20.5 164
SVFilterOh [109]69.1 7.94 69 17.5 134 4.94 38 8.27 42 19.8 84 3.66 21 9.83 26 17.7 60 4.59 36 13.4 67 34.5 124 6.82 45 4.89 29 5.93 48 3.15 8 10.4 66 22.7 98 9.35 85 3.51 124 4.72 136 4.17 131 7.68 60 14.3 61 4.90 67
ProbFlowFields [126]70.1 8.84 100 17.9 141 6.90 105 7.20 21 17.3 56 4.75 44 11.6 76 20.5 79 6.31 70 8.48 11 22.0 43 5.26 16 5.25 90 6.24 104 4.67 89 9.96 57 23.9 114 6.99 47 1.64 19 2.80 11 1.41 31 14.7 114 25.5 126 14.7 118
Complementary OF [21]70.8 7.37 46 15.1 25 5.30 59 9.46 65 22.5 116 4.63 37 13.0 91 22.8 99 4.04 26 14.8 92 37.9 162 6.87 52 4.97 39 5.86 36 4.39 65 11.0 77 24.4 118 8.06 65 1.79 40 2.79 10 2.22 78 12.2 97 22.0 108 11.2 95
EPPM w/o HM [86]71.8 7.33 43 14.5 9 5.00 42 7.20 21 17.2 55 3.41 16 11.8 77 20.8 82 3.20 13 12.6 46 31.1 87 7.00 60 5.14 69 6.08 78 4.67 89 12.0 89 22.7 98 9.97 94 4.48 147 3.69 102 6.02 144 10.4 84 17.6 82 11.5 96
MDP-Flow [26]72.5 6.73 11 14.1 4 5.59 71 6.70 12 16.0 46 4.65 39 9.78 24 17.2 56 6.61 75 13.0 56 34.7 128 6.48 29 5.54 112 6.17 94 5.84 125 10.5 68 23.6 108 7.81 59 1.89 49 3.42 83 1.37 26 20.0 152 32.5 156 19.1 156
ALD-Flow [66]72.8 6.69 9 14.4 8 4.54 19 12.5 147 25.7 142 6.93 93 14.3 107 24.9 113 4.29 30 14.8 92 35.3 138 7.04 61 4.98 42 5.92 46 3.66 18 10.1 60 23.6 108 6.92 44 2.02 59 3.23 61 2.86 101 10.2 83 18.9 91 6.45 76
TC-Flow [46]73.8 6.56 6 14.1 4 4.48 14 9.25 61 21.4 103 5.03 48 14.9 112 25.8 117 3.93 23 14.5 89 35.9 142 6.97 58 5.01 48 5.97 54 3.63 14 9.98 58 22.8 101 6.83 43 2.11 68 3.25 62 3.61 124 16.7 127 26.8 133 20.0 162
FlowFields [108]73.9 9.03 105 17.5 134 7.31 113 8.02 33 18.6 70 5.24 58 11.1 72 18.9 69 6.32 71 11.6 27 28.7 64 7.40 76 5.14 69 6.03 72 4.64 84 10.1 60 23.8 113 7.62 55 1.69 26 2.86 20 1.51 47 12.9 101 22.8 113 14.9 121
JOF [136]73.9 7.77 64 16.9 120 5.33 60 10.6 124 20.8 95 7.75 104 10.9 69 18.9 69 5.34 50 12.7 48 32.6 103 6.67 36 4.91 33 5.86 36 3.97 34 9.05 36 17.9 28 5.47 19 3.04 114 3.66 99 3.43 117 13.3 108 21.4 102 12.2 105
C-RAFT_RVC [181]74.9 11.3 133 20.0 172 8.25 134 9.80 74 19.5 76 7.34 98 12.5 87 20.6 80 7.33 90 12.3 37 29.3 68 8.16 89 5.16 75 5.96 51 4.63 81 7.59 14 17.0 18 5.94 26 2.40 86 4.74 137 1.93 66 6.80 49 12.8 50 2.13 6
ProFlow_ROB [142]75.2 7.98 75 17.0 122 5.55 70 9.17 59 21.5 105 5.69 68 13.9 103 24.5 111 5.39 54 13.9 80 32.3 102 7.54 79 5.19 84 6.19 97 4.26 59 9.15 41 21.8 93 5.47 19 1.57 9 2.92 25 1.15 13 13.9 111 23.8 119 12.3 106
S2F-IF [121]75.4 8.86 101 17.2 129 7.05 109 7.84 32 18.3 67 5.20 55 10.8 67 18.5 68 6.21 67 13.0 56 30.7 79 8.15 88 5.09 60 5.98 60 4.58 76 9.62 48 22.7 98 7.20 51 1.92 52 3.77 107 1.73 58 10.7 86 18.4 88 12.8 108
SimpleFlow [49]75.5 7.56 60 16.2 64 5.59 71 9.48 66 21.0 98 5.68 67 17.1 129 27.0 133 6.29 69 13.0 56 32.8 107 7.09 62 5.18 81 6.16 90 4.62 79 8.75 31 17.6 26 6.81 42 2.13 71 3.50 91 2.30 83 9.78 77 17.4 80 7.10 79
IROF-TV [53]76.5 7.55 59 16.1 60 5.46 67 9.23 60 21.8 108 5.88 72 13.3 96 22.2 95 5.50 58 12.8 50 31.6 93 7.28 71 5.12 63 6.09 79 4.67 89 13.3 108 29.6 156 9.97 94 1.60 11 3.12 49 1.06 10 11.5 92 21.3 101 11.5 96
PBOFVI [189]76.9 7.44 55 16.0 54 4.64 23 10.3 121 23.8 129 3.70 24 18.5 140 29.7 153 5.88 63 11.0 20 28.2 62 5.96 21 5.91 126 7.08 142 4.88 100 9.88 53 18.2 30 7.43 54 2.20 75 4.04 114 2.26 80 8.84 71 15.2 66 5.15 69
SRR-TVOF-NL [89]77.4 7.83 65 15.4 34 5.99 84 13.2 154 26.1 147 8.61 110 13.2 94 22.0 94 6.78 76 13.6 75 30.3 75 7.34 75 4.72 12 5.56 10 4.04 41 9.87 52 19.8 84 8.30 69 3.25 119 3.73 105 3.18 110 6.93 53 12.9 52 4.92 68
