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        
SD
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]3.1 4.89 3 5.93 3 1.39 2 5.09 2 6.39 2 2.41 2 8.86 4 8.88 2 5.01 3 6.62 2 8.45 2 5.09 4 14.8 2 16.7 2 7.59 4 10.1 2 14.2 2 4.86 8 16.1 2 24.7 2 6.38 10 14.0 2 17.6 2 6.39 5
IFRNet [193]6.7 4.88 2 5.99 4 1.49 7 5.57 4 7.06 4 3.38 42 7.09 1 8.69 1 4.53 2 6.93 4 8.83 4 5.89 8 15.6 3 17.7 3 8.10 12 11.8 7 16.7 7 4.80 5 16.5 5 25.3 5 6.35 5 14.8 5 18.6 5 6.63 16
SoftSplat [169]9.0 4.71 1 5.71 2 1.42 5 5.82 5 7.42 7 2.98 26 9.56 6 9.45 6 6.82 15 6.69 3 8.59 3 5.07 3 18.5 16 21.0 16 7.63 5 10.9 5 15.4 5 5.18 33 16.7 6 25.6 6 6.69 24 15.1 7 19.0 7 6.17 4
EAFI [186]9.1 5.02 4 6.49 5 1.24 1 5.04 1 6.23 1 2.39 1 8.17 2 11.6 17 5.84 7 6.50 1 8.17 1 4.77 1 20.0 22 22.7 22 8.16 16 13.6 19 19.3 19 5.03 21 18.3 15 28.0 15 6.33 2 14.3 3 17.9 3 6.69 19
BMBC [171]15.4 5.17 6 6.57 6 1.56 8 6.16 9 7.86 12 3.58 48 12.7 16 11.7 18 9.83 49 8.17 8 10.6 8 6.27 14 16.9 9 19.2 10 8.14 15 10.4 3 14.7 3 5.03 21 18.0 14 27.5 14 6.24 1 15.2 8 19.1 8 8.10 62
FGME [158]16.1 5.49 11 7.87 12 1.40 3 6.88 21 8.20 19 4.52 99 11.2 8 12.4 25 7.41 19 7.30 6 9.16 6 7.71 26 16.3 5 18.4 5 9.05 32 12.4 12 17.7 12 4.89 10 16.2 3 24.9 4 6.38 10 15.5 9 19.5 9 6.70 21
SepConv++ [185]17.5 6.61 24 10.1 26 1.61 13 6.11 7 7.85 11 2.41 2 14.7 56 10.7 12 13.5 106 8.52 10 11.2 14 6.34 16 16.9 9 19.1 9 8.18 17 10.6 4 15.0 4 4.87 9 17.0 7 26.1 7 6.33 2 17.2 23 21.7 24 6.51 9
DistillNet [184]18.5 5.05 5 6.97 8 2.46 153 5.26 3 6.62 3 3.10 34 9.11 5 9.58 7 5.74 5 7.14 5 9.02 5 6.04 10 16.6 7 18.7 6 8.98 31 12.6 13 17.8 13 5.17 32 17.3 9 26.4 9 7.34 40 15.8 11 19.9 11 6.69 19
STAR-Net [164]19.2 5.30 8 7.45 10 1.40 3 7.21 23 9.10 32 3.88 63 12.8 18 13.2 31 8.32 30 8.94 12 10.8 12 5.65 5 16.6 7 18.9 8 7.90 8 13.9 22 19.7 22 5.02 20 21.2 34 32.5 34 6.59 21 16.7 19 21.0 19 5.33 1
FLAVR [188]19.2 5.99 15 8.35 13 1.60 12 6.18 10 7.45 8 3.48 44 12.9 20 10.8 14 9.41 45 14.8 91 17.0 45 8.82 54 14.5 1 16.4 1 7.27 2 13.7 20 19.4 21 4.34 1 16.3 4 24.8 3 6.82 28 14.3 3 18.0 4 6.14 3
AdaCoF [165]22.2 6.28 17 9.48 23 2.43 148 6.15 8 7.83 10 3.49 45 13.8 42 9.26 3 10.4 57 9.55 16 11.3 15 6.22 11 19.4 20 22.0 20 8.11 13 10.9 5 15.4 5 4.92 12 18.5 16 28.4 16 6.36 6 15.0 6 18.9 6 6.59 13
IDIAL [192]24.3 5.95 14 8.38 14 4.03 174 6.55 13 8.37 21 4.03 74 11.8 10 9.42 5 5.75 6 9.26 14 11.6 18 7.79 31 23.0 34 26.1 34 7.11 1 11.9 8 16.9 8 4.69 3 18.8 17 28.9 17 6.59 21 17.1 22 21.5 22 6.12 2
CyclicGen [149]28.0 5.21 7 5.40 1 4.82 187 6.70 17 7.19 5 6.53 179 8.79 3 10.2 9 7.42 20 10.2 21 10.7 9 11.3 112 18.5 16 21.0 16 7.91 10 7.38 1 10.4 1 4.92 12 13.6 1 20.8 1 6.46 15 10.5 1 13.2 1 6.74 27
EDSC [173]29.6 6.50 22 9.34 21 4.62 185 6.34 11 8.04 14 4.17 84 11.9 11 12.1 20 6.77 13 8.83 11 11.1 13 8.90 58 20.1 23 22.8 24 8.41 23 15.6 33 22.2 35 4.95 14 17.1 8 26.2 8 6.37 8 18.2 33 22.9 33 6.45 6
FRUCnet [153]30.6 7.39 33 10.7 31 5.61 194 6.60 14 8.27 20 4.37 93 12.6 14 12.4 25 9.21 40 9.30 15 11.7 20 9.37 69 18.2 15 20.6 15 7.68 6 12.2 9 17.3 9 4.96 16 17.6 10 26.9 10 6.89 29 15.9 12 19.9 11 6.73 24
MS-PFT [159]30.8 6.84 27 10.3 28 2.20 136 7.23 25 9.20 34 4.24 87 12.5 13 13.7 34 7.81 25 8.95 13 11.5 16 6.31 15 18.5 16 21.0 16 9.24 34 12.9 17 18.3 17 4.98 19 19.4 22 29.7 24 7.28 35 17.8 29 22.4 31 6.74 27
DSepConv [162]31.8 6.88 28 10.3 28 4.01 173 6.65 15 8.37 21 4.68 106 13.0 22 11.9 19 7.98 27 10.7 22 12.5 27 9.29 67 17.3 14 19.6 14 8.34 19 12.6 13 17.9 15 4.95 14 17.8 11 27.3 11 6.37 8 17.7 27 22.2 27 6.82 34
