Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R10.0
interpolation
error		 avg. Mequon
(Hidden texture)
im0   GT   im1 		Schefflera
(Hidden texture)
im0   GT   im1 		Urban
(Synthetic)
im0   GT   im1 		Teddy
(Stereo)
im0   GT   im1 		Backyard
(High-speed camera)
im0   GT   im1 		Basketball
(High-speed camera)
im0   GT   im1 		Dumptruck
(High-speed camera)
im0   GT   im1 		Evergreen
(High-speed camera)
im0   GT   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
SoftsplatAug [190]3.9 0.55 1 1.38 1 0.01 7 0.89 2 2.19 2 0.06 5 0.27 2 0.98 6 0.06 1 1.50 3 3.04 3 0.32 2 8.10 2 13.4 2 0.69 17 2.17 4 8.99 4 0.02 1 3.03 5 16.8 4 0.05 7 4.81 3 12.2 3 0.10 6
EAFI [186]9.2 0.71 11 1.92 8 0.00 1 0.81 1 1.85 1 0.04 1 0.23 1 0.67 1 0.06 1 1.46 2 2.72 1 0.37 10 11.4 26 18.9 26 0.70 19 3.29 22 13.6 22 0.02 1 3.39 15 18.9 16 0.03 1 6.61 15 16.7 16 0.09 2
SoftSplat [169]9.4 0.60 5 1.65 3 0.00 1 1.31 5 3.46 7 0.15 56 0.28 3 0.82 3 0.07 3 1.42 1 2.96 2 0.38 12 9.15 17 15.1 17 0.63 5 2.47 7 10.2 6 0.03 7 3.25 14 18.1 15 0.05 7 4.83 4 12.2 3 0.14 23
FGME [158]15.2 0.61 7 1.77 6 0.01 7 2.07 29 4.59 13 0.33 130 0.43 7 1.03 7 0.13 23 1.74 5 3.35 5 0.49 85 7.62 1 12.6 1 0.66 9 2.09 3 8.67 3 0.02 1 2.52 1 14.0 1 0.03 1 4.84 5 12.3 5 0.11 11
IFRNet [193]15.3 0.56 3 1.41 2 0.01 7 1.18 4 2.92 4 0.23 95 0.31 4 0.75 2 0.07 3 1.56 4 3.24 4 0.58 128 8.74 7 14.4 6 0.72 23 2.74 11 11.3 11 0.02 1 3.14 8 17.5 8 0.04 3 5.92 9 15.0 9 0.11 11
BMBC [171]15.7 0.77 17 1.96 9 0.01 7 1.57 10 4.13 11 0.10 34 0.89 19 2.31 30 0.12 15 2.14 10 4.27 9 0.41 31 8.96 12 14.8 12 0.86 34 2.45 6 10.2 6 0.04 16 3.22 12 17.8 12 0.06 20 5.33 6 13.5 6 0.16 32
SepConv++ [185]16.9 0.77 17 2.72 22 0.01 7 1.49 9 4.07 10 0.07 12 1.09 30 1.23 12 0.21 99 2.77 16 5.92 24 0.56 119 8.13 3 13.4 2 0.55 1 1.78 2 7.39 2 0.02 1 2.88 3 16.1 3 0.05 7 4.21 2 10.7 2 0.08 1
DistillNet [184]17.2 0.59 4 1.71 4 0.01 7 1.03 3 2.63 3 0.11 44 0.33 5 0.83 4 0.08 5 1.91 7 3.87 7 0.47 73 9.21 18 15.2 18 0.75 28 3.36 24 13.9 24 0.04 16 3.76 17 20.7 20 0.06 20 6.75 17 17.1 17 0.15 27
EDSC [173]21.2 0.78 20 2.49 17 0.01 7 1.77 12 4.62 15 0.27 108 0.91 21 1.46 17 0.16 45 2.64 15 5.70 22 0.57 123 8.58 5 14.1 5 0.66 9 2.87 12 11.9 12 0.03 7 3.00 4 16.8 4 0.05 7 6.23 10 15.8 10 0.09 2
STAR-Net [164]22.9 0.60 5 1.73 5 0.00 1 2.34 53 5.83 36 0.21 85 1.04 26 1.08 10 0.18 67 2.40 13 4.54 11 0.49 85 8.24 4 13.6 4 0.67 14 3.13 20 13.0 20 0.04 16 3.79 18 17.8 12 0.06 20 6.45 12 16.2 11 0.09 2
AdaCoF [165]25.2 0.80 22 2.69 21 0.01 7 1.72 11 4.46 12 0.18 68 1.04 26 1.38 15 0.19 81 3.46 57 6.23 26 0.64 143 10.4 24 17.2 24 0.67 14 2.41 5 10.0 5 0.02 1 3.17 9 17.7 11 0.04 3 5.44 7 13.8 7 0.10 6
IDIAL [192]25.2 0.68 8 2.03 11 0.01 7 1.87 16 4.85 20 0.25 100 0.70 8 1.06 9 0.11 9 2.52 14 4.81 13 0.48 78 8.73 6 14.4 6 0.72 23 3.12 19 12.9 18 0.03 7 3.94 23 19.1 17 0.14 144 6.58 14 16.5 13 0.14 23
CyclicGen [149]26.7 0.55 1 1.82 7 0.01 7 1.48 8 3.28 5 0.45 164 0.94 22 2.65 32 0.17 55 3.61 69 6.73 28 1.04 182 9.11 16 14.9 13 0.60 3 1.58 1 6.55 1 0.03 7 2.59 2 14.4 2 0.04 3 3.82 1 9.70 1 0.11 11
FRUCnet [153]28.6 0.89 27 2.84 26 0.01 7 1.94 21 4.76 17 0.36 135 0.96 24 1.45 16 0.20 90 2.99 23 5.85 23 0.63 139 9.22 19 15.2 18 0.57 2 2.70 10 11.2 10 0.03 7 3.18 11 17.5 8 0.06 20 6.56 13 16.6 15 0.10 6
MV_VFI [183]30.8 0.75 14 2.61 18 0.01 7 1.92 18 4.77 18 0.45 164 0.83 16 1.58 21 0.17 55 2.83 20 5.63 21 0.80 166 9.05 13 14.9 13 0.65 7 3.09 16 12.8 16 0.05 25 3.86 20 21.2 24 0.05 7 7.14 22 18.0 22 0.12 16
TC-GAN [166]31.0 0.76 16 2.64 19 0.01 7 1.94 21 4.83 19 0.45 164 0.83 16 1.60 23 0.17 55 2.81 17 5.56 19 0.83 171 9.05 13 14.9 13 0.66 9 3.09 16 12.8 16 0.04 16 3.86 20 21.2 24 0.05 7 7.16 24 18.1 24 0.12 16
DSepConv [162]31.1 0.88 26 3.15 29 0.01 7 2.05 27 4.93 25 0.45 164 0.95 23 1.51 19 0.14 28 3.79 100 6.79 31 0.56 119 8.79 8 14.5 8 0.65 7 2.96 13 12.3 13 0.04 16 3.04 6 17.0 6 0.06 20 6.95 20 17.6 20 0.11 11
ProBoost-Net [191]31.1 0.72 13 2.33 16 0.01 7 2.94 99 6.49 58 0.47 171 0.75 11 1.32 13 0.09 6 2.30 12 4.74 12 0.57 123 10.3 23 17.0 23 0.74 26 3.23 21 13.4 21 0.04 16 3.22 12 18.0 14 0.05 7 6.89 18 17.4 18 0.10 6
DAIN [152]31.2 0.78 20 2.72 22 0.01 7 1.98 23 4.89 23 0.44 161 0.81 15 1.50 18 0.16 45 2.82 19 5.58 20 0.83 171 9.07 15 15.0 16 0.66 9 3.06 15 12.7 15 0.05 25 3.86 20 21.2 24 0.05 7 7.14 22 18.0 22 0.12 16
GDCN [172]33.0 0.77 17 2.80 25 0.01 7 2.99 108 6.52 60 0.24 97 0.80 13 1.35 14 0.13 23 3.99 126 5.28 16 0.67 148 8.91 11 14.7 10 0.64 6 3.10 18 12.9 18 0.05 25 3.17 9 17.5 8 0.05 7 6.43 11 16.3 12 0.09 2
STSR [170]35.5 0.87 25 2.75 24 0.01 7 1.35 6 3.28 5 0.30 120 0.80 13 1.55 20 0.22 107 2.03 9 4.43 10 0.72 157 12.6 29 20.8 29 0.72 23 3.93 31 16.2 30 0.06 32 4.13 28 22.9 32 0.07 40 7.92 32 20.0 32 0.11 11
MAF-net [163]35.8 0.69 10 2.29 15 0.01 7 2.57 73 5.86 37 0.47 171 0.85 18 1.64 24 0.16 45 2.81 17 5.13 15 0.65 144 12.0 28 19.7 28 0.77 30 3.68 28 15.3 28 0.05 25 3.46 16 19.3 19 0.05 7 7.40 26 18.7 27 0.13 22
PMMST [112]36.8 1.35 43 4.72 45 0.01 7 2.31 49 6.03 42 0.07 12 1.11 31 3.99 38 0.12 15 3.07 25 6.79 31 0.40 22 13.6 39 22.1 36 1.00 48 4.53 38 18.6 38 0.11 41 4.33 37 24.1 43 0.07 40 8.94 62 22.6 61 0.19 39
FeFlow [167]36.8 0.75 14 2.27 14 0.01 7 2.35 54 5.57 32 0.49 180 0.78 12 1.22 11 0.11 9 2.92 21 5.53 18 0.84 173 8.90 10 14.7 10 0.70 19 3.32 23 13.7 23 0.03 7 3.96 24 19.2 18 0.14 144 6.92 19 17.4 18 0.14 23
CtxSyn [134]37.1 0.83 23 2.64 19 0.01 7 1.46 7 3.91 8 0.12 48 0.89 19 1.58 21 0.21 99 1.91 7 4.91 14 0.47 73 13.3 34 21.6 34 0.88 35 4.13 33 16.8 33 0.05 25 5.12 167 24.8 69 0.06 20 7.83 31 19.5 31 0.17 34