ACK-Prior [27]78.2 6.39 3 13.4 3 4.38 9 8.58 49 19.7 80 3.63 20 11.4 73 20.3 77 3.82 20 12.5 39 33.7 116 5.09 15 5.53 110 6.42 116 4.76 95 15.0 126 28.4 144 11.4 111 3.54 125 4.36 126 4.84 137 13.2 106 20.2 95 8.94 83
HBM-GC [103]78.7 8.35 93 18.4 146 4.98 41 7.66 27 18.2 64 5.20 55 13.8 102 24.2 109 5.34 50 12.0 29 30.5 77 6.83 47 5.04 55 6.02 70 4.43 68 9.34 46 15.5 12 7.92 61 3.03 113 4.57 132 2.51 93 16.1 122 26.0 128 17.9 148
LiteFlowNet [138]79.1 9.19 106 16.6 111 7.02 108 8.23 37 18.9 73 4.53 35 12.9 89 21.5 91 6.23 68 12.0 29 26.7 54 7.32 74 5.39 105 6.23 101 5.47 118 9.09 37 18.7 39 6.31 34 2.02 59 3.14 51 1.47 37 19.2 145 24.7 122 21.9 175
Sparse Occlusion [54]80.8 7.38 48 15.8 45 5.28 56 8.25 38 19.9 87 4.71 42 15.5 119 26.3 127 4.63 37 13.5 73 33.3 115 6.92 55 5.25 90 6.26 106 4.11 47 9.70 49 21.1 88 5.94 26 4.85 149 5.95 152 3.71 127 10.8 87 20.0 94 8.01 82
2DHMM-SAS [90]81.2 7.39 50 15.9 50 5.25 55 10.7 127 23.4 123 5.43 61 18.0 136 27.0 133 7.95 135 13.1 60 32.7 105 7.28 71 4.89 29 5.78 27 4.01 38 9.88 53 18.2 30 6.37 35 2.50 94 3.39 78 3.37 115 13.8 110 22.4 111 15.5 124
ROF-ND [105]81.5 7.02 21 14.7 14 4.66 26 8.18 36 19.5 76 4.66 40 15.5 119 25.9 119 5.47 57 4.68 4 12.6 2 2.76 9 5.93 127 7.12 143 5.27 111 12.2 91 25.4 126 9.09 80 4.23 144 4.20 119 3.32 113 14.7 114 22.1 110 18.8 154
DPOF [18]83.2 8.43 95 16.8 115 6.36 95 10.7 127 20.7 93 9.52 119 8.72 16 15.4 51 3.63 14 11.3 24 29.1 66 6.09 22 5.34 98 6.18 95 5.38 116 12.2 91 22.4 97 8.06 65 5.27 150 3.55 92 6.79 149 8.85 72 16.5 72 4.24 63
COFM [59]83.9 8.49 97 18.5 149 5.95 80 8.44 46 18.7 71 4.71 42 13.0 91 22.9 100 5.84 62 13.8 78 35.2 136 6.78 42 5.63 118 6.58 123 5.94 126 11.7 86 23.5 106 9.80 90 2.29 82 3.20 56 2.72 96 6.42 44 12.1 43 3.07 49
OFH [38]84.1 7.25 35 15.0 24 5.29 58 11.1 131 25.0 138 7.19 97 18.6 142 29.1 148 5.56 60 16.0 108 40.8 180 7.44 77 5.05 56 5.92 46 4.28 60 11.4 82 26.0 130 8.73 73 1.64 19 3.04 33 1.36 25 12.5 99 23.3 117 7.79 81
TCOF [69]84.8 7.46 57 15.1 25 5.70 74 9.13 58 21.1 100 5.43 61 19.6 148 29.8 154 8.31 139 12.9 53 31.0 83 7.17 68 6.02 132 7.00 137 4.59 78 7.92 19 18.4 35 6.11 30 3.78 134 4.09 116 5.18 139 8.51 67 15.9 69 3.80 60
ResPWCR_ROB [140]84.8 8.30 89 14.5 9 7.12 110 8.82 52 19.6 79 5.91 73 11.8 77 19.3 72 7.90 134 12.4 38 28.5 63 7.89 85 5.18 81 5.97 54 5.36 114 10.9 74 23.9 114 8.84 76 2.85 105 3.65 98 2.34 85 14.7 114 21.8 105 16.2 135
PGM-C [118]85.2 9.43 111 18.5 149 7.51 119 9.84 76 23.4 123 6.05 75 12.0 80 20.6 80 7.17 83 15.8 104 35.3 138 9.67 107 5.20 86 6.11 81 4.66 86 9.86 51 23.7 110 7.06 49 1.63 15 2.84 16 1.49 43 11.1 90 20.8 99 6.23 75
ComplOF-FED-GPU [35]87.2 7.49 58 15.4 34 5.37 64 12.1 143 26.5 154 7.51 100 13.1 93 22.7 98 4.33 34 15.6 101 37.7 161 7.55 81 4.94 35 5.82 32 4.13 50 12.3 93 27.7 140 8.48 71 2.49 93 3.04 33 3.56 121 12.9 101 23.9 120 9.01 84
S2D-Matching [83]87.5 8.25 86 18.0 143 5.76 77 10.9 129 22.8 119 5.71 69 17.3 130 28.5 139 6.38 73 12.1 32 30.3 75 6.65 35 5.15 74 6.13 85 4.63 81 9.18 43 19.5 82 6.69 39 2.66 97 3.35 71 3.50 118 11.6 93 19.9 93 14.7 118
SegFlow [156]87.9 9.47 115 18.6 152 7.51 119 10.2 83 24.1 133 6.22 79 12.2 81 21.0 86 7.22 84 16.1 109 36.3 148 9.76 110 5.21 89 6.12 83 4.69 92 10.1 60 24.2 117 7.76 58 1.66 23 2.89 23 1.50 44 9.31 76 17.5 81 4.27 64
OAR-Flow [123]88.5 8.08 79 16.8 115 6.19 90 17.4 169 28.9 166 12.3 166 16.3 125 26.7 132 7.01 80 15.1 97 35.2 136 7.31 73 5.17 78 6.16 90 4.24 57 9.51 47 22.9 103 5.52 21 1.54 8 2.98 29 1.59 51 9.10 75 17.1 79 3.69 57
AggregFlow [95]92.3 10.3 126 21.3 184 6.91 106 15.1 162 27.6 161 10.7 124 14.0 105 24.0 106 8.70 141 14.1 83 35.0 131 7.15 66 5.05 56 6.03 72 4.02 39 7.73 17 18.2 30 5.09 13 2.13 71 4.40 128 1.67 53 9.91 81 18.1 86 6.13 74