GDCN [172]31.8 5.89 13 8.80 17 1.46 6 7.53 40 9.15 33 4.14 80 13.2 26 14.4 36 8.69 33 12.8 40 12.4 26 9.09 61 27.4 76 31.1 76 8.38 20 12.6 13 17.8 13 5.14 30 17.9 13 27.4 13 6.46 15 17.8 29 22.3 28 6.74 27
CtxSyn [134]32.1 5.47 9 7.82 11 2.18 133 5.98 6 7.57 9 3.23 38 19.2 134 10.6 11 17.0 140 7.49 7 9.86 7 5.67 6 20.6 25 23.3 25 8.83 30 12.8 16 18.0 16 4.72 4 19.4 22 29.6 22 6.47 17 16.8 20 21.0 19 7.43 43
MPRN [151]32.1 6.90 29 10.7 31 1.78 66 7.67 50 8.95 27 4.37 93 10.2 7 12.1 20 4.23 1 11.0 29 14.1 32 7.77 28 20.8 28 23.5 28 8.13 14 14.1 24 19.9 24 5.38 36 20.8 30 31.7 30 7.28 35 18.1 32 22.7 32 7.62 45
ADC [161]34.2 6.60 23 9.73 24 4.20 179 6.40 12 8.08 17 4.08 77 15.1 63 10.7 12 10.6 63 10.9 26 12.1 23 8.34 42 20.6 25 23.4 26 8.39 21 14.2 26 20.1 27 4.97 17 19.1 19 29.3 19 6.45 14 17.7 27 22.3 28 6.54 10
SuperSlomo [130]38.9 7.27 32 10.8 33 4.59 183 7.40 33 9.09 30 5.23 136 11.7 9 11.2 16 6.26 9 11.1 31 12.9 30 10.9 102 21.1 29 23.9 29 8.02 11 14.2 26 20.0 26 4.85 7 19.9 27 30.4 26 6.69 24 17.4 25 21.8 25 6.97 35
STSR [170]39.2 6.06 16 8.60 16 3.79 169 8.01 80 7.20 6 10.4 196 13.1 24 10.8 14 11.4 75 8.49 9 10.7 9 8.73 51 20.7 27 23.4 26 7.52 3 15.1 32 21.3 32 5.34 35 20.1 28 30.7 28 7.22 34 15.7 10 19.7 10 6.56 12
MAF-net [163]39.4 6.90 29 9.87 25 5.38 192 7.49 37 8.96 28 5.64 165 12.6 14 13.0 30 8.75 35 10.7 22 12.5 27 8.27 40 21.4 30 24.3 30 8.67 29 14.8 31 20.9 30 5.10 26 20.9 31 32.1 31 6.42 12 16.6 17 20.8 17 6.66 17
TOF-M [150]41.3 6.83 26 10.1 26 3.40 168 7.55 41 9.25 36 5.28 137 13.2 26 10.1 8 10.7 65 10.7 22 13.0 31 9.18 64 22.7 31 25.7 31 8.66 28 13.7 20 19.3 19 5.12 28 21.0 32 32.1 31 6.49 18 19.6 35 24.6 35 6.79 33
ProBoost-Net [191]41.6 6.97 31 10.3 28 4.55 182 7.73 54 9.23 35 5.83 169 13.5 33 10.3 10 10.9 67 9.65 17 12.2 24 9.39 70 19.8 21 22.4 21 8.48 25 14.5 28 20.6 29 4.97 17 19.8 26 30.5 27 6.43 13 17.8 29 22.3 28 6.61 14
OFRI [154]42.7 5.75 12 6.90 7 5.06 189 8.11 91 8.48 23 9.61 191 13.4 30 13.5 32 9.12 38 11.0 29 12.3 25 13.7 168 16.5 6 18.7 6 7.90 8 16.3 44 23.2 45 4.90 11 18.9 18 28.9 17 6.34 4 15.9 12 19.9 11 6.50 8
FeFlow [167]43.3 6.81 25 8.52 15 6.23 196 8.28 107 8.62 25 9.28 188 12.3 12 9.39 4 9.93 50 10.9 26 11.7 20 12.8 162 15.8 4 17.8 4 8.46 24 12.3 10 17.4 10 4.56 2 17.8 11 27.3 11 6.72 26 18.6 34 23.4 34 7.07 40
DAI [168]44.6 5.47 9 7.37 9 3.86 171 7.29 28 8.64 26 5.37 148 13.4 30 16.0 55 9.34 44 10.8 25 10.7 9 14.9 182 20.1 23 22.7 22 8.32 18 17.0 57 24.1 60 5.06 25 20.1 28 30.8 29 6.36 6 16.9 21 21.1 21 6.73 24
DAIN [152]44.8 6.45 21 9.46 22 4.07 175 6.69 16 8.09 18 6.20 175 16.0 77 12.2 24 13.6 108 9.77 20 11.7 20 10.3 86 16.9 9 19.2 10 8.65 27 13.9 22 19.8 23 5.10 26 19.2 20 29.4 20 8.11 100 16.3 14 20.5 14 6.74 27
MV_VFI [183]46.5 6.36 19 9.24 19 4.10 176 6.79 19 8.02 13 6.72 182 17.0 101 12.5 27 14.5 119 9.73 19 11.6 18 10.3 86 16.9 9 19.2 10 8.54 26 14.7 30 20.9 30 5.04 23 19.3 21 29.5 21 7.94 88 16.5 15 20.7 15 6.76 31
TC-GAN [166]46.7 6.31 18 9.15 18 4.14 177 6.80 20 8.05 15 6.66 180 17.1 106 12.5 27 14.5 119 9.69 18 11.5 16 10.3 86 17.0 13 19.2 10 8.40 22 14.5 28 20.5 28 5.05 24 19.4 22 29.6 22 7.95 90 16.5 15 20.7 15 6.77 32
MEMC-Net+ [160]52.2 6.44 20 9.31 20 4.42 181 8.18 98 8.07 16 9.92 193 14.7 56 12.1 20 13.3 102 10.9 26 12.6 29 12.4 156 18.8 19 21.3 19 9.95 37 12.3 10 17.4 10 4.83 6 19.6 25 29.9 25 8.66 114 16.6 17 20.8 17 7.01 37