MEMC-Net+ [160]38.7 0.71 11 2.21 13 0.01 7 2.01 26 4.85 20 0.48 174 1.07 28 1.64 24 0.22 107 2.96 22 5.29 17 0.82 170 10.5 25 17.3 25 0.71 21 3.40 25 14.1 25 0.05 25 4.01 25 21.0 22 0.07 40 7.41 27 18.7 27 0.14 23
SuperSlomo [130]40.0 0.91 29 2.94 27 0.01 7 2.72 83 6.28 49 0.48 174 0.71 10 1.99 28 0.12 15 3.19 30 6.15 25 0.81 168 12.7 30 20.8 29 0.74 26 3.92 30 16.2 30 0.04 16 4.20 29 22.7 31 0.05 7 7.68 30 19.4 30 0.15 27
ADC [161]40.1 0.92 30 3.15 29 0.02 101 1.92 18 4.61 14 0.32 125 1.31 64 1.92 26 0.18 67 4.07 133 7.05 39 0.69 151 9.99 22 16.4 22 0.61 4 2.99 14 12.4 14 0.03 7 3.11 7 17.4 7 0.06 20 7.06 21 17.9 21 0.10 6
MDP-Flow2 [68]40.8 1.29 36 4.46 39 0.01 7 2.18 34 6.04 43 0.06 5 1.11 31 4.13 43 0.14 28 3.08 26 6.86 34 0.36 7 13.5 35 22.1 36 1.01 60 4.96 71 20.4 73 0.18 75 4.31 35 24.0 41 0.07 40 8.94 62 22.6 61 0.20 58
DAI [168]41.8 0.85 24 2.04 12 0.20 198 2.39 64 5.22 28 0.75 193 0.39 6 1.05 8 0.11 9 1.85 6 3.73 6 1.39 191 11.6 27 19.1 27 0.71 21 3.61 26 14.9 26 0.03 7 3.83 19 21.2 24 0.04 3 7.36 25 18.6 26 0.15 27
OFRI [154]42.8 0.68 8 1.98 10 0.02 101 2.09 30 4.70 16 0.44 161 0.70 8 0.86 5 0.17 55 2.16 11 4.06 8 0.77 163 9.25 20 15.3 20 0.66 9 3.64 27 14.9 26 0.03 7 5.14 169 21.0 22 0.08 68 7.41 27 18.2 25 0.16 32
CoT-AMFlow [174]44.8 1.32 39 4.67 43 0.01 7 2.20 37 6.12 46 0.05 2 1.15 38 4.42 50 0.15 37 3.10 27 6.95 36 0.36 7 13.6 39 22.2 41 1.02 75 4.99 80 20.5 79 0.20 84 4.36 44 24.2 46 0.06 20 8.96 69 22.7 70 0.20 58
MPRN [151]49.3 1.02 32 3.42 32 0.01 7 2.81 88 5.90 39 0.24 97 1.40 89 5.46 125 0.14 28 3.69 81 7.51 56 0.61 134 12.7 30 20.8 29 0.78 31 3.89 29 16.1 29 0.07 34 4.37 46 23.6 34 0.07 40 7.54 29 19.1 29 0.12 16
NN-field [71]52.8 1.45 61 5.41 78 0.01 7 1.87 16 5.01 27 0.06 5 1.51 115 3.94 36 0.16 45 3.78 98 8.92 125 0.41 31 13.6 39 22.2 41 1.00 48 5.05 88 20.7 87 0.20 84 4.27 30 23.7 35 0.07 40 8.85 46 22.4 45 0.19 39
NNF-Local [75]54.0 1.41 50 5.16 63 0.01 7 1.85 14 5.00 26 0.07 12 1.12 33 4.05 39 0.14 28 3.68 80 8.61 107 0.42 39 13.6 39 22.3 44 1.00 48 5.21 113 21.4 116 0.24 109 4.35 39 24.1 43 0.11 116 8.85 46 22.4 45 0.19 39
TOF-M [150]56.0 1.06 33 3.25 31 0.02 101 2.86 94 6.62 67 0.50 181 1.17 40 2.25 29 0.21 99 3.42 52 6.74 29 0.59 131 13.0 33 21.2 33 0.84 33 4.19 34 17.3 34 0.08 35 4.61 106 22.9 32 0.06 20 8.43 35 21.0 34 0.15 27
DeepFlow [85]57.8 1.35 43 4.67 43 0.00 1 3.01 110 8.09 106 0.21 85 1.26 51 5.00 79 0.12 15 3.97 124 8.00 76 0.44 55 13.7 47 22.4 51 1.03 87 4.46 36 18.3 36 0.08 35 4.40 49 24.5 57 0.06 20 8.74 42 22.1 41 0.21 98
DeepFlow2 [106]60.0 1.40 49 4.87 49 0.01 7 3.01 110 8.13 108 0.20 79 1.25 50 5.01 83 0.11 9 3.83 109 8.21 88 0.43 48 13.7 47 22.4 51 1.03 87 4.49 37 18.5 37 0.08 35 4.49 69 24.8 69 0.06 20 8.87 49 22.5 52 0.21 98
MS-PFT [159]60.1 0.89 27 3.07 28 0.01 7 2.25 43 5.71 33 0.32 125 1.26 51 1.95 27 0.31 152 4.49 155 8.39 95 0.91 179 9.43 21 15.5 21 0.75 28 2.64 9 10.9 9 0.04 16 4.98 158 21.5 28 0.21 175 6.65 16 16.5 13 0.15 27
SepConv-v1 [125]61.4 0.93 31 3.75 33 0.02 101 2.74 85 6.52 60 0.46 169 1.13 34 2.38 31 0.42 165 3.64 77 7.10 42 0.94 180 13.6 39 22.1 36 0.82 32 4.01 32 16.5 32 0.05 25 4.02 26 22.3 29 0.12 133 8.05 33 20.3 33 0.12 16
DF-Auto [113]61.6 1.26 34 3.92 34 0.00 1 3.13 118 7.98 101 0.29 115 1.14 36 4.08 41 0.16 45 3.57 63 7.48 54 0.46 67 13.5 35 22.0 35 1.01 60 4.66 39 19.2 40 0.15 56 4.49 69 24.8 69 0.09 88 9.09 90 23.0 90 0.21 98
FLAVR [188]61.8 1.62 123 4.22 35 0.01 7 2.23 41 3.98 9 0.20 79 1.23 48 2.89 33 0.21 99 12.2 197 17.1 196 1.42 192 8.82 9 14.6 9 0.67 14 2.53 8 10.5 8 0.04 16 4.66 119 20.7 20 0.19 169 5.78 8 14.3 8 0.18 35
IROF++ [58]62.7 1.54 92 5.77 106 0.01 7 2.35 54 6.39 51 0.10 34 1.50 112 5.04 85 0.25 128 3.10 27 6.75 30 0.39 15 13.7 47 22.4 51 1.16 133 4.66 39 19.2 40 0.11 41 4.55 92 25.1 89 0.10 102 8.84 45 22.4 45 0.19 39
PH-Flow [99]62.9 1.54 92 5.76 104 0.01 7 1.93 20 5.29 29 0.08 21 1.17 40 4.41 49 0.17 55 3.05 24 6.71 27 0.39 15 13.6 39 22.3 44 1.01 60 5.35 134 21.9 137 0.34 158 4.36 44 24.3 50 0.10 102 8.92 60 22.6 61 0.22 137
NNF-EAC [101]64.4 1.48 66 4.99 55 0.03 169 2.49 69 6.76 75 0.08 21 1.56 122 4.39 48 0.24 121 3.28 34 7.08 40 0.39 15 13.7 47 22.3 44 1.01 60 4.66 39 19.1 39 0.12 45 4.41 53 24.5 57 0.11 116 9.02 76 22.8 77 0.20 58
Layers++ [37]66.3 1.44 59 5.17 64 0.01 7 1.83 13 4.87 22 0.05 2 1.32 67 4.86 68 0.22 107 3.34 41 7.36 48 0.43 48 13.8 63 22.6 80 1.13 126 5.37 141 22.0 141 0.24 109 4.39 48 24.3 50 0.05 7 9.00 73 22.7 70 0.22 137
GMFlow_RVC [196]66.7 1.69 147 7.05 162 0.01 7 2.20 37 6.24 47 0.06 5 1.14 36 4.29 45 0.12 15 3.43 55 8.12 83 0.39 15 13.9 89 22.6 80 1.03 87 5.16 104 21.2 109 0.14 53 4.44 58 24.7 65 0.07 40 9.05 82 22.9 82 0.21 98
nLayers [57]67.2 1.51 77 5.46 81 0.01 7 2.17 33 5.91 40 0.08 21 1.24 49 3.88 35 0.18 67 3.47 58 7.71 67 0.40 22 13.9 89 22.7 106 1.18 141 5.25 115 21.6 122 0.31 139 4.35 39 23.8 36 0.09 88 8.99 72 22.7 70 0.19 39
Local-TV-L1 [65]68.0 1.34 41 4.39 37 0.02 101 4.19 161 9.42 148 0.37 141 1.34 69 4.34 47 0.15 37 3.61 69 7.78 69 0.44 55 13.8 63 22.5 61 1.04 94 4.71 45 19.5 48 0.16 65 4.40 49 24.5 57 0.07 40 8.70 40 22.0 38 0.20 58
Brox et al. [5]68.5 1.43 56 4.82 47 0.01 7 2.95 100 7.80 96 0.18 68 1.40 89 5.17 98 0.16 45 3.73 89 7.70 66 0.45 60 13.7 47 22.4 51 1.00 48 5.04 86 20.6 84 0.27 122 4.52 75 25.1 89 0.09 88 8.87 49 22.4 45 0.19 39
ALD-Flow [66]69.5 1.53 89 5.62 91 0.01 7 2.86 94 7.94 98 0.16 57 1.29 56 5.15 95 0.12 15 3.34 41 7.68 64 0.38 12 14.0 129 22.8 127 1.15 131 4.71 45 19.2 40 0.11 41 4.41 53 24.4 54 0.06 20 9.30 125 23.5 126 0.20 58