CPM-Flow [114]94.5 9.46 113 18.6 152 7.51 119 10.0 80 23.7 127 6.20 78 12.2 81 20.9 85 7.13 81 15.8 104 35.6 141 9.71 109 5.20 86 6.12 83 4.65 85 10.9 74 23.7 110 8.90 78 1.73 31 3.15 52 1.51 47 14.5 113 26.0 128 13.6 112
AdaConv-v1 [124]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
SepConv-v1 [125]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
SuperSlomo [130]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
CtxSyn [134]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
CyclicGen [149]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
TOF-M [150]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
MPRN [151]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
DAIN [152]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
FRUCnet [153]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
OFRI [154]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
FGME [158]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
MS-PFT [159]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
MEMC-Net+ [160]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
ADC [161]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
DSepConv [162]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
MAF-net [163]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
STAR-Net [164]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
AdaCoF [165]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
TC-GAN [166]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
FeFlow [167]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
DAI [168]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
SoftSplat [169]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
STSR [170]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
BMBC [171]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
GDCN [172]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
EDSC [173]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
MV_VFI [183]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
DistillNet [184]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
SepConv++ [185]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
EAFI [186]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
FLAVR [188]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
SoftsplatAug [190]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
ProBoost-Net [191]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
IDIAL [192]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
IFRNet [193]95.1 13.0 149 16.4 74 8.62 140 10.2 83 9.17 1 11.5 129 10.7 32 11.1 1 7.66 96 16.3 114 17.8 6 14.4 140 10.8 161 8.97 158 16.5 161 19.7 151 18.7 39 19.4 153 19.7 165 17.1 165 8.18 154 3.51 1 4.92 1 2.42 8
CompactFlow_ROB [155]95.3 11.5 137 20.6 178 8.79 176 8.99 56 18.8 72 6.75 90 14.8 110 21.3 89 14.7 164 14.0 81 32.1 97 9.13 97 5.17 78 6.02 70 4.82 99 10.4 66 22.8 101 7.73 57 1.63 15 2.68 5 0.88 7 19.0 142 24.6 121 24.3 180
EpicFlow [100]95.5 9.39 110 18.4 146 7.50 118 10.0 80 23.8 129 6.29 81 15.8 122 26.6 130 7.35 92 15.5 99 34.4 123 9.65 105 5.20 86 6.11 81 4.66 86 10.2 64 24.5 119 8.18 68 1.63 15 2.81 13 1.48 38 15.8 119 24.8 123 17.1 144
Occlusion-TV-L1 [63]97.0 7.73 63 16.4 74 5.36 62 9.48 66 22.4 115 6.18 77 19.2 145 30.0 157 7.14 82 14.4 88 33.8 118 7.91 86 5.31 97 6.27 108 4.47 70 11.9 88 27.9 141 8.04 63 2.09 66 3.08 38 1.50 44 21.9 162 35.3 172 17.5 145
RFlow [88]98.1 7.10 27 14.9 18 5.40 65 8.98 55 21.9 110 5.19 54 18.5 140 29.3 150 5.35 52 18.1 162 44.9 198 9.86 113 5.12 63 6.01 67 4.38 64 13.0 105 29.3 153 9.93 93 2.28 81 2.85 17 3.52 119 20.3 153 33.3 162 16.1 133