MDP-Flow2 [68]55.3 8.94 64 13.9 61 1.56 8 7.36 31 9.57 43 2.68 7 15.9 75 20.5 126 16.3 136 13.4 49 18.2 64 8.87 57 24.1 40 27.3 40 12.1 55 17.6 66 25.0 72 6.01 60 22.8 45 34.9 46 7.11 31 20.9 51 26.2 51 7.78 49
CBF [12]57.2 8.02 35 12.4 35 1.75 53 8.18 98 10.3 78 4.84 119 13.2 26 15.5 49 9.17 39 11.5 32 15.0 34 7.94 34 22.8 32 25.8 32 12.2 74 16.2 42 22.9 43 6.24 86 23.4 59 35.8 59 8.06 99 21.2 60 26.7 62 8.24 94
PMMST [112]57.4 8.93 60 14.0 68 1.57 10 7.21 23 9.34 37 2.66 5 14.1 48 16.2 61 11.0 69 15.6 122 21.2 133 14.7 178 24.1 40 27.3 40 12.1 55 16.3 44 23.0 44 5.91 49 22.6 42 34.5 42 7.52 53 19.9 38 25.0 38 8.18 78
CoT-AMFlow [174]61.4 8.90 58 14.0 68 1.64 18 7.56 43 9.84 53 2.60 4 16.3 85 20.2 123 14.8 124 13.3 45 18.0 59 8.86 56 24.1 40 27.3 40 12.1 55 17.9 79 25.4 81 6.03 62 22.9 46 35.1 49 7.09 30 20.7 46 26.0 47 8.55 162
SepConv-v1 [125]62.3 8.19 37 12.5 36 5.08 190 7.89 65 9.09 30 8.08 187 20.8 151 12.1 20 18.4 154 12.5 38 14.8 33 11.7 136 23.5 35 26.6 35 9.13 33 14.1 24 19.9 24 5.12 28 21.1 33 32.2 33 8.37 107 17.2 23 21.5 22 6.71 22
DeepFlow [85]63.4 8.76 49 13.7 52 1.59 11 8.08 88 10.4 89 4.72 108 13.8 42 18.1 89 7.83 26 12.1 33 15.2 35 8.41 44 28.8 110 32.7 110 12.1 55 17.0 57 24.1 60 5.99 57 21.6 36 33.0 37 7.45 46 23.0 117 28.9 119 7.80 51
DeepFlow2 [106]68.8 8.59 44 13.4 45 1.64 18 8.06 86 10.4 89 4.45 96 13.8 42 18.6 94 8.12 29 12.4 35 16.1 37 10.6 93 28.5 104 32.3 103 12.3 85 16.7 49 23.6 49 5.92 51 23.0 51 35.0 47 7.49 49 22.6 98 28.4 99 8.47 157
AdaConv-v1 [124]73.2 9.51 101 14.1 76 4.99 188 9.04 145 9.51 42 9.70 192 18.8 132 13.8 35 18.3 153 14.5 80 16.5 42 15.2 184 25.9 57 29.4 57 7.81 7 13.1 18 18.4 18 5.63 40 21.4 35 32.7 35 7.45 46 17.4 25 21.8 25 6.73 24
CLG-TV [48]73.5 8.34 41 12.9 40 1.98 112 8.74 130 10.8 120 4.75 115 14.0 46 16.0 55 9.23 41 12.4 35 16.1 37 9.95 79 29.7 138 33.7 138 12.0 50 16.8 50 23.9 53 5.46 37 22.2 38 32.9 36 8.02 94 21.8 77 27.4 78 8.33 124
SIOF [67]73.9 8.78 51 13.5 47 1.80 75 8.97 141 11.2 147 4.51 98 16.7 94 23.2 153 11.6 78 13.2 43 17.7 53 9.61 75 23.7 37 26.8 37 11.8 41 17.8 73 25.2 76 5.98 56 23.4 59 35.9 63 7.33 39 22.1 82 27.8 85 8.15 71
Aniso. Huber-L1 [22]75.0 8.22 38 12.7 38 1.84 88 9.12 156 11.1 142 5.11 129 13.6 37 16.3 63 7.58 23 12.2 34 16.1 37 9.16 63 29.8 144 33.8 143 12.7 97 16.9 53 23.9 53 5.57 39 23.2 55 35.5 55 7.30 37 21.8 77 27.4 78 8.32 122
NN-field [71]76.2 9.03 72 14.1 76 1.74 48 7.01 22 9.05 29 2.74 13 18.3 126 19.1 102 12.6 94 16.8 151 22.7 157 15.8 186 24.2 43 27.5 44 12.1 55 17.8 73 25.1 74 6.07 68 23.1 52 35.4 53 7.69 68 20.6 43 25.9 44 8.36 136
LME [70]76.5 8.97 66 14.0 68 1.62 15 8.07 87 10.5 98 3.69 53 16.9 97 17.7 80 9.29 43 14.5 80 19.6 94 9.68 76 29.2 129 33.1 129 15.3 151 18.1 84 25.7 86 6.15 77 22.7 43 34.7 43 7.37 42 21.0 54 26.4 56 8.20 85
CombBMOF [111]77.0 9.74 117 14.3 86 3.85 170 7.82 59 10.2 69 3.81 60 16.2 82 19.1 102 12.8 96 13.8 58 18.5 69 10.2 84 26.5 59 30.0 59 12.2 74 17.8 73 25.2 76 6.09 73 23.1 52 35.2 52 7.64 63 21.3 63 26.7 62 8.21 90
MDP-Flow [26]78.3 8.27 39 12.8 39 1.74 48 7.26 27 9.42 38 3.90 64 17.2 107 16.1 60 15.0 127 13.6 53 18.0 59 10.9 102 28.8 110 32.7 110 15.3 151 17.9 79 25.2 76 7.36 151 23.6 67 36.1 67 12.2 163 20.6 43 25.9 44 8.07 56
IROF-TV [53]78.5 8.93 60 13.9 61 1.82 83 8.15 95 10.6 103 4.01 71 13.9 45 17.6 77 8.70 34 13.3 45 18.0 59 9.04 60 28.5 104 32.3 103 15.3 151 18.5 100 26.2 102 6.57 118 24.7 93 37.8 95 6.81 27 22.2 87 28.0 90 6.71 22