LME [70]71.0 1.39 47 5.10 59 0.01 7 2.49 69 6.95 80 0.10 34 1.35 75 5.64 133 0.15 37 3.29 36 7.55 58 0.39 15 14.1 156 23.0 160 1.26 193 5.13 101 21.1 105 0.19 81 4.37 46 24.2 46 0.06 20 8.89 56 22.5 52 0.19 39
CBF [12]72.7 1.28 35 4.40 38 0.01 7 3.24 126 8.20 113 0.25 100 1.59 129 4.63 54 0.18 67 3.60 68 7.61 61 0.49 85 13.8 63 22.5 61 0.99 43 4.89 60 20.2 63 0.18 75 4.56 94 25.3 107 0.07 40 9.21 109 23.3 111 0.18 35
JOF [136]72.8 1.58 113 5.80 109 0.01 7 2.18 34 5.88 38 0.10 34 1.28 54 4.68 56 0.19 81 3.37 48 7.21 45 0.42 39 13.9 89 22.7 106 1.21 156 5.35 134 21.9 137 0.20 84 4.33 37 24.0 41 0.07 40 9.18 104 23.2 104 0.20 58
Aniso. Huber-L1 [22]72.9 1.43 56 5.00 56 0.01 7 4.12 157 9.46 152 0.36 135 1.60 132 4.77 59 0.17 55 3.69 81 7.99 74 0.43 48 13.7 47 22.3 44 1.00 48 4.90 63 20.1 58 0.12 45 4.62 109 25.2 97 0.07 40 8.95 67 22.6 61 0.20 58
WLIF-Flow [91]72.9 1.44 59 5.19 66 0.01 7 2.52 72 6.81 77 0.16 57 1.38 82 4.67 55 0.20 90 3.21 31 6.98 37 0.42 39 13.7 47 22.4 51 1.07 108 5.37 141 22.1 147 0.28 128 4.43 56 24.4 54 0.08 68 9.09 90 23.0 90 0.21 98
ComponentFusion [94]73.0 1.54 92 6.05 126 0.01 7 2.33 52 6.57 64 0.07 12 1.31 64 4.82 63 0.16 45 3.35 45 7.66 63 0.37 10 13.9 89 22.6 80 1.13 126 4.93 65 20.3 67 0.20 84 4.61 106 25.7 128 0.13 140 9.06 83 22.9 82 0.20 58
RAFT-it+_RVC [198]73.9 1.63 127 6.74 156 0.01 7 2.14 31 6.06 45 0.06 5 1.18 42 4.75 57 0.11 9 3.65 78 8.80 119 0.41 31 13.9 89 22.6 80 1.02 75 5.56 163 21.7 128 0.62 198 4.35 39 24.2 46 0.08 68 8.71 41 22.1 41 0.21 98
HCFN [157]75.1 1.51 77 5.76 104 0.01 7 2.65 77 7.50 86 0.11 44 1.34 69 5.07 88 0.18 67 3.35 45 7.86 71 0.32 2 13.7 47 22.3 44 1.04 94 5.13 101 20.3 67 0.34 158 4.58 98 25.3 107 0.11 116 9.08 86 23.0 90 0.20 58
TV-L1-MCT [64]75.7 1.70 149 6.35 142 0.02 101 2.90 96 7.98 101 0.17 62 1.39 86 5.19 102 0.20 90 3.32 40 7.10 42 0.45 60 13.9 89 22.6 80 1.17 139 4.67 42 19.3 44 0.15 56 4.44 58 24.4 54 0.08 68 8.67 38 22.0 38 0.19 39
VCN_RVC [178]76.6 1.77 158 7.53 172 0.02 101 2.31 49 6.52 60 0.08 21 1.49 109 6.27 156 0.16 45 3.70 85 9.04 132 0.41 31 13.8 63 22.6 80 1.01 60 4.96 71 20.3 67 0.12 45 4.53 80 25.1 89 0.07 40 8.79 43 22.3 43 0.19 39
COFM [59]77.2 1.49 72 5.57 86 0.01 7 2.37 57 6.48 57 0.11 44 1.30 59 4.84 66 0.23 115 3.29 36 7.33 47 0.40 22 13.8 63 22.5 61 1.02 75 5.52 157 22.7 163 0.39 175 4.04 27 22.5 30 0.11 116 9.33 129 23.6 131 0.20 58
CLG-TV [48]77.3 1.35 43 4.56 40 0.02 101 3.84 145 9.35 143 0.29 115 1.38 82 5.11 90 0.18 67 3.71 87 7.93 72 0.50 97 13.8 63 22.4 51 1.00 48 4.74 48 19.5 48 0.13 50 4.59 103 25.2 97 0.07 40 9.08 86 22.9 82 0.20 58
CombBMOF [111]78.1 1.59 115 5.46 81 0.02 101 2.30 48 6.40 52 0.10 34 1.39 86 4.83 65 0.21 99 3.90 118 8.60 105 0.46 67 13.8 63 22.5 61 1.01 60 4.92 64 20.1 58 0.11 41 5.35 180 25.9 135 0.10 102 8.89 56 22.4 45 0.19 39
MS_RAFT+_RVC [195]78.1 1.63 127 6.51 149 0.02 101 2.29 47 6.57 64 0.07 12 0.99 25 3.73 34 0.14 28 3.17 29 6.90 35 0.45 60 13.8 63 22.6 80 1.20 150 4.74 48 19.4 46 0.06 32 4.28 32 23.8 36 0.11 116 10.3 182 26.1 187 0.28 192
Sparse-NonSparse [56]79.6 1.54 92 5.67 97 0.02 101 2.38 61 6.47 56 0.12 48 1.42 96 5.13 92 0.17 55 3.42 52 7.36 48 0.42 39 13.8 63 22.5 61 1.18 141 5.29 123 21.7 128 0.23 101 4.43 56 24.5 57 0.10 102 9.11 94 23.0 90 0.20 58
TF+OM [98]80.0 1.41 50 5.19 66 0.01 7 2.38 61 6.62 67 0.12 48 1.42 96 5.51 127 0.15 37 3.87 113 8.66 112 0.49 85 13.9 89 22.6 80 1.05 100 4.96 71 20.3 67 0.16 65 4.54 86 25.3 107 0.10 102 9.12 96 23.0 90 0.21 98
ProbFlowFields [126]80.2 1.46 63 5.63 92 0.02 101 2.23 41 6.35 50 0.09 28 1.19 43 4.55 52 0.20 90 3.51 60 8.02 78 0.45 60 13.9 89 22.7 106 1.24 182 5.28 122 21.6 122 0.39 175 4.32 36 24.1 43 0.11 116 8.68 39 22.0 38 0.21 98
SegFlow [156]80.2 1.52 85 5.83 112 0.01 7 2.37 57 6.71 73 0.10 34 1.34 69 5.00 79 0.12 15 3.69 81 8.87 122 0.49 85 13.9 89 22.6 80 1.22 169 5.08 94 20.9 95 0.33 154 4.58 98 25.3 107 0.08 68 8.87 49 22.4 45 0.20 58
PGM-C [118]80.4 1.50 74 5.75 102 0.01 7 2.37 57 6.68 70 0.10 34 1.48 108 5.32 110 0.15 37 3.77 95 9.13 138 0.50 97 13.9 89 22.6 80 1.21 156 4.97 77 20.4 73 0.23 101 4.54 86 25.1 89 0.08 68 8.94 62 22.6 61 0.20 58
IROF-TV [53]80.7 1.51 77 5.64 93 0.02 101 2.60 74 6.84 78 0.16 57 1.34 69 5.38 118 0.18 67 3.29 36 7.49 55 0.42 39 14.0 129 22.8 127 1.21 156 5.05 88 20.8 91 0.20 84 4.52 75 25.2 97 0.07 40 8.82 44 22.3 43 0.21 98
FlowFields [108]80.7 1.52 85 5.99 121 0.02 101 2.31 49 6.55 63 0.09 28 1.30 59 4.97 76 0.20 90 3.76 93 9.03 130 0.40 22 13.9 89 22.7 106 1.16 133 5.16 104 21.3 111 0.28 128 4.40 49 24.5 57 0.07 40 8.88 52 22.5 52 0.21 98
HAST [107]80.8 1.48 66 5.42 79 0.01 7 2.14 31 5.79 34 0.06 5 1.52 117 5.24 104 0.23 115 3.27 33 7.14 44 0.33 4 14.0 129 22.8 127 0.99 43 5.52 157 22.7 163 0.31 139 4.35 39 24.3 50 0.07 40 9.68 158 24.4 158 0.21 98
CPM-Flow [114]81.0 1.50 74 5.73 101 0.01 7 2.37 57 6.69 71 0.10 34 1.38 82 5.06 87 0.12 15 4.02 132 9.68 152 0.51 103 13.9 89 22.6 80 1.21 156 4.83 53 19.9 52 0.15 56 4.63 112 25.6 122 0.08 68 8.88 52 22.5 52 0.22 137
SIOF [67]81.1 1.53 89 5.38 76 0.01 7 4.17 158 10.1 169 0.31 122 1.40 89 5.38 118 0.14 28 3.62 72 7.99 74 0.61 134 13.5 35 22.1 36 0.98 40 4.87 56 20.1 58 0.13 50 4.49 69 24.9 79 0.08 68 9.34 131 23.6 131 0.20 58
RAFT-TF_RVC [179]81.7 1.70 149 7.21 165 0.02 101 2.25 43 6.40 52 0.06 5 1.16 39 4.53 51 0.18 67 3.67 79 8.70 113 0.47 73 13.9 89 22.6 80 1.00 48 5.44 149 20.7 87 0.28 128 4.35 39 24.2 46 0.06 20 9.06 83 22.9 82 0.24 173
FMOF [92]82.5 1.67 144 5.98 119 0.03 169 2.22 39 6.04 43 0.08 21 1.56 122 5.22 103 0.28 144 3.81 106 8.34 92 0.49 85 13.8 63 22.5 61 1.01 60 5.01 83 20.5 79 0.15 56 4.30 34 23.9 39 0.07 40 9.21 109 23.3 111 0.20 58