ContinualFlow_ROB [148]99.2 11.4 135 20.8 179 8.47 138 9.76 73 18.5 69 7.94 107 16.5 126 26.6 130 11.7 154 15.7 102 37.2 154 8.85 96 5.25 90 5.97 54 5.27 111 11.8 87 24.9 121 11.4 111 1.53 7 3.06 35 1.10 11 12.4 98 17.7 85 13.1 109
FF++_ROB [141]100.2 9.92 121 19.4 161 7.55 123 8.87 53 20.9 96 5.83 71 15.3 115 25.3 115 7.95 135 11.0 20 25.4 51 7.23 70 5.19 84 6.10 80 4.80 97 17.1 135 25.3 125 13.2 127 1.88 47 2.96 28 2.77 97 18.7 139 27.2 134 25.3 182
Adaptive [20]101.2 7.94 69 17.0 122 5.33 60 10.2 83 23.9 131 6.28 80 21.2 162 31.7 176 7.69 131 13.6 75 29.8 69 7.87 84 4.88 27 5.75 22 3.71 21 13.2 106 28.9 150 9.72 89 3.21 118 4.71 135 2.91 103 19.3 147 30.5 145 15.6 125
DMF_ROB [135]101.5 8.27 87 16.7 113 6.36 95 11.7 140 26.4 152 7.10 96 17.8 135 28.6 141 7.33 90 15.9 107 35.9 142 9.46 101 5.05 56 5.97 54 4.51 72 12.8 103 27.4 137 9.90 92 1.60 11 2.99 30 1.48 38 19.8 151 32.0 152 16.8 140
Steered-L1 [116]102.0 5.97 1 12.7 1 4.67 28 7.14 20 18.2 64 4.63 37 13.2 94 23.3 104 5.12 44 15.2 98 38.1 164 7.54 79 5.85 125 6.73 127 6.98 146 13.7 114 26.5 132 11.7 117 6.39 155 4.25 121 13.3 192 22.3 165 32.7 158 20.3 163
DeepFlow2 [106]102.1 8.14 81 16.6 111 5.96 82 14.1 156 26.5 154 10.2 120 15.8 122 26.2 125 6.46 74 16.5 151 37.4 158 9.54 103 5.01 48 5.94 50 3.72 22 10.7 71 25.1 122 8.08 67 1.92 52 3.12 49 2.45 89 20.3 153 32.1 154 16.3 136
TF+OM [98]103.5 7.97 74 16.8 115 5.98 83 9.40 64 20.7 93 6.33 82 15.4 116 22.9 100 17.5 170 13.4 67 31.5 90 8.10 87 5.13 67 6.06 77 4.66 86 13.9 115 29.3 153 14.0 133 2.47 90 4.09 116 2.00 68 18.3 137 29.4 142 19.3 158
Aniso. Huber-L1 [22]103.6 7.96 73 16.3 72 6.10 87 11.4 134 24.7 136 6.77 91 20.6 155 29.6 152 7.26 86 13.2 63 29.2 67 7.77 83 5.52 109 6.58 123 4.29 61 12.4 95 26.7 134 8.83 75 2.93 110 3.68 100 3.10 106 16.5 126 27.4 135 13.9 114
LSM_FLOW_RVC [182]105.7 11.6 139 19.9 169 9.11 179 14.3 158 29.2 169 9.06 114 18.9 144 28.8 145 12.4 158 18.3 165 39.8 172 11.9 132 5.14 69 5.98 60 4.73 93 10.7 71 21.8 93 9.34 84 1.70 29 2.66 4 1.19 14 7.77 61 14.3 61 3.43 53
OFRF [132]106.6 9.69 117 19.6 164 6.25 91 22.2 188 29.4 170 20.7 191 21.6 166 30.1 158 17.0 168 14.1 83 31.0 83 8.47 92 4.93 34 5.87 39 3.94 33 9.10 38 18.6 37 6.40 36 2.84 104 4.62 134 3.66 125 12.6 100 16.7 75 15.9 132
LocallyOriented [52]107.5 9.89 119 19.9 169 6.55 98 14.7 161 27.7 162 11.0 126 21.7 169 31.9 178 7.32 89 13.3 66 30.5 77 8.32 90 5.16 75 6.04 74 4.11 47 9.90 55 21.6 92 8.75 74 2.20 75 3.43 85 2.17 75 18.3 137 26.0 128 19.6 159
EAI-Flow [147]108.6 10.4 129 19.0 158 7.83 125 13.2 154 25.8 143 9.43 118 13.7 101 21.6 92 8.47 140 14.8 92 33.0 110 9.68 108 5.12 63 6.01 67 4.74 94 11.6 83 25.7 128 9.23 82 3.66 129 3.57 96 2.04 70 13.4 109 24.8 123 10.5 93
AugFNG_ROB [139]108.9 12.7 146 22.1 185 9.46 182 12.1 143 24.6 135 9.39 117 18.8 143 27.1 137 14.7 164 14.0 81 30.9 81 9.24 99 5.03 52 5.72 18 5.09 106 11.0 77 24.0 116 9.53 87 1.82 43 3.25 62 1.22 16 18.2 136 23.7 118 21.6 170
LFNet_ROB [145]110.1 10.1 124 17.0 122 8.16 133 9.48 66 21.8 108 6.00 74 16.8 127 26.1 123 11.1 151 13.4 67 29.9 71 8.73 95 5.40 106 6.20 98 5.58 121 13.3 108 29.4 155 10.0 96 2.04 62 3.21 58 1.85 62 22.7 169 35.6 173 21.8 174
SegOF [10]110.9 9.43 111 17.7 137 8.06 130 12.0 142 22.9 121 10.4 123 17.0 128 26.1 123 12.6 159 13.8 78 26.8 55 11.2 126 5.53 110 6.26 106 6.06 129 19.0 148 35.6 192 18.8 151 1.37 4 2.60 2 0.83 4 16.4 124 30.0 143 14.0 115
TriangleFlow [30]111.7 8.08 79 17.0 122 5.12 46 11.7 140 26.1 147 6.98 95 19.5 146 30.3 161 6.34 72 12.9 53 33.0 110 6.71 40 7.00 152 8.16 156 6.63 143 12.8 103 24.5 119 10.5 100 3.59 126 5.17 147 3.27 112 12.9 101 21.9 107 12.1 103