ALD-Flow [66]78.6 10.4 142 16.0 139 1.76 56 7.99 76 10.3 78 3.78 58 14.1 48 19.3 109 6.64 11 16.1 138 21.9 146 5.92 9 26.5 59 30.0 59 14.0 114 16.9 53 23.9 53 6.23 85 22.5 41 34.4 41 7.50 51 23.2 128 29.2 133 8.09 59
NNF-Local [75]78.7 8.84 54 13.8 54 1.61 13 7.25 26 9.44 39 2.76 15 14.6 54 19.3 109 14.5 119 16.0 136 21.6 142 15.8 186 24.2 43 27.5 44 12.2 74 18.4 94 26.0 97 6.42 108 24.2 78 37.1 82 9.54 133 20.3 41 25.4 41 8.27 106
p-harmonic [29]78.7 8.89 57 13.9 61 1.68 25 8.86 135 10.9 127 5.20 135 13.4 30 17.5 76 6.45 10 13.7 56 17.9 58 10.0 81 28.9 115 32.8 116 12.8 98 17.6 66 24.9 68 6.53 117 22.9 46 35.0 47 8.88 115 22.5 93 28.3 95 8.10 62
Second-order prior [8]79.5 8.06 36 12.5 36 1.93 101 8.80 131 11.0 132 4.80 118 12.8 18 16.2 61 7.51 22 12.6 39 16.7 43 6.25 13 28.9 115 32.8 116 12.2 74 18.1 84 25.7 86 6.10 74 23.3 56 35.5 55 9.35 129 22.7 104 28.6 110 8.45 155
OAR-Flow [123]79.5 9.14 81 14.0 68 1.71 36 7.90 67 10.1 60 4.04 75 14.3 51 18.8 97 5.59 4 16.6 147 22.6 153 6.23 12 27.7 86 31.4 85 15.3 151 15.9 38 22.4 38 6.89 132 24.2 78 36.4 71 7.80 78 22.9 114 28.8 116 8.15 71
WLIF-Flow [91]79.6 8.64 45 13.4 45 1.69 29 7.89 65 10.2 69 3.94 66 17.0 101 22.0 137 14.5 119 13.7 56 18.4 67 11.5 124 26.7 62 30.3 62 12.3 85 19.8 152 28.0 153 8.12 175 22.4 40 34.2 40 7.58 59 21.1 58 26.4 56 7.62 45
Ad-TV-NDC [36]81.4 9.09 77 13.8 54 2.24 141 9.50 176 11.1 142 6.94 183 14.2 50 15.4 48 6.85 16 14.5 80 18.6 70 9.51 72 27.4 76 31.1 76 12.3 85 18.2 89 25.8 93 6.40 105 22.9 46 34.7 43 7.43 43 20.6 43 25.8 43 8.26 103
GMFlow_RVC [196]82.8 10.2 136 16.0 139 1.83 86 7.58 44 9.82 52 2.78 17 13.3 29 17.7 80 11.4 75 15.3 108 20.7 121 11.1 107 27.7 86 31.5 88 11.8 41 19.2 133 27.2 135 5.90 48 23.7 69 36.4 71 7.62 61 21.8 77 27.4 78 8.27 106
DF-Auto [113]84.2 9.30 93 14.4 95 1.99 113 8.37 112 10.6 103 4.99 123 15.5 71 22.3 139 8.88 36 13.3 45 17.6 52 9.86 78 25.7 54 29.1 54 13.9 113 18.1 84 25.7 86 5.96 55 25.2 103 38.6 109 10.8 153 20.7 46 25.9 44 8.09 59
IROF++ [58]84.7 8.58 43 13.3 43 1.68 25 7.99 76 10.4 89 3.84 61 17.3 109 18.5 92 12.5 91 12.4 35 16.7 43 9.15 62 28.4 103 32.3 103 15.3 151 19.5 143 27.6 144 6.06 66 23.3 56 35.6 57 8.55 112 23.4 137 29.4 142 7.79 50
Brox et al. [5]84.8 9.33 95 14.7 101 1.62 15 7.86 63 10.1 60 4.14 80 15.9 75 16.0 55 10.4 57 13.5 52 17.7 53 8.77 53 26.8 63 30.4 63 11.9 44 19.1 127 27.0 128 9.52 191 28.6 167 43.6 165 23.0 197 19.9 38 25.0 38 8.05 55
RAFT-it+_RVC [198]85.5 12.8 180 20.3 180 1.64 18 7.62 48 9.89 56 2.95 25 12.9 20 15.3 46 7.13 17 16.8 151 22.7 157 11.0 104 24.0 39 27.2 39 12.0 50 19.0 123 26.8 122 8.90 187 22.7 43 34.8 45 9.44 130 21.0 54 26.3 54 8.56 164
SegFlow [156]86.4 10.1 131 15.9 136 1.67 23 7.58 44 9.88 55 3.06 32 14.8 58 15.0 42 6.71 12 17.3 161 23.6 169 13.1 165 27.7 86 31.4 85 15.3 151 15.8 36 22.3 37 6.18 80 22.9 46 35.1 49 8.62 113 23.1 121 29.0 123 8.31 118
Modified CLG [34]87.3 7.87 34 12.2 34 1.68 25 8.96 139 10.7 115 5.94 173 16.8 95 16.7 65 15.9 134 13.3 45 16.4 41 12.6 160 27.6 82 31.3 82 11.9 44 18.8 114 26.6 115 6.50 114 22.3 39 34.0 39 7.67 65 22.2 87 27.9 87 8.64 167
NNF-EAC [101]87.6 9.00 69 14.0 68 1.99 113 7.79 57 10.2 69 2.85 20 17.5 115 25.1 172 19.2 158 15.4 114 20.6 116 11.6 130 29.9 148 33.9 148 12.1 55 16.5 46 23.4 46 5.99 57 22.9 46 35.1 49 7.51 52 20.9 51 26.2 51 8.42 152
UnDAF [187]90.6 10.3 138 16.2 142 2.94 161 8.10 90 10.6 103 2.74 13 16.9 97 22.9 149 17.3 146 16.4 142 22.0 148 8.13 38 25.3 52 28.7 52 12.1 55 17.6 66 24.9 68 6.10 74 23.3 56 35.6 57 7.30 37 21.0 54 26.4 56 9.46 180