ProFlow_ROB [142]83.2 1.48 66 5.67 97 0.01 7 2.74 85 7.77 95 0.14 53 1.36 77 4.82 63 0.15 37 3.58 65 8.56 102 0.35 5 14.0 129 22.8 127 1.22 169 4.69 44 19.3 44 0.09 38 4.75 132 25.9 135 0.08 68 9.34 131 23.6 131 0.21 98
Ramp [62]83.4 1.57 111 5.75 102 0.01 7 2.38 61 6.51 59 0.19 72 1.41 93 5.11 90 0.17 55 3.26 32 7.09 41 0.41 31 13.9 89 22.6 80 1.15 131 5.51 155 22.5 156 0.32 148 4.48 65 24.7 65 0.07 40 9.33 129 23.6 131 0.20 58
RAFT-it [194]84.0 1.65 136 6.90 160 0.02 101 2.05 27 5.79 34 0.05 2 1.08 29 4.23 44 0.10 7 3.56 62 8.52 99 0.39 15 13.8 63 22.5 61 1.03 87 5.47 151 21.3 111 0.34 158 4.29 33 23.9 39 0.07 40 10.7 191 27.0 192 0.24 173
PRAFlow_RVC [177]84.0 1.67 144 6.70 154 0.02 101 2.39 64 6.57 64 0.11 44 1.13 34 4.12 42 0.15 37 3.70 85 8.75 114 0.48 78 13.8 63 22.5 61 1.03 87 4.85 55 19.9 52 0.15 56 4.40 49 24.5 57 0.11 116 9.52 148 23.9 149 0.23 163
FlowFields+ [128]85.8 1.52 85 5.97 118 0.02 101 2.26 45 6.42 55 0.09 28 1.29 56 5.05 86 0.19 81 3.69 81 8.96 127 0.44 55 14.0 129 22.8 127 1.21 156 5.26 116 21.6 122 0.33 154 4.41 53 24.5 57 0.08 68 8.86 48 22.5 52 0.20 58
2DHMM-SAS [90]86.2 1.65 136 6.25 138 0.02 101 3.41 131 8.58 121 0.22 89 1.36 77 4.84 66 0.19 81 3.28 34 7.02 38 0.43 48 13.8 63 22.5 61 1.19 147 4.94 68 20.1 58 0.09 38 4.52 75 24.8 69 0.12 133 9.25 120 23.4 120 0.20 58
F-TV-L1 [15]86.8 1.54 92 5.24 70 0.02 101 4.11 156 9.73 163 0.32 125 1.50 112 5.44 122 0.23 115 3.76 93 8.03 79 0.47 73 13.5 35 22.1 36 0.94 36 4.71 45 19.4 46 0.17 70 4.61 106 25.3 107 0.13 140 8.92 60 22.6 61 0.19 39
Classic++ [32]86.9 1.46 63 5.27 71 0.01 7 3.38 130 8.81 131 0.25 100 1.47 107 5.14 94 0.17 55 3.93 123 8.15 85 0.46 67 13.8 63 22.6 80 1.00 48 5.16 104 21.2 109 0.25 117 4.59 103 25.2 97 0.08 68 9.17 102 23.2 104 0.20 58
MDP-Flow [26]87.2 1.35 43 4.97 54 0.02 101 2.22 39 6.25 48 0.09 28 1.20 44 4.07 40 0.14 28 3.89 116 8.34 92 0.48 78 13.8 63 22.5 61 1.24 182 5.74 174 23.6 179 0.50 193 4.63 112 25.6 122 0.11 116 8.97 70 22.7 70 0.19 39
BlockOverlap [61]87.2 1.34 41 4.33 36 0.02 101 4.04 154 9.04 136 0.48 174 1.36 77 4.31 46 0.32 153 3.43 55 6.81 33 0.71 155 14.0 129 22.8 127 1.04 94 4.89 60 20.0 56 0.22 95 4.44 58 24.7 65 0.11 116 8.64 37 21.8 36 0.20 58
Classic+NL [31]88.0 1.62 123 5.98 119 0.02 101 2.48 66 6.65 69 0.17 62 1.41 93 5.13 92 0.19 81 3.37 48 7.27 46 0.44 55 13.9 89 22.6 80 1.12 125 5.34 131 21.8 134 0.22 95 4.48 65 24.8 69 0.09 88 9.27 123 23.4 120 0.19 39
Second-order prior [8]88.7 1.39 47 4.88 50 0.02 101 3.85 147 9.45 151 0.27 108 1.83 151 5.99 148 0.26 133 3.83 109 8.56 102 0.49 85 13.6 39 22.3 44 1.01 60 4.82 52 19.9 52 0.18 75 4.67 120 25.6 122 0.06 20 9.03 78 22.8 77 0.20 58
OAR-Flow [123]89.3 1.56 107 5.61 90 0.01 7 2.99 108 8.09 106 0.22 89 1.29 56 4.89 70 0.10 7 3.29 36 7.60 60 0.38 12 14.0 129 22.8 127 1.23 175 5.11 99 21.0 98 0.29 133 4.78 137 26.1 143 0.09 88 9.19 105 23.2 104 0.20 58
LSM [39]90.0 1.64 132 6.31 141 0.01 7 2.48 66 6.79 76 0.12 48 1.51 115 5.55 129 0.17 55 3.59 67 7.98 73 0.41 31 13.9 89 22.6 80 1.19 147 5.36 137 21.9 137 0.25 117 4.47 62 24.7 65 0.10 102 9.23 115 23.3 111 0.20 58
AggregFlow [95]90.7 1.89 171 7.48 170 0.01 7 2.95 100 8.13 108 0.16 57 1.22 46 4.86 68 0.14 28 4.18 140 9.69 153 0.45 60 13.9 89 22.6 80 1.04 94 4.94 68 20.2 63 0.15 56 4.51 73 25.0 84 0.12 133 9.24 119 23.3 111 0.21 98
LDOF [28]90.8 1.45 61 4.81 46 0.02 101 3.10 115 7.33 83 0.56 189 1.58 127 5.39 121 0.22 107 3.92 122 8.47 97 0.63 139 13.8 63 22.5 61 1.02 75 4.68 43 19.2 40 0.13 50 4.48 65 25.0 84 0.10 102 9.01 74 22.8 77 0.22 137
DMF_ROB [135]91.6 1.54 92 5.65 94 0.01 7 3.31 129 8.76 128 0.28 113 2.11 167 6.42 161 0.44 167 4.01 130 8.89 124 0.46 67 13.7 47 22.4 51 1.20 150 4.87 56 20.1 58 0.22 95 4.54 86 24.8 69 0.07 40 8.90 58 22.5 52 0.20 58
ComplOF-FED-GPU [35]92.1 1.56 107 5.92 114 0.02 101 2.71 82 7.63 90 0.17 62 1.95 159 5.09 89 0.39 164 3.63 73 8.64 109 0.40 22 13.7 47 22.5 61 1.13 126 4.98 78 20.5 79 0.17 70 4.70 124 25.7 128 0.07 40 9.31 126 23.4 120 0.19 39
CRTflow [81]92.4 1.50 74 5.48 83 0.02 101 3.87 148 9.40 147 0.36 135 1.62 135 6.22 155 0.24 121 3.55 61 7.76 68 0.43 48 13.9 89 22.7 106 1.21 156 4.77 51 19.6 50 0.14 53 4.53 80 25.2 97 0.07 40 9.04 79 22.9 82 0.20 58
DPOF [18]93.0 1.64 132 6.52 151 0.04 188 1.98 23 5.37 30 0.07 12 1.83 151 4.75 57 0.34 156 3.75 92 8.80 119 0.48 78 13.7 47 22.3 44 1.01 60 5.16 104 21.0 98 0.14 53 4.67 120 25.3 107 0.06 20 9.31 126 23.5 126 0.22 137
S2F-IF [121]93.4 1.55 103 6.13 130 0.01 7 2.26 45 6.41 54 0.09 28 1.30 59 5.17 98 0.17 55 3.72 88 9.01 129 0.45 60 14.0 129 22.9 149 1.24 182 5.27 117 21.6 122 0.32 148 4.54 86 25.2 97 0.09 88 8.88 52 22.5 52 0.23 163
TC-Flow [46]93.9 1.51 77 5.70 100 0.01 7 2.97 103 8.31 116 0.21 85 1.46 104 5.35 113 0.11 9 3.63 73 8.10 81 0.58 128 14.0 129 22.8 127 1.21 156 5.10 96 21.0 98 0.29 133 4.53 80 25.0 84 0.07 40 9.19 105 23.3 111 0.21 98
OFLAF [78]94.9 1.48 66 5.49 85 0.01 7 2.00 25 5.50 31 0.07 12 1.30 59 4.97 76 0.15 37 3.34 41 7.40 51 0.40 22 14.0 129 22.8 127 1.21 156 5.56 163 22.8 167 0.41 178 4.83 144 26.3 152 0.17 164 9.73 163 24.5 164 0.20 58
UnDAF [187]95.4 1.65 136 6.82 159 0.02 101 2.70 79 7.50 86 0.07 12 1.65 139 7.12 176 0.18 67 4.54 159 11.8 180 0.44 55 13.7 47 22.4 51 1.00 48 5.07 91 20.8 91 0.22 95 4.50 72 24.9 79 0.09 88 9.21 109 23.3 111 0.20 58
p-harmonic [29]95.7 1.42 53 4.96 53 0.01 7 4.00 151 9.50 153 0.39 147 1.38 82 5.68 135 0.19 81 4.20 142 8.58 104 0.49 85 13.9 89 22.6 80 1.01 60 4.93 65 20.3 67 0.21 90 4.81 140 26.1 143 0.11 116 9.12 96 23.1 100 0.20 58
SVFilterOh [109]96.0 1.51 77 5.48 83 0.02 101 2.19 36 5.94 41 0.10 34 1.50 112 5.00 79 0.25 128 3.78 98 8.01 77 0.40 22 14.3 174 23.2 172 1.22 169 5.35 134 22.0 141 0.23 101 4.27 30 23.8 36 0.06 20 9.55 149 24.1 152 0.22 137