CVENG22+RIC [199]111.8 9.46 113 18.8 156 7.38 115 11.2 132 25.8 143 6.73 89 17.4 132 28.7 142 7.56 93 16.3 114 36.4 151 10.1 118 6.99 151 7.88 153 6.07 131 12.4 95 28.3 142 10.7 105 1.62 13 2.75 8 1.48 38 16.0 121 28.6 138 10.1 90
SIOF [67]112.0 8.21 85 17.0 122 5.49 68 13.0 152 27.4 160 8.63 111 20.1 153 29.0 146 16.3 167 16.8 153 37.3 157 10.0 116 5.40 106 6.34 112 4.88 100 11.6 83 25.4 126 10.1 97 1.81 42 3.27 64 1.34 23 15.1 118 25.1 125 11.9 101
CRTflow [81]112.8 7.92 66 16.0 54 5.91 79 11.4 134 23.7 127 6.55 86 19.8 150 30.1 158 7.77 132 17.2 158 41.3 183 9.76 110 5.34 98 6.30 109 3.69 19 15.8 131 31.0 168 14.3 136 2.12 70 2.92 25 2.35 86 19.2 145 32.9 160 15.3 122
DeepFlow [85]114.0 8.73 98 17.1 128 6.26 93 15.3 165 26.7 157 11.9 165 17.3 130 26.5 129 14.1 163 18.6 169 42.8 192 11.0 123 5.00 46 5.91 44 3.75 24 11.2 81 26.2 131 8.35 70 1.88 47 2.80 11 2.60 94 22.5 167 33.6 163 17.5 145
Fusion [6]114.4 8.76 99 17.7 137 7.01 107 7.82 31 19.7 80 4.78 45 10.9 69 18.4 67 7.23 85 12.8 50 32.6 103 8.32 90 7.04 153 8.11 154 6.57 141 14.9 124 28.3 142 13.2 127 4.37 146 5.18 148 2.77 97 26.2 182 38.6 184 26.4 184
IRR-PWC_RVC [180]114.6 13.4 186 23.3 190 9.25 181 13.0 152 24.1 133 9.24 116 17.7 134 26.2 125 17.2 169 13.2 63 25.9 52 11.0 123 5.13 67 5.96 51 4.77 96 9.91 56 23.0 104 6.24 32 2.59 95 4.31 123 1.70 56 19.3 147 26.4 131 21.5 169
TriFlow [93]114.9 9.01 104 18.5 149 6.60 101 11.4 134 26.4 152 7.40 99 20.9 158 29.9 156 20.9 178 12.2 35 30.8 80 6.95 56 5.26 95 6.16 90 4.88 100 12.0 89 26.5 132 11.6 115 6.97 156 4.54 130 6.57 148 13.0 104 22.0 108 9.86 89
p-harmonic [29]115.2 8.15 83 16.2 64 6.50 97 9.66 71 22.6 117 6.57 87 21.2 162 31.2 169 9.65 144 15.7 102 33.9 120 10.0 116 5.18 81 6.04 74 5.31 113 14.3 120 30.3 163 12.2 123 3.10 115 3.55 92 1.91 64 23.1 171 34.8 170 17.8 147
CBF [12]115.9 7.23 34 14.9 18 5.16 48 9.95 79 21.9 110 7.69 103 17.6 133 27.0 133 7.28 88 16.4 150 39.3 171 9.18 98 6.34 143 7.35 149 6.11 133 13.4 111 28.4 144 8.52 72 5.54 152 5.11 144 6.41 146 18.7 139 30.8 146 16.4 137
Brox et al. [5]116.0 8.46 96 16.7 113 6.56 99 11.3 133 26.2 149 6.94 94 15.0 113 25.4 116 6.89 79 17.4 159 38.8 167 9.80 112 5.99 130 6.88 134 6.26 135 14.1 118 31.1 171 12.0 119 2.03 61 3.41 82 1.14 12 19.1 144 30.3 144 12.1 103
CLG-TV [48]117.9 7.94 69 16.2 64 5.80 78 10.5 123 24.0 132 6.44 84 19.9 151 29.8 154 6.83 77 14.1 83 31.5 90 7.73 82 5.98 128 7.01 138 5.15 109 14.8 123 31.0 168 12.2 123 4.20 143 4.80 138 5.22 140 19.3 147 32.6 157 15.7 129
TV-L1-improved [17]118.7 7.64 62 16.2 64 5.67 73 10.1 82 23.4 123 6.38 83 21.3 164 32.0 181 9.27 143 17.5 160 42.1 187 9.54 103 5.25 90 6.13 85 4.07 42 14.5 121 30.4 165 11.4 111 3.38 121 5.02 141 2.99 105 19.6 150 32.1 154 16.6 139
EPMNet [131]120.2 11.6 139 20.5 176 8.03 129 17.7 171 28.9 166 13.2 171 12.9 89 20.3 77 10.7 147 15.5 99 37.4 158 9.48 102 5.36 102 6.23 101 4.94 103 14.0 116 29.9 159 12.2 123 2.97 111 5.82 151 2.01 69 10.1 82 18.8 90 3.51 54
FlowNet2 [120]120.9 12.8 147 23.3 190 8.09 131 16.8 168 28.5 163 12.5 167 13.9 103 21.6 92 12.0 156 15.0 96 34.0 121 9.98 115 5.36 102 6.23 101 4.94 103 14.0 116 29.9 159 12.2 123 3.36 120 6.60 157 2.24 79 8.83 70 16.6 74 3.02 48
Classic++ [32]122.0 8.05 77 17.4 133 6.09 86 11.5 137 26.3 151 6.91 92 18.1 138 28.7 142 8.18 137 16.2 110 39.0 169 8.57 93 5.36 102 6.33 110 4.54 74 15.0 126 30.4 165 11.6 115 2.70 100 3.55 92 2.94 104 21.9 162 34.0 166 17.9 148