Local-TV-L1 [65]91.0 8.65 46 13.3 43 1.90 97 9.07 150 11.0 132 5.04 127 13.1 24 15.3 46 8.62 32 12.8 40 17.0 45 7.89 33 30.8 180 35.0 181 15.5 186 18.4 94 26.0 97 6.98 136 23.9 75 36.5 76 7.66 64 21.4 66 26.9 67 8.40 148
HCFN [157]91.2 9.82 124 15.4 126 1.74 48 7.71 52 10.1 60 3.24 39 14.8 58 17.1 70 9.77 48 15.2 104 20.6 116 10.8 98 28.1 98 31.9 100 12.1 55 18.0 82 25.4 81 6.40 105 26.0 126 39.7 130 7.69 68 23.1 121 29.0 123 8.48 158
JOF [136]92.3 9.04 73 14.1 76 1.81 80 7.55 41 9.71 50 5.06 128 15.1 63 16.7 65 12.0 80 14.4 76 19.4 89 11.4 118 29.2 129 33.2 131 15.4 178 19.8 152 28.0 153 6.36 101 23.4 59 35.8 59 7.68 67 21.4 66 26.8 66 8.30 115
F-TV-L1 [15]92.4 10.4 142 16.2 142 1.94 104 9.02 143 11.2 147 4.72 108 14.6 54 16.7 65 11.0 69 14.2 67 18.9 79 10.3 86 27.5 79 31.2 80 12.3 85 16.0 39 22.6 39 6.38 102 23.9 75 36.6 78 9.23 124 21.3 63 26.7 62 10.2 185
PH-Flow [99]92.9 9.30 93 14.3 86 1.70 33 7.70 51 10.1 60 2.82 19 14.9 62 20.6 129 14.8 124 14.3 71 19.4 89 11.5 124 25.0 50 28.3 49 12.2 74 21.6 190 30.7 191 9.38 190 25.0 100 38.3 102 7.76 75 22.6 98 28.4 99 8.15 71
FMOF [92]93.6 9.22 88 13.9 61 1.96 108 7.58 44 9.87 54 2.87 21 19.5 138 22.4 140 17.7 148 15.3 108 20.6 116 12.5 159 24.5 47 27.7 46 13.7 108 19.3 137 27.3 138 6.05 64 24.6 91 37.7 93 6.64 23 23.4 137 29.4 142 6.98 36
VCN_RVC [178]95.3 14.1 188 22.5 191 1.93 101 7.72 53 10.1 60 3.17 36 15.6 73 19.7 113 11.0 69 22.0 186 29.9 187 10.2 84 27.1 68 30.7 68 12.1 55 17.6 66 25.0 72 5.84 42 24.3 83 37.1 82 7.57 57 22.1 82 27.7 83 11.2 188
Filter Flow [19]95.8 9.35 97 14.5 97 1.79 70 9.19 158 11.1 142 5.50 157 17.6 119 16.8 69 12.2 84 14.0 63 18.0 59 11.3 112 24.6 48 27.9 48 12.2 74 18.4 94 26.0 97 7.54 157 24.8 94 37.9 97 7.77 76 21.5 69 27.0 70 8.40 148
DMF_ROB [135]95.8 9.66 109 15.1 113 1.75 53 8.12 93 10.3 78 4.86 120 17.2 107 22.7 146 11.7 79 14.5 80 19.3 85 9.60 73 27.3 73 31.0 73 15.3 151 17.9 79 25.4 81 8.26 178 23.5 64 35.9 63 6.49 18 23.2 128 29.2 133 8.32 122
PRAFlow_RVC [177]96.0 10.6 146 16.6 148 1.85 90 7.46 36 9.61 45 3.14 35 16.1 79 20.9 130 15.5 133 15.2 104 20.6 116 6.66 17 23.8 38 26.9 38 12.1 55 18.9 118 26.8 122 6.70 122 23.8 70 36.5 76 14.0 174 24.0 166 30.2 167 8.18 78
C-RAFT_RVC [181]96.1 13.0 182 20.5 182 2.43 148 7.97 75 10.3 78 3.53 46 16.1 79 19.7 113 12.3 87 15.5 118 21.0 129 12.2 148 24.9 49 28.3 49 11.8 41 18.3 93 25.9 95 6.05 64 24.8 94 37.9 97 9.19 123 21.1 58 26.5 60 8.25 99
Sparse Occlusion [54]97.6 9.75 118 15.2 116 2.05 120 8.71 128 11.2 147 4.19 85 13.5 33 15.9 54 7.80 24 14.6 86 19.7 101 7.51 24 30.4 162 34.5 163 15.3 151 16.1 40 22.7 40 6.27 92 26.9 141 41.1 143 7.45 46 23.2 128 29.2 133 8.12 68
TC/T-Flow [77]98.1 9.42 99 14.6 100 2.39 147 8.67 127 11.2 147 4.00 69 13.6 37 16.0 55 8.03 28 17.5 165 23.5 168 10.8 98 27.3 73 31.0 73 15.3 151 17.4 64 24.6 64 5.89 47 25.8 121 37.8 95 9.59 135 22.8 108 28.7 114 8.13 69
CRTflow [81]98.5 8.75 48 13.6 49 2.04 117 9.27 163 11.5 170 5.28 137 16.2 82 22.5 142 9.27 42 12.8 40 17.0 45 11.5 124 27.0 66 30.6 66 15.3 151 17.6 66 24.9 68 6.06 66 27.8 151 42.7 154 7.62 61 23.4 137 29.4 142 8.16 76
RAFT-it [194]99.2 12.3 173 19.5 173 1.80 75 7.30 29 9.44 39 2.73 11 13.6 37 17.6 77 11.2 74 16.7 149 22.6 153 16.0 190 24.2 43 27.4 43 12.0 50 18.5 100 26.2 102 6.41 107 23.1 52 35.4 53 9.26 126 24.5 179 30.6 178 8.67 168