FC-2Layers-FF [74]97.0 1.56 107 5.94 116 0.02 101 1.86 15 4.90 24 0.08 21 1.39 86 5.29 108 0.20 90 3.34 41 7.46 53 0.40 22 13.9 89 22.8 127 1.20 150 5.56 163 22.9 168 0.37 171 4.53 80 24.9 79 0.11 116 9.35 134 23.6 131 0.22 137
EAI-Flow [147]97.8 1.65 136 5.96 117 0.03 169 2.84 91 7.64 92 0.25 100 1.56 122 5.73 139 0.19 81 3.82 107 8.93 126 0.35 5 13.9 89 22.6 80 1.18 141 4.87 56 20.0 56 0.22 95 4.75 132 26.0 138 0.14 144 8.63 36 21.8 36 0.20 58
Occlusion-TV-L1 [63]101.1 1.43 56 5.20 69 0.01 7 4.18 160 10.3 173 0.37 141 1.34 69 5.35 113 0.27 140 4.19 141 9.14 139 0.56 119 13.7 47 22.4 51 0.97 37 4.99 80 20.6 84 0.33 154 5.12 167 25.4 115 0.27 182 9.01 74 22.7 70 0.19 39
S2D-Matching [83]102.2 1.65 136 6.07 128 0.02 101 3.21 122 8.58 121 0.23 95 1.34 69 5.00 79 0.23 115 3.35 45 7.36 48 0.42 39 13.9 89 22.7 106 1.07 108 5.53 160 22.6 159 0.35 164 4.57 97 24.8 69 0.07 40 9.22 114 23.3 111 0.22 137
TC/T-Flow [77]102.3 1.69 147 6.24 136 0.02 101 2.98 105 8.17 111 0.19 72 1.27 53 4.78 60 0.13 23 3.58 65 8.26 89 0.36 7 14.1 156 23.0 160 1.23 175 5.03 85 20.6 84 0.12 45 4.85 147 26.3 152 0.16 160 9.40 140 23.8 144 0.19 39
HBM-GC [103]102.8 1.54 92 5.66 95 0.01 7 2.98 105 8.21 114 0.17 62 1.20 44 3.96 37 0.18 67 3.63 73 7.79 70 0.43 48 14.4 180 23.5 181 1.29 196 5.96 186 24.4 188 0.48 189 4.46 61 24.6 64 0.05 7 9.35 134 23.6 131 0.22 137
EpicFlow [100]103.3 1.51 77 5.82 111 0.01 7 2.90 96 8.08 104 0.18 68 1.43 99 5.25 105 0.16 45 3.88 115 9.42 146 0.54 113 13.9 89 22.7 106 1.21 156 5.13 101 21.1 105 0.31 139 4.71 126 25.8 132 0.14 144 9.13 98 23.1 100 0.21 98
RFlow [88]104.0 1.41 50 5.18 65 0.02 101 3.96 150 9.67 160 0.35 132 1.41 93 5.37 116 0.26 133 3.91 121 8.76 115 0.52 105 13.7 47 22.5 61 1.01 60 4.96 71 20.5 79 0.21 90 4.58 98 25.5 118 0.09 88 9.37 138 23.7 141 0.23 163
AGIF+OF [84]104.7 1.66 143 6.04 125 0.02 101 2.48 66 6.73 74 0.19 72 1.44 100 4.96 75 0.26 133 3.41 51 7.54 57 0.45 60 14.1 156 23.1 169 1.21 156 5.47 151 22.3 152 0.27 122 4.52 75 24.3 50 0.07 40 9.41 143 23.8 144 0.21 98
MLDP_OF [87]104.9 1.55 103 6.03 124 0.02 101 3.12 117 8.40 119 0.20 79 1.22 46 4.97 76 0.13 23 3.77 95 7.62 62 0.73 158 13.9 89 22.7 106 1.01 60 5.60 168 23.0 172 0.31 139 4.63 112 25.3 107 0.14 144 9.21 109 23.3 111 0.21 98
OFH [38]105.5 1.56 107 5.79 108 0.01 7 3.55 136 8.78 130 0.30 120 1.62 135 6.44 162 0.16 45 3.57 63 8.52 99 0.39 15 13.8 63 22.6 80 1.16 133 5.18 109 21.3 111 0.31 139 4.94 155 26.6 155 0.15 153 9.36 136 23.6 131 0.19 39
RNLOD-Flow [119]105.8 1.52 85 5.81 110 0.01 7 3.05 114 8.32 118 0.19 72 1.58 127 5.84 145 0.32 153 3.47 58 7.69 65 0.43 48 13.9 89 22.7 106 1.19 147 5.36 137 22.0 141 0.26 121 4.51 73 24.8 69 0.14 144 9.66 154 24.4 158 0.21 98
PMF [73]106.0 1.59 115 6.16 134 0.01 7 2.73 84 7.62 89 0.07 12 1.65 139 6.90 171 0.28 144 3.74 90 8.38 94 0.40 22 14.1 156 23.0 160 1.02 75 5.10 96 20.9 95 0.19 81 4.56 94 25.4 115 0.09 88 9.84 169 24.9 177 0.22 137
Ad-TV-NDC [36]107.2 1.63 127 4.88 50 0.03 169 5.06 184 10.3 173 0.36 135 1.45 102 5.55 129 0.20 90 4.53 158 9.15 140 0.57 123 14.1 156 22.9 149 0.99 43 4.74 48 19.6 50 0.16 65 4.80 139 25.8 132 0.06 20 9.02 76 22.8 77 0.19 39
Sparse Occlusion [54]108.8 1.51 77 5.58 87 0.02 101 3.51 135 9.43 150 0.19 72 1.37 81 4.95 74 0.18 67 3.80 103 8.33 90 0.49 85 13.9 89 22.7 106 1.20 150 5.58 166 22.9 168 0.37 171 4.73 129 25.8 132 0.07 40 9.38 139 23.7 141 0.20 58
TCOF [69]108.8 1.54 92 5.59 88 0.01 7 4.46 169 10.4 176 0.43 158 1.28 54 5.15 95 0.14 28 3.63 73 8.04 80 0.42 39 13.9 89 22.7 106 0.98 40 5.41 145 22.3 152 0.24 109 5.00 160 26.7 158 0.09 88 9.76 164 24.6 168 0.24 173
C-RAFT_RVC [181]109.1 2.24 186 9.02 185 0.02 101 2.91 98 8.15 110 0.18 68 1.54 120 5.96 147 0.28 144 4.11 137 9.64 151 0.48 78 13.8 63 22.5 61 0.99 43 5.29 123 21.7 128 0.21 90 4.60 105 25.4 115 0.06 20 9.19 105 23.2 104 0.22 137
CostFilter [40]110.8 1.77 158 7.36 168 0.01 7 2.66 78 7.51 88 0.08 21 1.82 150 7.88 187 0.29 149 4.00 128 9.50 149 0.31 1 14.2 170 23.1 169 1.07 108 4.98 78 20.4 73 0.17 70 4.62 109 25.6 122 0.08 68 9.65 152 24.4 158 0.21 98
HBpMotionGpu [43]111.4 1.64 132 5.67 97 0.02 101 5.07 185 11.0 188 0.48 174 1.33 68 4.89 70 0.22 107 4.40 148 9.95 160 0.52 105 13.8 63 22.6 80 1.17 139 5.30 126 21.4 116 0.29 133 4.48 65 24.9 79 0.06 20 9.23 115 23.2 104 0.21 98
Modified CLG [34]111.5 1.31 37 4.60 41 0.01 7 4.56 174 9.63 158 0.50 181 1.63 137 6.45 164 0.33 155 4.14 139 9.05 133 0.62 137 13.9 89 22.6 80 1.02 75 5.08 94 20.8 91 0.31 139 4.65 116 25.9 135 0.09 88 9.08 86 22.9 82 0.22 137
Adaptive [20]112.2 1.48 66 5.33 74 0.02 101 4.48 170 10.6 182 0.43 158 1.53 119 5.50 126 0.18 67 3.84 111 8.33 90 0.54 113 13.9 89 22.7 106 1.00 48 5.20 112 21.4 116 0.28 128 4.89 149 26.1 143 0.07 40 9.41 143 23.8 144 0.21 98
FF++_ROB [141]113.4 1.55 103 6.13 130 0.01 7 2.70 79 7.41 84 0.14 53 1.46 104 5.35 113 0.25 128 3.98 125 9.53 150 0.53 110 14.1 156 22.9 149 1.25 190 5.34 131 21.9 137 0.32 148 4.55 92 25.2 97 0.12 133 8.94 62 22.6 61 0.25 180
AdaConv-v1 [124]114.0 2.34 188 9.17 186 0.04 188 4.08 155 8.31 116 0.75 193 2.48 178 6.07 152 0.62 180 7.79 191 14.5 194 2.10 197 12.8 32 20.9 32 0.69 17 4.24 35 17.6 35 0.09 38 4.52 75 25.1 89 0.22 180 8.39 34 21.2 35 0.12 16
PWC-Net_RVC [143]114.0 1.82 164 7.81 175 0.02 101 3.01 110 8.61 124 0.12 48 1.46 104 6.05 150 0.19 81 3.79 100 9.29 145 0.41 31 14.1 156 23.1 169 1.24 182 5.30 126 21.3 111 0.20 84 4.54 86 25.0 84 0.10 102 8.98 71 22.7 70 0.23 163