WOLF_ROB [144]122.1 9.97 122 18.4 146 7.33 114 20.8 179 34.8 195 13.9 173 22.2 176 30.7 165 10.9 148 17.0 157 33.2 114 12.3 134 5.16 75 6.01 67 5.11 108 10.2 64 20.7 86 9.05 79 1.97 55 3.28 65 2.48 92 17.9 135 23.1 114 21.3 168
Local-TV-L1 [65]123.0 9.74 118 17.9 141 6.89 104 18.4 174 29.4 170 14.9 175 24.4 180 30.8 166 20.2 176 19.4 174 42.4 190 12.7 136 5.35 101 6.00 64 4.10 45 13.6 112 28.9 150 9.26 83 1.62 13 2.58 1 1.48 38 20.3 153 32.0 152 16.4 137
Rannacher [23]124.5 8.07 78 16.8 115 6.15 89 10.6 124 24.8 137 6.51 85 21.9 173 32.6 187 10.9 148 18.4 166 43.3 194 10.5 119 5.27 96 6.18 95 4.17 53 15.5 129 32.3 178 12.0 119 2.69 99 3.57 96 2.68 95 17.8 133 31.0 147 16.1 133
StereoOF-V1MT [117]125.0 8.14 81 15.8 45 5.42 66 17.6 170 34.3 193 10.3 121 21.6 166 31.5 173 7.27 87 15.8 104 32.7 105 10.7 120 5.62 117 6.40 114 6.00 128 16.6 134 30.0 161 15.5 138 2.01 58 3.08 38 3.15 108 33.6 192 44.0 193 32.8 189
BriefMatch [122]125.3 6.91 17 14.8 16 4.85 32 11.0 130 22.8 119 8.24 108 9.42 19 16.6 55 5.13 46 16.7 152 40.7 179 8.61 94 9.76 159 10.6 195 14.1 159 18.2 145 31.0 168 17.4 147 9.26 160 6.60 157 20.9 198 28.0 186 36.5 175 34.9 191
F-TV-L1 [15]126.5 8.41 94 16.8 115 6.31 94 18.0 173 29.7 172 12.8 168 21.6 166 30.5 162 10.1 146 18.2 163 42.3 189 9.65 105 5.02 51 5.97 54 3.91 29 14.1 118 30.8 167 10.6 104 2.79 101 4.90 139 2.35 86 20.5 156 32.7 158 15.6 125
Dynamic MRF [7]128.9 8.32 92 17.3 132 5.95 80 12.3 145 28.5 163 7.75 104 19.6 148 31.8 177 7.56 93 18.4 166 42.2 188 11.6 130 5.25 90 6.16 90 4.80 97 17.7 139 34.4 188 16.6 143 1.89 49 2.63 3 3.21 111 30.3 188 43.6 192 29.0 186
Bartels [41]129.1 8.31 91 17.7 137 5.51 69 8.46 47 20.6 90 4.89 46 14.8 110 26.0 121 7.89 133 18.5 168 43.6 195 11.1 125 6.18 136 6.51 122 8.63 154 15.6 130 32.6 180 13.9 132 3.86 137 4.56 131 7.09 150 22.5 167 36.5 175 18.4 152
Shiralkar [42]130.8 7.92 66 15.2 30 5.73 75 14.6 160 30.3 173 9.04 113 21.7 169 31.2 169 9.77 145 19.6 176 41.5 184 13.2 138 5.17 78 6.04 74 4.63 81 18.0 144 31.1 171 14.7 137 3.67 130 3.40 80 4.74 136 23.9 177 36.6 177 18.9 155
DF-Auto [113]130.9 10.7 132 19.8 168 7.42 117 16.3 167 25.3 139 13.1 170 19.5 146 28.5 139 17.8 172 16.9 155 37.2 154 10.8 121 6.76 150 8.12 155 5.56 120 10.8 73 25.2 123 6.95 45 3.69 131 4.92 140 1.48 38 17.7 132 27.9 137 14.6 117
GraphCuts [14]132.4 9.24 108 17.2 129 7.53 122 22.1 186 33.0 187 16.8 183 15.9 124 23.1 102 15.6 166 14.2 86 28.9 65 9.34 100 5.83 124 6.82 130 6.25 134 18.5 147 29.7 157 12.0 119 2.85 105 3.39 78 3.52 119 23.8 176 36.1 174 19.1 156
Second-order prior [8]134.8 8.04 76 16.3 72 6.01 85 12.5 147 26.5 154 9.10 115 21.0 159 31.1 168 9.23 142 16.2 110 36.2 147 9.93 114 5.70 121 6.67 126 5.09 106 20.7 188 34.1 186 21.0 190 3.76 133 3.89 110 4.25 132 18.9 141 31.8 151 19.9 161
Filter Flow [19]136.7 10.5 130 19.4 161 8.33 135 12.5 147 25.8 143 8.69 112 19.9 151 27.0 133 21.7 181 19.0 171 33.1 113 15.9 177 5.34 98 6.21 99 5.37 115 16.2 133 26.7 134 15.5 138 3.46 123 4.48 129 2.26 80 23.3 175 31.5 150 18.5 153
CNN-flow-warp+ref [115]136.9 9.91 120 19.6 164 7.85 126 10.6 124 22.9 121 8.55 109 21.3 164 32.1 183 11.9 155 18.7 170 42.0 186 11.3 127 5.56 113 6.34 112 6.08 132 12.3 93 27.6 138 10.8 106 2.06 64 3.69 102 3.16 109 33.3 190 40.4 187 34.7 190
FlowNetS+ft+v [110]137.7 8.96 103 17.8 140 6.83 102 14.2 157 26.2 149 11.1 127 22.3 177 32.2 184 12.7 160 16.8 153 36.1 146 10.9 122 6.31 142 7.29 147 6.26 135 12.5 100 28.8 148 9.88 91 3.84 136 6.75 159 6.30 145 16.4 124 29.0 140 14.7 118
IAOF2 [51]139.2 10.0 123 19.9 169 7.91 128 14.4 159 26.7 157 10.9 125 22.0 175 32.2 184 17.6 171 19.1 172 33.0 110 17.1 181 5.81 123 6.86 132 4.94 103 12.6 101 25.9 129 11.9 118 4.26 145 4.11 118 7.75 153 16.2 123 26.5 132 13.5 111