CPM-Flow [114]99.6 9.82 124 15.4 126 1.69 29 7.60 47 9.90 57 3.04 29 15.6 73 15.7 52 7.43 21 16.9 154 23.0 163 12.0 142 27.6 82 31.3 82 15.3 151 18.5 100 26.2 102 7.13 144 23.4 59 35.8 59 9.99 142 23.8 155 29.9 157 8.37 140
COFM [59]99.8 8.95 65 13.8 54 1.90 97 7.42 34 9.61 45 3.19 37 15.3 68 22.1 138 16.3 136 15.4 114 20.9 126 14.6 174 26.8 63 30.4 63 12.2 74 21.4 186 30.3 186 6.26 91 26.3 130 40.4 133 10.4 149 20.8 48 26.1 48 8.36 136
CNN-flow-warp+ref [115]99.9 8.33 40 13.0 41 2.06 122 8.26 106 10.3 78 5.85 170 18.3 126 22.7 146 11.1 72 13.6 53 16.0 36 11.1 107 29.1 127 33.0 126 15.3 151 15.7 35 22.1 34 6.96 135 28.2 157 43.1 158 7.67 65 21.8 77 27.3 76 8.49 159
ComplOF-FED-GPU [35]100.0 9.91 129 15.5 129 1.77 63 7.74 55 10.1 60 4.25 89 19.8 143 17.7 80 17.0 140 15.3 108 20.7 121 11.8 137 28.2 102 32.0 102 14.5 120 16.2 42 22.8 42 5.95 54 26.2 129 39.6 129 9.25 125 22.7 104 28.4 99 8.25 99
PMF [73]100.5 9.35 97 14.5 97 1.77 63 7.80 58 10.1 60 2.68 7 24.0 172 28.7 185 22.5 180 15.3 108 20.6 116 11.6 130 25.7 54 29.2 55 12.1 55 19.1 127 27.0 128 5.92 51 27.6 148 42.4 151 9.09 120 23.1 121 29.0 123 6.47 7
2DHMM-SAS [90]100.8 8.83 53 13.6 49 1.76 56 8.88 137 11.3 155 4.29 90 17.5 115 20.9 130 12.5 91 14.5 80 19.6 94 11.3 112 30.1 153 34.1 152 15.1 136 17.6 66 24.9 68 5.84 42 25.2 103 38.7 111 8.23 104 23.1 121 29.1 126 8.16 76
RAFT-TF_RVC [179]100.8 12.3 173 19.5 173 2.22 137 7.37 32 9.58 44 2.80 18 13.5 33 17.7 80 10.6 63 15.7 128 21.2 133 8.56 45 24.4 46 27.7 46 12.1 55 20.0 156 28.2 156 7.59 162 26.4 131 40.6 138 9.12 121 22.5 93 28.3 95 8.55 162
TC-Flow [46]101.1 10.9 152 17.1 154 1.71 36 8.86 135 11.6 173 4.00 69 13.0 22 16.0 55 6.24 8 15.6 122 21.1 130 8.58 46 27.9 90 31.7 92 15.1 136 18.7 110 26.4 111 6.72 123 24.6 91 37.6 91 7.95 90 23.4 137 29.4 142 8.28 111
OFLAF [78]101.8 9.70 112 15.0 110 1.69 29 7.94 72 10.4 89 2.73 11 14.3 51 15.0 42 10.2 53 13.8 58 18.6 70 8.40 43 30.0 150 34.0 150 15.4 178 17.0 57 23.9 53 6.73 124 30.1 182 46.1 182 13.9 172 23.4 137 29.3 138 9.45 179
LDOF [28]102.2 8.85 55 13.8 54 2.04 117 10.2 193 9.70 49 10.8 198 17.0 101 20.4 125 12.0 80 13.4 49 17.4 50 12.3 153 22.9 33 26.0 33 11.9 44 18.9 118 26.7 118 6.27 92 30.1 182 46.3 184 16.0 178 19.7 36 24.7 36 8.89 175
Horn & Schunck [3]102.4 8.92 59 13.6 49 1.73 41 9.79 186 11.4 160 6.31 177 24.1 173 18.7 95 18.6 156 15.8 132 19.4 89 11.1 107 28.0 93 31.8 94 10.4 38 17.8 73 25.2 76 5.54 38 25.3 108 38.4 105 9.70 138 22.1 82 27.7 83 8.27 106
ProFlow_ROB [142]102.5 9.82 124 15.5 129 1.71 36 8.15 95 10.6 103 3.63 50 15.4 70 12.7 29 8.98 37 19.8 181 26.9 182 7.99 35 29.0 125 33.0 126 15.3 151 15.6 33 22.0 33 5.16 31 26.4 131 40.3 132 7.90 86 24.4 176 30.5 175 11.5 190
Black & Anandan [4]102.7 9.24 90 14.1 76 1.95 106 9.65 183 11.4 160 5.28 137 28.3 182 24.2 162 20.2 168 14.8 91 18.7 74 10.5 91 27.7 86 31.5 88 9.57 36 19.0 123 27.0 128 6.35 99 24.2 78 36.7 79 8.42 108 21.0 54 26.3 54 6.55 11
2D-CLG [1]103.1 8.51 42 13.2 42 1.76 56 8.84 134 10.4 89 5.71 167 19.4 137 15.6 51 15.0 127 14.2 67 16.3 40 14.0 170 31.1 187 35.3 187 20.9 198 16.1 40 22.7 40 6.34 97 27.7 150 42.3 149 8.19 103 21.4 66 26.9 67 8.13 69
FlowNetS+ft+v [110]103.1 9.02 71 14.1 76 2.07 126 10.0 191 11.0 132 9.60 190 16.3 85 14.4 36 13.5 106 13.8 58 17.7 53 13.3 166 29.7 138 33.8 143 15.3 151 16.8 50 23.8 51 6.25 89 27.8 151 42.6 152 7.83 82 20.4 42 25.5 42 8.24 94
PGM-C [118]103.4 9.70 112 15.2 116 1.69 29 7.84 62 10.2 69 3.70 54 21.2 154 17.2 72 12.3 87 17.4 162 23.6 169 8.69 48 28.0 93 31.8 94 15.3 151 16.6 47 23.4 46 6.17 78 26.4 131 40.5 137 8.04 96 24.3 172 30.5 175 8.34 127