TriFlow [93]114.9 1.65 136 6.58 152 0.01 7 3.78 144 9.53 155 0.29 115 1.45 102 5.99 148 0.18 67 4.07 133 9.25 143 0.49 85 14.0 129 22.9 149 1.18 141 5.34 131 21.4 116 0.15 56 4.64 115 25.2 97 0.08 68 9.40 140 23.6 131 0.21 98
FlowNetS+ft+v [110]115.4 1.48 66 5.14 62 0.02 101 4.36 165 9.68 162 0.78 195 1.57 125 5.37 116 0.26 133 3.90 118 8.47 97 0.81 168 13.9 89 22.7 106 1.23 175 4.83 53 19.9 52 0.24 109 4.70 124 26.1 143 0.12 133 9.09 90 23.0 90 0.21 98
Efficient-NL [60]115.6 1.53 89 5.60 89 0.01 7 2.98 105 7.94 98 0.16 57 2.05 161 5.45 124 0.56 176 3.82 107 8.12 83 0.42 39 13.8 63 22.5 61 1.18 141 5.69 172 23.2 174 0.32 148 4.75 132 26.1 143 0.11 116 9.94 179 24.8 174 0.22 137
MCPFlow_RVC [197]116.3 2.12 182 8.90 183 0.02 101 2.36 56 6.69 71 0.09 28 1.31 64 5.29 108 0.13 23 3.84 111 8.87 122 0.51 103 14.0 129 22.9 149 1.02 75 5.66 170 23.4 178 0.28 128 4.47 62 24.8 69 0.09 88 13.2 198 33.4 198 0.39 196
Bartels [41]116.8 1.59 115 6.24 136 0.03 169 3.20 121 8.92 134 0.31 122 1.40 89 5.17 98 0.25 128 4.09 135 9.05 133 0.86 176 14.1 156 22.9 149 0.97 37 5.43 148 22.2 150 0.25 117 4.47 62 24.8 69 0.10 102 9.15 100 23.1 100 0.20 58
EPPM w/o HM [86]117.8 1.68 146 7.02 161 0.02 101 2.84 91 8.08 104 0.10 34 2.13 170 7.82 186 0.36 158 3.87 113 9.12 136 0.49 85 13.9 89 22.7 106 1.04 94 5.27 117 21.6 122 0.17 70 4.56 94 25.2 97 0.15 153 9.34 131 23.6 131 0.22 137
PBOFVI [189]117.8 1.81 162 7.16 163 0.02 101 3.76 143 9.42 148 0.37 141 1.80 149 5.32 110 0.18 67 3.77 95 8.54 101 0.62 137 13.9 89 22.7 106 1.22 169 5.07 91 20.3 67 0.16 65 4.85 147 26.0 138 0.17 164 9.07 85 23.0 90 0.21 98
Filter Flow [19]118.1 1.54 92 5.28 72 0.01 7 4.52 173 9.97 168 0.35 132 1.61 134 5.53 128 0.20 90 4.55 160 8.61 107 0.46 67 14.3 174 23.2 172 1.08 113 5.10 96 21.0 98 0.21 90 4.76 136 26.1 143 0.11 116 9.65 152 24.3 157 0.20 58
Nguyen [33]118.8 1.55 103 5.02 57 0.00 1 5.69 191 10.8 184 0.48 174 1.63 137 6.70 168 0.28 144 5.35 177 10.5 167 0.77 163 13.8 63 22.5 61 1.01 60 4.99 80 20.7 87 0.18 75 5.44 182 28.2 176 0.21 175 9.08 86 22.9 82 0.20 58
FESL [72]118.9 1.63 127 5.93 115 0.02 101 2.50 71 6.86 79 0.14 53 1.49 109 5.44 122 0.26 133 3.80 103 8.16 86 0.50 97 14.1 156 22.9 149 1.21 156 5.60 168 22.9 168 0.40 177 4.58 98 25.0 84 0.08 68 9.50 145 24.0 151 0.22 137
Classic+CPF [82]119.2 1.65 136 6.18 135 0.02 101 2.63 76 7.07 82 0.17 62 1.44 100 5.38 118 0.23 115 3.40 50 7.45 52 0.42 39 14.3 174 23.3 176 1.21 156 5.68 171 23.2 174 0.31 139 4.71 126 25.3 107 0.10 102 9.77 165 24.6 168 0.22 137
Complementary OF [21]119.5 1.61 120 6.47 146 0.01 7 2.74 85 7.75 94 0.19 72 2.67 185 5.71 136 0.89 196 3.74 90 8.76 115 0.41 31 13.9 89 22.7 106 1.14 130 5.19 110 21.4 116 0.31 139 4.98 158 26.9 163 0.13 140 9.78 167 24.8 174 0.21 98
GraphCuts [14]119.7 1.90 172 6.51 149 0.02 101 2.96 102 7.63 90 0.22 89 3.79 194 5.16 97 0.64 182 4.49 155 9.24 142 0.55 116 13.9 89 22.7 106 0.99 43 5.04 86 20.8 91 0.21 90 4.53 80 25.2 97 0.15 153 9.88 174 24.9 177 0.21 98
2D-CLG [1]120.2 1.42 53 5.09 58 0.01 7 4.91 180 9.82 167 0.48 174 2.21 172 5.62 131 0.57 177 5.05 170 9.90 159 0.80 166 13.8 63 22.5 61 1.09 117 5.07 91 21.0 98 0.42 180 4.89 149 26.7 158 0.13 140 9.11 94 22.6 61 0.20 58
TVL1_RVC [175]120.2 1.54 92 4.90 52 0.01 7 5.65 190 11.1 189 0.46 169 1.54 120 5.71 136 0.36 158 4.83 167 9.25 143 0.70 154 14.0 129 22.8 127 1.03 87 5.05 88 20.9 95 0.23 101 4.92 152 26.8 161 0.19 169 9.04 79 22.9 82 0.19 39
Black & Anandan [4]120.5 1.63 127 5.12 60 0.01 7 5.17 187 10.5 179 0.41 151 2.30 175 6.36 158 0.47 171 5.20 174 9.84 158 0.49 85 14.0 129 22.9 149 1.02 75 4.88 59 20.2 63 0.18 75 5.10 166 27.0 164 0.08 68 9.23 115 23.1 100 0.21 98
SRR-TVOF-NL [89]120.8 1.79 160 6.72 155 0.02 101 3.21 122 8.72 127 0.29 115 1.42 96 5.34 112 0.20 90 4.29 143 9.00 128 0.53 110 13.9 89 22.8 127 1.20 150 5.24 114 21.5 121 0.22 95 4.68 122 25.1 89 0.07 40 9.93 178 25.0 179 0.22 137
IAOF [50]120.9 1.79 160 5.85 113 0.02 101 6.44 196 12.4 197 0.55 187 1.84 154 5.77 142 0.36 158 4.78 165 9.12 136 0.75 162 13.7 47 22.4 51 1.01 60 5.01 83 20.7 87 0.15 56 4.73 129 25.7 128 0.09 88 9.29 124 23.4 120 0.20 58
TV-L1-improved [17]121.6 1.42 53 5.19 66 0.01 7 4.41 167 10.4 176 0.40 148 2.10 164 5.27 107 0.50 173 3.89 116 8.46 96 0.52 105 14.0 129 22.8 127 1.00 48 5.33 130 22.0 141 0.25 117 4.96 157 27.5 172 0.23 181 9.26 121 23.4 120 0.21 98
Steered-L1 [116]122.2 1.33 40 4.83 48 0.02 101 2.85 93 7.86 97 0.32 125 2.08 163 5.18 101 0.64 182 4.36 145 8.60 105 1.06 183 14.1 156 23.0 160 0.97 37 5.12 100 21.1 105 0.34 158 4.69 123 26.1 143 0.12 133 9.50 145 24.1 152 0.22 137
LFNet_ROB [145]123.0 1.82 164 7.57 173 0.03 169 3.04 113 8.27 115 0.22 89 1.49 109 6.12 154 0.21 99 3.99 126 9.80 156 0.57 123 13.8 63 22.6 80 1.26 193 5.51 155 22.5 156 0.34 158 4.54 86 25.1 89 0.09 88 8.94 62 22.5 52 0.25 180
Fusion [6]124.4 1.46 63 5.40 77 0.02 101 2.70 79 6.97 81 0.17 62 1.30 59 4.55 52 0.29 149 4.32 144 8.77 117 0.46 67 14.3 174 23.5 181 1.02 75 5.93 185 24.4 188 0.47 186 4.83 144 26.7 158 0.12 133 10.4 186 26.1 187 0.22 137
3DFlow [133]126.0 1.71 152 6.28 140 0.02 101 2.62 75 7.42 85 0.20 79 1.91 158 4.91 73 0.25 128 3.61 69 8.10 81 0.55 116 13.9 89 22.7 106 1.02 75 6.30 195 25.3 196 0.47 186 5.26 176 27.2 169 0.15 153 9.71 160 24.5 164 0.21 98
ResPWCR_ROB [140]126.5 1.70 149 6.74 156 0.02 101 3.24 126 8.87 132 0.27 108 2.22 173 6.11 153 0.23 115 4.42 149 10.6 168 0.69 151 13.6 39 22.2 41 1.23 175 5.36 137 21.7 128 0.16 65 4.79 138 25.7 128 0.15 153 9.31 126 23.5 126 0.21 98
CNN-flow-warp+ref [115]127.9 1.31 37 4.62 42 0.02 101 3.65 142 9.05 137 0.47 171 2.07 162 6.56 167 0.43 166 5.51 179 9.78 155 1.12 186 13.9 89 22.7 106 1.23 175 4.96 71 20.5 79 0.35 164 4.90 151 27.1 167 0.18 168 9.04 79 22.8 77 0.21 98