StereoFlow [44]139.5 16.2 193 22.6 188 13.9 195 22.1 186 31.6 179 18.8 188 24.7 181 30.6 164 21.2 180 23.3 188 39.9 173 19.6 188 5.98 128 6.22 100 7.11 148 11.6 83 27.6 138 8.05 64 1.36 3 2.85 17 0.65 1 20.7 157 33.7 164 17.0 143
Ad-TV-NDC [36]143.5 12.1 144 18.6 152 10.7 187 25.5 192 32.0 183 22.2 192 29.3 194 34.3 192 22.8 185 16.9 155 32.8 107 12.2 133 5.99 130 7.20 145 3.83 26 12.6 101 28.5 146 10.3 98 2.79 101 4.07 115 1.78 59 24.1 178 31.4 149 25.1 181
TVL1_RVC [175]144.4 12.9 148 20.8 179 9.79 185 21.3 183 30.9 176 17.9 187 27.9 188 33.7 188 23.5 189 20.6 178 37.9 162 16.7 179 5.57 114 6.47 119 5.47 118 14.5 121 32.1 177 12.0 119 1.69 26 2.82 15 1.22 16 23.1 171 36.6 177 18.3 151
LDOF [28]145.5 9.66 116 18.9 157 7.13 111 15.1 162 29.1 168 11.3 128 15.6 121 25.1 114 10.9 148 20.9 181 43.1 193 14.9 175 6.12 134 7.01 138 6.26 135 16.0 132 31.2 173 13.2 127 3.89 139 5.61 150 8.96 189 19.0 142 33.0 161 11.7 99
IAOF [50]145.6 10.1 124 18.6 152 7.89 127 22.2 188 33.7 190 15.9 179 33.0 198 39.2 199 23.7 190 16.2 110 32.1 97 11.6 130 5.80 122 6.87 133 5.39 117 17.8 141 30.1 162 11.4 111 3.13 117 3.69 102 3.88 129 22.4 166 29.3 141 21.6 170
Nguyen [33]145.8 11.4 135 19.6 164 8.44 137 21.0 182 31.7 181 17.7 185 29.8 196 36.3 196 24.1 193 18.2 163 34.6 127 13.9 139 6.28 138 6.85 131 7.51 151 15.4 128 33.0 181 14.0 133 2.24 79 3.11 45 1.79 60 21.6 160 33.9 165 15.8 131
2D-CLG [1]147.2 15.2 191 24.5 195 11.2 189 15.1 162 25.9 146 13.5 172 27.5 187 33.9 189 24.7 194 22.2 185 38.3 165 19.0 187 5.67 119 6.44 117 6.29 138 17.5 137 34.3 187 16.4 142 1.47 5 2.68 5 1.54 50 21.7 161 34.6 169 16.9 142
SPSA-learn [13]148.4 11.3 133 19.4 161 8.52 139 20.9 180 34.2 192 16.2 182 26.5 185 33.9 189 22.4 184 22.5 187 39.9 173 18.9 186 5.59 115 6.41 115 5.94 126 17.8 141 31.4 175 18.3 150 2.11 68 3.11 45 1.37 26 24.3 179 35.1 171 19.7 160
UnFlow [127]149.5 16.0 192 25.1 196 11.3 190 12.7 151 22.2 114 11.7 164 20.4 154 27.6 138 13.6 161 20.8 179 36.0 144 17.9 184 6.34 143 6.89 135 7.74 152 17.7 139 33.5 183 17.1 146 2.92 109 4.33 124 1.37 26 20.7 157 37.3 182 15.6 125
Learning Flow [11]149.5 8.28 88 17.0 122 5.75 76 12.3 145 28.5 163 7.79 106 18.4 139 28.7 142 8.29 138 22.2 185 40.6 178 17.3 182 8.52 154 10.3 194 7.04 147 19.9 186 35.1 190 16.8 145 3.11 116 4.59 133 3.59 123 26.9 184 40.0 186 20.9 167
HBpMotionGpu [43]149.6 12.2 145 22.1 185 8.34 136 17.9 172 31.4 178 14.7 174 29.2 193 37.8 198 20.6 177 19.1 172 44.6 197 11.5 129 5.60 116 6.45 118 6.06 129 13.2 106 28.8 148 11.1 109 3.45 122 3.97 113 2.04 70 23.1 171 34.1 167 20.7 165
Modified CLG [34]153.7 11.6 139 20.5 176 9.14 180 12.6 150 25.4 141 10.3 121 27.4 186 34.4 193 23.8 191 21.8 183 42.7 191 16.7 179 6.18 136 7.06 141 6.57 141 14.9 124 33.0 181 13.4 130 2.45 88 3.80 108 3.81 128 22.0 164 36.6 177 16.8 140
Black & Anandan [4]155.3 10.5 130 18.0 143 8.14 132 21.4 185 32.8 186 16.1 181 26.1 184 32.3 186 21.8 182 20.8 179 38.9 168 16.1 178 6.29 140 7.41 150 5.62 123 17.1 135 31.2 173 13.7 131 4.06 142 5.11 144 2.37 88 23.1 171 34.1 167 15.7 129
2bit-BM-tele [96]156.7 10.3 126 20.1 173 7.40 116 11.5 137 26.7 157 7.57 102 20.6 155 32.0 181 11.4 153 17.9 161 40.3 176 12.3 134 6.29 140 6.80 129 6.93 145 21.0 189 32.0 176 18.0 149 7.61 157 6.57 156 11.1 191 27.5 185 39.4 185 29.2 187
GroupFlow [9]157.0 11.5 137 21.2 183 8.71 175 20.5 177 33.0 187 15.7 178 23.6 178 31.6 174 20.1 175 16.2 110 34.5 124 11.3 127 8.86 155 9.84 193 6.50 140 18.2 145 30.3 163 17.4 147 3.82 135 5.05 142 6.55 147 21.1 159 28.8 139 22.4 178