MLDP_OF [87]103.5 9.06 74 14.1 76 1.83 86 8.81 132 11.3 155 4.78 117 14.0 46 17.6 77 8.56 31 15.5 118 20.3 112 15.8 186 29.7 138 33.7 138 13.6 104 19.1 127 27.0 128 5.86 45 23.8 70 36.3 69 8.15 102 23.2 128 29.1 126 8.25 99
EpicFlow [100]103.8 9.69 111 15.2 116 1.67 23 7.90 67 10.2 69 4.37 93 16.0 77 14.5 38 9.75 47 19.1 177 25.8 180 12.3 153 27.9 90 31.6 90 15.3 151 16.9 53 23.9 53 6.21 84 24.9 97 38.0 99 10.3 147 24.6 180 30.9 181 8.30 115
Fusion [6]104.9 8.82 52 13.8 54 2.62 155 7.96 73 10.1 60 4.47 97 16.5 89 13.6 33 17.3 146 14.0 63 18.1 63 9.97 80 29.8 144 33.8 143 12.8 98 19.4 139 27.4 139 10.1 194 26.4 131 40.4 133 8.14 101 21.7 73 27.2 74 10.1 184
LFNet_ROB [145]105.0 11.6 162 18.2 165 2.58 154 8.05 84 10.4 89 4.02 73 17.8 121 26.6 177 11.5 77 13.2 43 17.8 56 7.21 22 26.9 65 30.5 65 14.8 127 21.1 179 29.9 180 7.31 149 23.5 64 35.9 63 11.3 156 22.4 91 28.2 93 8.11 66
TV-L1-MCT [64]105.5 9.18 84 14.2 83 1.78 66 8.53 119 11.1 142 3.70 54 17.7 120 23.3 156 13.6 108 14.4 76 19.5 93 11.6 130 30.5 169 34.6 167 13.8 110 18.1 84 25.7 86 6.02 61 25.8 121 39.5 125 15.0 176 21.7 73 27.3 76 7.99 53
AGIF+OF [84]105.5 9.07 75 14.0 68 1.78 66 7.93 71 10.3 78 3.78 58 14.4 53 17.8 84 12.4 89 14.9 95 20.2 109 11.4 118 28.9 115 32.8 116 15.3 151 20.0 156 28.3 157 6.98 136 25.5 111 39.0 114 7.74 73 23.9 162 30.1 166 8.28 111
EAI-Flow [147]105.5 11.1 155 15.4 126 6.27 197 8.02 82 10.2 69 4.70 107 16.9 97 20.1 122 15.0 127 14.8 91 19.8 103 4.86 2 29.2 129 33.1 129 14.8 127 16.6 47 23.5 48 5.99 57 23.8 70 36.4 71 20.9 193 22.6 98 28.4 99 11.1 187
Bartels [41]106.3 12.7 177 20.1 179 2.13 132 8.52 118 11.0 132 4.96 122 13.5 33 14.5 38 10.2 53 14.4 76 18.9 79 10.8 98 23.5 35 26.6 35 12.9 101 19.0 123 26.9 125 6.94 134 24.5 86 37.5 89 19.7 190 23.4 137 29.4 142 8.31 118
S2F-IF [121]106.4 10.3 138 16.3 145 1.79 70 7.83 61 10.2 69 2.90 23 17.0 101 20.0 120 13.9 114 16.1 138 21.6 142 6.69 18 29.2 129 33.2 131 15.3 151 16.8 50 23.7 50 6.34 97 24.9 97 38.2 100 10.7 151 23.9 162 30.0 164 8.35 133
MS_RAFT+_RVC [195]108.3 9.79 121 15.2 116 4.60 184 7.50 38 9.77 51 2.91 24 15.2 66 19.5 111 14.3 117 14.7 90 19.6 94 12.9 164 28.1 98 31.8 94 15.2 145 17.3 62 24.5 63 5.94 53 25.1 101 38.5 107 12.3 164 24.9 185 31.2 186 8.57 165
HAST [107]108.8 8.87 56 13.8 54 1.76 56 7.34 30 9.50 41 2.70 9 28.8 184 28.6 184 24.0 185 14.9 95 20.2 109 7.68 25 28.9 115 32.8 116 12.1 55 21.3 185 30.2 185 7.57 159 28.6 167 43.9 168 7.55 56 22.8 108 28.7 114 8.43 154
OFH [38]108.8 9.54 103 15.0 110 1.74 48 8.49 117 10.6 103 5.13 130 18.1 124 24.9 170 10.4 57 17.4 162 23.7 172 5.72 7 28.7 108 32.5 106 14.6 123 17.6 66 24.8 66 5.85 44 26.0 126 39.2 119 10.2 145 22.7 104 28.5 107 14.1 195
nLayers [57]109.1 9.15 82 14.3 86 1.76 56 7.42 34 9.62 47 3.57 47 27.8 180 29.9 188 25.8 190 15.9 134 21.5 140 11.9 138 30.2 155 34.3 157 14.7 126 20.3 165 28.8 166 6.45 111 23.5 64 36.0 66 7.87 84 21.6 70 27.1 71 8.10 62
TCOF [69]109.7 9.34 96 14.3 86 1.89 93 9.50 176 11.7 180 5.42 150 16.2 82 21.7 135 10.3 55 13.8 58 18.6 70 9.45 71 30.4 162 34.6 167 13.6 104 18.2 89 25.7 86 6.20 83 28.5 164 43.5 164 7.54 54 22.9 114 28.8 116 8.18 78
BlockOverlap [61]110.0 9.09 77 14.3 86 2.04 117 8.96 139 10.9 127 5.37 148 18.1 124 15.5 49 18.0 151 14.2 67 17.2 48 14.0 170 28.9 115 32.8 116 13.8 110 18.8 114 26.7 118 7.92 169 24.8 94 37.2 84 21.0 194 20.0 40 25.1 40 8.38 142