BriefMatch [122]128.0 1.61 120 6.15 133 0.03 169 2.97 103 7.73 93 0.61 191 2.12 168 4.79 61 0.58 178 4.84 168 9.05 133 1.68 194 13.9 89 22.7 106 1.08 113 5.30 126 21.8 134 0.24 109 4.53 80 24.9 79 0.14 144 9.13 98 23.0 90 0.28 192
Rannacher [23]128.0 1.49 72 5.66 95 0.01 7 4.49 171 10.6 182 0.40 148 2.19 171 5.77 142 0.52 175 3.79 100 8.65 111 0.53 110 14.0 129 22.8 127 1.02 75 5.29 123 21.8 134 0.27 122 4.95 156 27.4 170 0.21 175 9.26 121 23.4 120 0.22 137
ContinualFlow_ROB [148]129.2 1.99 175 8.31 181 0.03 169 3.22 125 8.92 134 0.25 100 1.78 146 6.97 173 0.26 133 4.00 128 9.83 157 0.48 78 14.0 129 22.9 149 1.24 182 4.93 65 20.4 73 0.18 75 4.62 109 25.1 89 0.08 68 9.40 140 23.8 144 0.25 180
AugFNG_ROB [139]129.3 1.87 169 7.84 177 0.02 101 3.57 138 9.08 138 0.35 132 1.85 155 8.05 190 0.22 107 4.52 157 11.3 172 0.55 116 14.2 170 23.2 172 1.25 190 4.89 60 20.2 63 0.12 45 4.92 152 26.0 138 0.10 102 8.88 52 22.4 45 0.23 163
FlowNet2 [120]129.7 2.65 192 10.2 191 0.02 101 3.21 122 8.40 119 0.22 89 1.75 143 6.40 159 0.27 140 4.43 152 11.4 174 0.67 148 14.1 156 23.0 160 1.11 122 5.17 108 21.0 98 0.19 81 4.65 116 25.5 118 0.08 68 9.10 93 23.0 90 0.24 173
CompactFlow_ROB [155]132.2 2.02 177 8.69 182 0.03 169 3.10 115 8.65 126 0.21 85 1.77 145 7.43 180 0.24 121 4.62 163 11.4 174 0.58 128 13.9 89 22.6 80 1.06 104 5.36 137 22.0 141 0.24 109 4.83 144 26.2 151 0.08 68 9.20 108 23.2 104 0.24 173
SimpleFlow [49]133.0 1.60 119 6.00 122 0.01 7 3.50 134 8.63 125 0.32 125 2.53 179 6.06 151 0.79 187 3.42 52 7.56 59 0.48 78 14.0 129 22.8 127 1.20 150 5.77 176 23.7 181 0.43 183 5.01 161 28.0 174 0.42 192 9.68 158 24.5 164 0.20 58
CVENG22+RIC [199]133.7 1.54 92 5.77 106 0.02 101 3.28 128 8.77 129 0.20 79 1.59 129 5.90 146 0.22 107 4.37 146 10.4 165 0.61 134 14.0 129 22.8 127 1.24 182 5.27 117 21.7 128 0.27 122 4.92 152 26.6 155 0.16 160 9.66 154 24.4 158 0.23 163
LSM_FLOW_RVC [182]134.1 2.21 185 9.43 187 0.05 194 3.45 133 9.33 142 0.22 89 1.70 142 7.32 179 0.24 121 4.38 147 11.1 171 0.52 105 13.8 63 22.6 80 1.18 141 5.27 117 21.6 122 0.32 148 4.82 141 26.0 138 0.10 102 9.17 102 23.0 90 0.25 180
LocallyOriented [52]134.2 1.61 120 6.13 130 0.01 7 4.64 176 10.9 185 0.40 148 1.83 151 6.44 162 0.26 133 4.45 154 10.2 164 0.47 73 14.0 129 22.8 127 1.01 60 5.58 166 22.6 159 0.27 122 5.18 172 26.8 161 0.15 153 9.66 154 24.4 158 0.20 58
Horn & Schunck [3]134.5 1.62 123 5.42 79 0.01 7 5.40 189 10.9 185 0.44 161 2.27 174 6.97 173 0.45 168 6.35 187 11.5 177 0.65 144 14.1 156 23.0 160 1.06 104 4.95 70 20.4 73 0.17 70 5.51 183 28.2 176 0.14 144 9.57 150 23.7 141 0.18 35
TriangleFlow [30]135.6 1.73 154 6.50 147 0.02 101 3.84 145 9.51 154 0.31 122 1.78 146 5.71 136 0.27 140 4.43 152 10.1 162 0.57 123 13.7 47 22.5 61 0.98 40 5.69 172 22.9 168 0.23 101 5.16 170 28.3 179 0.21 175 10.1 181 25.4 181 0.21 98
2bit-BM-tele [96]138.6 1.51 77 5.13 61 0.04 188 4.17 158 10.2 170 0.41 151 1.52 117 4.90 72 0.46 169 4.01 130 8.64 109 0.60 133 14.4 180 23.3 176 1.05 100 5.89 180 24.1 183 0.45 185 5.77 189 32.3 196 0.60 195 8.90 58 22.5 52 0.21 98
Shiralkar [42]139.2 1.85 167 7.19 164 0.01 7 4.31 164 9.75 164 0.37 141 2.10 164 7.58 181 0.36 158 5.54 180 11.4 174 0.63 139 13.8 63 22.5 61 1.07 108 5.46 150 22.4 154 0.34 158 5.32 178 27.8 173 0.20 174 9.36 136 23.5 126 0.20 58
LiteFlowNet [138]140.2 1.90 172 8.16 179 0.03 169 2.81 88 8.01 103 0.20 79 1.60 132 6.95 172 0.24 121 4.75 164 11.8 180 0.86 176 13.9 89 22.7 106 1.25 190 5.50 154 22.1 147 0.32 148 5.07 165 26.6 155 0.19 169 8.95 67 22.6 61 0.25 180
EPMNet [131]140.5 2.65 192 10.8 194 0.03 169 3.16 120 8.19 112 0.25 100 1.75 143 6.40 159 0.27 140 5.13 171 13.4 191 0.65 144 14.1 156 23.0 160 1.11 122 5.39 143 22.1 147 0.23 101 4.65 116 25.5 118 0.08 68 9.23 115 23.3 111 0.25 180
Correlation Flow [76]140.6 1.71 152 6.50 147 0.02 101 4.00 151 10.2 170 0.36 135 1.35 75 4.81 62 0.19 81 3.90 118 8.77 117 0.50 97 14.0 129 22.9 149 1.05 100 6.25 194 24.8 193 0.43 183 5.22 174 28.1 175 0.19 169 9.80 168 24.7 171 0.23 163
TI-DOFE [24]141.8 1.76 156 6.02 123 0.01 7 6.21 195 11.7 195 0.51 184 1.97 160 7.23 177 0.28 144 6.30 186 11.3 172 0.85 175 14.0 129 22.8 127 1.02 75 4.96 71 20.4 73 0.15 56 5.21 173 27.1 167 0.15 153 9.86 171 23.8 144 0.26 189
SPSA-learn [13]142.2 1.59 115 5.32 73 0.01 7 4.23 162 9.36 145 0.42 156 2.54 181 6.27 156 0.80 188 5.24 176 9.44 147 0.73 158 14.0 129 22.8 127 1.03 87 5.27 117 21.7 128 0.31 139 5.93 194 33.0 197 0.86 198 10.4 186 26.2 190 0.20 58
IAOF2 [51]143.0 1.81 162 6.46 145 0.02 101 4.65 177 11.3 193 0.36 135 1.57 125 5.79 144 0.21 99 4.61 162 10.0 161 0.56 119 14.4 180 23.5 181 1.16 133 5.48 153 22.6 159 0.29 133 4.75 132 25.6 122 0.11 116 9.57 150 24.1 152 0.21 98
ROF-ND [105]143.0 1.73 154 5.36 75 0.01 7 3.43 132 9.15 139 0.27 108 1.59 129 5.63 132 0.21 99 5.50 178 12.2 187 0.77 163 14.0 129 22.8 127 1.21 156 5.96 186 24.2 186 0.42 180 5.51 183 28.7 182 0.11 116 9.90 177 24.7 171 0.22 137
IIOF-NLDP [129]143.1 1.76 156 6.66 153 0.02 101 3.58 139 9.59 157 0.28 113 1.79 148 5.02 84 0.24 121 4.13 138 8.86 121 0.63 139 13.8 63 22.6 80 1.05 100 6.33 196 24.8 193 0.52 195 5.81 191 31.8 195 0.63 196 9.72 162 24.2 156 0.22 137
StereoFlow [44]145.1 4.05 198 12.8 198 0.02 101 5.34 188 12.0 196 0.29 115 1.36 77 5.65 134 0.22 107 3.80 103 8.17 87 0.50 97 16.7 197 27.3 197 1.13 126 7.27 198 29.7 198 0.42 180 4.58 98 25.5 118 0.10 102 10.3 182 26.1 187 0.21 98