H+S_RVC [176]158.8 16.6 195 23.7 193 11.9 192 19.0 175 30.6 175 15.5 177 24.8 182 30.2 160 23.4 187 29.3 194 36.5 152 28.2 195 6.53 147 6.24 104 9.34 156 25.9 195 38.4 197 27.0 196 1.69 26 2.81 13 1.42 32 32.3 189 41.4 190 30.3 188
BlockOverlap [61]160.6 10.3 126 19.1 159 7.74 124 15.4 166 25.3 139 13.0 169 24.3 179 31.9 178 21.0 179 19.5 175 43.8 196 13.1 137 9.14 156 7.60 151 13.9 158 19.0 148 29.0 152 15.7 140 11.0 161 8.77 161 24.8 199 23.0 170 31.3 148 25.9 183
Heeger++ [102]160.9 11.7 142 18.3 145 9.04 178 23.3 191 37.0 198 17.4 184 21.0 159 29.1 148 11.1 151 27.0 192 40.5 177 24.4 191 5.69 120 6.33 110 5.80 124 25.9 195 37.5 195 26.3 195 2.48 91 3.88 109 2.20 77 37.6 195 46.0 196 41.6 198
HCIC-L [97]161.9 14.6 188 21.1 181 9.67 183 42.7 199 36.7 197 46.6 199 21.8 171 30.5 162 17.9 173 21.1 182 35.1 133 18.6 185 6.42 145 6.58 123 7.35 150 17.8 141 28.6 147 16.6 143 12.8 163 14.3 163 15.3 194 16.8 129 25.7 127 12.7 107
TI-DOFE [24]163.2 14.6 188 21.1 181 11.7 191 22.4 190 31.6 179 19.6 189 28.6 191 31.2 169 26.3 195 26.3 191 36.0 144 25.1 192 6.43 146 7.34 148 6.67 144 19.1 150 33.8 184 18.9 152 2.88 107 3.15 52 2.82 100 25.7 181 36.6 177 22.3 177
Horn & Schunck [3]165.5 11.8 143 19.3 160 8.85 177 20.1 176 33.5 189 15.3 176 25.5 183 31.2 169 24.0 192 26.1 190 38.6 166 23.5 189 6.12 134 6.99 136 6.34 139 19.9 186 33.9 185 19.6 188 3.95 141 4.28 122 2.46 91 25.3 180 37.5 183 22.0 176
FFV1MT [104]174.5 13.9 187 23.4 192 10.8 188 20.9 180 34.5 194 16.0 180 21.8 171 29.5 151 13.8 162 31.0 197 41.7 185 29.4 196 9.97 160 6.78 128 17.9 196 23.8 192 35.3 191 25.0 194 2.99 112 4.24 120 3.57 122 37.6 195 46.0 196 41.6 198
SILK [80]175.5 13.2 184 22.4 187 10.2 186 20.5 177 32.2 185 17.7 185 29.0 192 34.1 191 23.4 187 22.0 184 40.8 180 17.3 182 6.28 138 7.17 144 7.12 149 21.7 190 35.8 193 19.6 188 5.44 151 3.45 88 10.8 190 29.3 187 40.6 189 26.7 185
PGAM+LK [55]175.8 14.9 190 22.8 189 14.1 196 25.5 192 31.3 177 26.6 194 21.9 173 26.4 128 22.2 183 26.0 189 39.1 170 24.0 190 9.61 158 6.49 121 14.1 159 24.3 193 35.0 189 23.0 192 6.19 154 6.24 155 7.26 151 34.3 193 40.4 187 40.8 197
SLK [47]176.2 17.2 197 24.0 194 18.2 197 21.3 183 30.4 174 20.1 190 27.9 188 31.9 178 23.3 186 31.4 198 39.9 173 30.0 198 6.60 148 7.04 140 8.37 153 22.8 191 36.4 194 21.6 191 3.90 140 3.75 106 5.02 138 33.3 190 41.7 191 35.2 192
Adaptive flow [45]176.4 13.2 184 20.2 174 9.78 184 27.3 194 31.9 182 25.4 193 28.3 190 31.6 174 30.5 198 19.7 177 37.6 160 15.3 176 11.2 196 12.6 196 8.93 155 17.6 138 29.8 158 15.8 141 13.1 164 11.0 162 18.3 195 26.4 183 36.8 181 22.7 179
AVG_FLOW_ROB [137]183.9 32.4 199 34.1 199 37.7 199 35.1 198 33.7 190 37.0 198 20.7 157 24.1 108 19.4 174 34.1 199 35.1 133 34.8 199 39.6 198 37.0 198 44.9 198 40.6 199 42.2 198 38.5 199 11.3 162 15.3 164 7.36 152 46.5 199 52.3 199 38.9 194
FOLKI [16]185.8 16.2 193 25.9 197 12.7 194 32.5 196 35.6 196 34.7 196 29.4 195 35.1 195 26.9 196 29.1 193 41.0 182 27.9 194 9.58 157 8.90 157 13.5 157 25.7 194 38.3 196 24.5 193 7.71 158 5.13 146 14.5 193 36.5 194 44.4 194 36.1 193
Pyramid LK [2]188.6 17.0 196 20.4 175 19.4 198 31.7 195 32.1 184 32.5 195 32.9 197 34.8 194 29.9 197 29.4 195 35.3 138 29.9 197 31.7 197 35.5 197 29.8 197 29.9 197 32.3 178 28.0 197 9.01 159 7.93 160 18.9 196 39.9 197 45.4 195 39.0 195
Periodicity [79]193.9 18.0 198 30.5 198 12.3 193 34.0 197 41.4 199 35.6 197 36.5 199 36.5 197 35.2 199 29.7 196 46.6 199 26.8 193 51.8 199 56.5 199 45.5 199 36.7 198 42.4 199 37.1 198 5.99 153 6.16 154 19.3 197 40.1 198 51.1 198 40.4 196
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.