SegOF [10]150.2 1.57 111 6.05 126 0.02 101 3.63 140 8.91 133 0.24 97 2.71 186 6.79 170 0.74 186 4.81 166 11.7 179 0.73 158 14.0 129 22.8 127 1.22 169 5.52 157 22.7 163 0.48 189 5.17 171 28.7 182 0.33 188 9.21 109 23.2 104 0.23 163
IRR-PWC_RVC [180]150.7 2.29 187 9.48 188 0.04 188 3.13 118 8.58 121 0.25 100 1.87 156 8.32 191 0.24 121 5.21 175 12.8 189 0.52 105 14.3 174 23.3 176 1.30 197 5.40 144 22.2 150 0.23 101 4.82 141 26.1 143 0.08 68 9.67 157 24.5 164 0.23 163
OFRF [132]150.8 2.03 179 7.52 171 0.03 169 4.40 166 10.2 170 0.41 151 1.67 141 6.55 165 0.17 55 4.10 136 9.44 147 0.50 97 14.2 170 23.2 172 1.16 133 5.75 175 23.2 174 0.24 109 5.02 162 27.0 164 0.11 116 10.0 180 25.4 181 0.22 137
ACK-Prior [27]153.9 1.64 132 6.39 144 0.02 101 2.81 88 7.97 100 0.19 72 2.53 179 5.74 140 0.63 181 4.56 161 10.1 162 1.09 185 14.7 190 24.0 191 1.27 195 6.04 189 24.5 191 0.29 133 5.04 164 27.4 170 0.10 102 11.0 193 27.7 194 0.22 137
SILK [80]154.2 1.86 168 7.35 167 0.01 7 5.84 192 11.2 190 0.60 190 3.00 189 7.69 182 0.83 191 5.68 182 10.6 168 0.69 151 14.1 156 23.0 160 1.00 48 5.31 129 21.3 111 0.36 168 5.02 162 27.0 164 0.28 183 9.50 145 23.5 126 0.24 173
Dynamic MRF [7]157.4 1.58 113 6.37 143 0.02 101 3.55 136 9.67 160 0.27 108 2.35 176 7.75 185 0.50 173 5.74 183 10.9 170 1.06 183 14.0 129 22.8 127 1.23 175 5.90 183 24.1 183 0.51 194 5.28 177 28.7 182 0.34 189 9.71 160 23.9 149 0.21 98
Adaptive flow [45]158.3 2.02 177 6.27 139 0.03 169 5.93 193 11.2 190 0.55 187 1.87 156 5.74 140 0.37 163 5.16 172 9.21 141 0.73 158 14.7 190 24.0 191 1.04 94 5.89 180 24.3 187 0.37 171 4.72 128 26.3 152 0.14 144 9.84 169 24.8 174 0.18 35
Learning Flow [11]158.8 1.62 123 6.12 129 0.02 101 4.43 168 10.4 176 0.33 130 2.86 187 7.92 188 0.82 190 5.19 173 9.72 154 0.59 131 14.6 187 23.8 189 1.10 120 5.42 146 22.4 154 0.27 122 5.24 175 28.3 179 0.17 164 10.3 182 25.4 181 0.23 163
H+S_RVC [176]160.9 2.01 176 7.81 175 0.01 7 4.57 175 9.19 141 0.41 151 2.93 188 9.46 193 0.48 172 8.52 195 12.1 185 0.86 176 14.5 184 23.4 179 1.09 117 5.54 162 22.6 159 0.35 164 5.77 189 28.8 186 0.31 185 9.88 174 23.6 131 0.21 98
StereoOF-V1MT [117]161.5 1.94 174 7.40 169 0.02 101 3.93 149 9.53 155 0.41 151 2.57 182 7.29 178 0.60 179 6.23 185 11.5 177 0.94 180 14.2 170 23.0 160 1.24 182 5.81 178 22.7 163 0.48 189 5.53 186 28.2 176 0.29 184 9.16 101 22.7 70 0.22 137
FOLKI [16]162.9 1.88 170 7.22 166 0.02 101 6.20 194 11.2 190 0.86 196 2.60 183 9.02 192 0.64 182 7.81 192 12.1 185 1.70 195 14.6 187 23.7 186 1.06 104 5.19 110 21.0 98 0.24 109 5.43 181 28.9 187 0.32 186 9.77 165 24.1 152 0.21 98
NL-TV-NCC [25]163.7 2.10 181 7.63 174 0.03 169 3.63 140 9.77 165 0.25 100 2.10 164 6.55 165 0.29 149 5.56 181 12.2 187 0.54 113 14.5 184 23.5 181 1.08 113 6.15 190 24.4 188 0.36 168 6.66 198 29.8 192 0.16 160 10.3 182 25.8 186 0.21 98
UnFlow [127]164.2 2.13 183 8.96 184 0.03 169 4.27 163 9.79 166 0.42 156 2.12 168 7.71 183 0.35 157 4.42 149 10.4 165 0.67 148 14.0 129 22.9 149 1.16 133 5.85 179 23.3 177 0.47 186 4.82 141 25.6 122 0.16 160 11.0 193 25.7 185 0.33 195
SLK [47]168.4 2.08 180 8.23 180 0.01 7 5.10 186 9.38 146 0.50 181 3.21 190 7.73 184 0.83 191 8.10 194 14.2 193 1.61 193 14.5 184 23.7 186 1.06 104 5.77 176 22.5 156 0.36 168 5.84 192 30.6 193 0.36 191 9.87 172 24.4 158 0.22 137
HCIC-L [97]169.6 3.37 197 10.9 195 0.07 196 4.98 181 10.3 173 0.38 146 2.44 177 8.00 189 0.36 158 7.09 188 13.0 190 0.71 155 14.9 193 24.2 193 1.07 108 5.99 188 24.1 183 0.23 101 4.74 131 26.0 138 0.11 116 12.3 197 30.4 197 0.25 180
WRT [146]170.4 1.84 166 6.75 158 0.03 169 4.02 153 9.17 140 0.37 141 3.21 190 5.25 105 0.84 193 4.42 149 9.03 130 0.84 173 14.3 174 23.4 179 1.08 113 6.54 197 26.5 197 0.54 196 6.27 196 34.8 198 0.84 197 10.9 192 27.5 193 0.27 191
WOLF_ROB [144]176.3 2.64 190 9.90 190 0.03 169 5.04 182 10.9 185 0.45 164 2.66 184 6.77 169 0.46 169 4.88 169 12.0 184 0.65 144 14.4 180 23.5 181 1.22 169 5.89 180 23.6 179 0.37 171 5.89 193 29.3 188 0.19 169 9.87 172 24.7 171 0.25 180
FFV1MT [104]176.8 2.64 190 10.4 193 0.03 169 4.88 179 9.35 143 0.52 186 4.45 195 13.1 197 0.71 185 7.42 189 11.9 182 1.22 188 14.6 187 23.7 186 1.09 117 5.53 160 21.1 105 0.33 154 6.16 195 29.7 191 0.35 190 10.5 189 25.6 184 0.26 189
PGAM+LK [55]182.1 2.35 189 9.74 189 0.05 194 5.04 182 10.5 179 0.66 192 3.38 192 9.68 194 0.84 193 7.99 193 14.6 195 1.24 190 14.7 190 23.8 189 1.10 120 5.92 184 23.9 182 0.35 164 5.33 179 28.5 181 0.17 164 9.88 174 24.6 168 0.32 194
Pyramid LK [2]183.2 2.13 183 8.10 178 0.04 188 7.17 197 11.5 194 0.99 198 6.22 197 6.97 173 1.21 197 13.9 198 24.7 198 2.97 198 15.7 196 25.7 196 1.11 122 5.42 146 22.0 141 0.30 138 5.55 187 29.5 190 0.52 193 11.9 195 29.7 196 0.54 198
Heeger++ [102]186.0 3.11 196 11.9 197 0.03 169 4.77 178 9.65 159 0.51 184 4.48 196 12.0 196 0.80 188 7.42 189 11.9 182 1.22 188 15.0 194 24.5 194 1.23 175 6.24 192 23.0 172 0.60 197 6.37 197 29.4 189 0.32 186 10.4 186 25.1 180 0.25 180
GroupFlow [9]186.6 2.80 195 11.2 196 0.04 188 4.49 171 10.5 179 0.43 158 3.45 193 9.80 195 0.88 195 5.90 184 13.7 192 1.21 187 15.1 195 24.6 195 1.24 182 6.24 192 25.2 195 0.49 192 5.51 183 28.7 182 0.21 175 10.6 190 26.4 191 0.24 173
Periodicity [79]194.8 2.65 192 10.3 192 0.09 197 9.86 198 13.0 198 0.95 197 7.07 198 15.7 198 2.07 198 9.47 196 22.6 197 1.94 196 16.9 198 27.6 198 1.35 198 6.22 191 24.5 191 0.41 178 5.73 188 30.9 194 0.58 194 12.2 196 29.3 195 0.40 197
AVG_FLOW_ROB [137]199.0 18.5 199 43.1 199 1.46 199 22.0 199 25.4 199 2.17 199 18.9 199 25.1 199 4.07 199 34.3 199 52.0 199 7.35 199 26.2 199 39.9 199 2.35 199 16.3 199 52.5 199 2.03 199 21.5 199 44.4 199 1.54 199 26.6 199 42.2 199 2.44 199
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.