Layers++ [37]110.0 8.93 60 14.0 68 1.76 56 6.74 18 8.61 24 2.71 10 18.3 126 25.8 175 19.3 159 15.3 108 20.8 124 11.3 112 33.1 195 37.6 195 19.8 195 21.6 190 30.6 190 8.73 184 24.4 84 37.4 87 7.81 80 21.6 70 27.1 71 8.09 59
MCPFlow_RVC [197]111.0 12.1 170 18.9 170 1.97 110 7.99 76 10.4 89 3.04 29 16.1 79 23.4 158 10.5 61 15.3 108 20.7 121 10.7 97 26.2 58 29.7 58 11.9 44 21.7 192 30.8 192 6.42 108 23.4 59 35.8 59 7.94 88 24.9 185 30.9 181 8.73 171
FlowFields [108]111.8 9.98 130 15.7 132 2.08 128 7.96 73 10.4 89 3.62 49 23.1 165 23.2 153 20.3 170 16.0 136 21.5 140 7.08 21 27.0 66 30.6 66 14.2 116 19.2 133 27.1 133 6.08 72 24.4 84 37.4 87 10.2 145 23.2 128 29.2 133 8.35 133
DPOF [18]112.1 11.0 153 17.4 158 3.88 172 7.78 56 10.2 69 3.01 27 18.7 130 18.1 89 18.4 154 16.5 144 22.4 150 14.6 174 28.8 110 32.7 110 12.1 55 18.9 118 26.7 118 6.18 80 25.2 103 38.4 105 7.59 60 23.6 150 29.6 150 8.07 56
Classic++ [32]112.4 9.48 100 14.9 105 1.80 75 8.59 122 11.0 132 4.61 102 13.7 41 15.0 42 9.57 46 14.4 76 19.0 81 8.76 52 29.9 148 33.9 148 13.6 104 20.2 163 28.7 164 6.87 131 27.4 145 42.0 145 9.63 137 23.8 155 29.9 157 8.34 127
HBM-GC [103]113.6 9.25 91 14.5 97 1.81 80 9.08 152 11.9 189 3.75 57 17.3 109 18.7 95 17.9 149 14.3 71 19.2 83 8.85 55 30.0 150 34.0 150 15.5 186 21.5 187 30.4 187 8.27 179 27.4 145 42.1 148 7.15 32 20.8 48 26.1 48 7.05 39
NL-TV-NCC [25]113.7 9.19 86 14.3 86 2.18 133 9.02 143 11.6 173 4.13 79 14.8 58 16.7 65 10.9 67 20.8 182 28.1 183 8.19 39 26.5 59 30.0 59 13.1 102 18.9 118 26.7 118 6.43 110 26.6 137 40.4 133 15.1 177 23.7 154 29.7 154 8.29 114
SRR-TVOF-NL [89]114.0 9.65 107 14.8 102 1.82 83 8.21 103 10.6 103 4.76 116 22.7 163 28.1 182 21.9 175 15.6 122 20.9 126 9.18 64 28.9 115 32.8 116 15.3 151 20.7 174 29.3 174 5.91 49 24.5 86 37.6 91 6.56 20 22.5 93 28.2 93 8.34 127
H+S_RVC [176]115.1 9.25 91 14.2 83 1.72 39 8.58 121 10.1 60 5.62 162 17.8 121 18.4 91 12.9 98 14.3 71 17.5 51 9.60 73 30.2 155 34.3 157 15.6 188 19.7 149 27.8 148 7.04 140 25.9 125 39.5 125 10.3 147 22.9 114 28.6 110 8.39 143
Complementary OF [21]115.3 11.4 161 18.1 164 1.70 33 9.23 161 12.1 191 4.19 85 31.6 189 19.0 101 23.6 182 19.5 180 26.5 181 6.72 19 28.1 98 31.8 94 14.6 123 17.3 62 24.4 62 6.38 102 26.1 128 39.0 114 8.92 117 22.3 89 27.9 87 7.57 44
Nguyen [33]115.4 9.83 127 15.2 116 1.73 41 9.59 181 11.0 132 5.65 166 15.3 68 20.5 126 10.3 55 14.6 86 18.8 75 12.1 144 28.8 110 32.7 110 12.2 74 19.4 139 27.4 139 8.01 173 29.7 177 45.5 177 8.29 106 21.2 60 26.6 61 8.34 127
LSM_FLOW_RVC [182]116.2 13.7 186 21.2 186 4.18 178 8.57 120 11.0 132 3.98 68 19.5 138 25.2 174 13.3 102 24.7 190 33.6 192 8.11 37 27.6 82 31.4 85 15.1 136 17.0 57 24.0 59 6.52 116 25.5 111 39.1 117 7.44 44 22.5 93 28.3 95 8.23 92
FESL [72]116.6 9.09 77 13.9 61 1.74 48 7.90 67 10.3 78 3.35 41 16.5 89 21.9 136 12.0 80 15.1 102 20.3 112 11.4 118 30.8 180 35.0 181 15.4 178 19.6 145 27.8 148 6.48 112 27.8 151 42.6 152 7.75 74 23.9 162 30.0 164 8.39 143
CompactFlow_ROB [155]116.7 12.7 177 20.0 178 2.28 142 8.24 105 10.7 115 4.14 80 19.8 143 22.5 142 14.5 119 27.5 197 36.7 198 7.77 28 27.6 82 31.3 82 12.1 55 19.8 152 28.0 153 6.19 82 27.4 145 42.0 145 7.16 33 22.0 81 27.6 81 8.20 85
ProbFlowFields [126]116.8 10.1 131 16.0 139 1.78 66 8.04 83 10.5 98 3.08 33 25.8 179 28.8 186 24.3 186 14.5 80 19.6 94 11.4 118 27.2 71 30.9 72 15.3 151 17.4 64 24.6 64 8.78 185 27.3 144 42.0 145 18.8 188 22.4 91 28.1 91 8.39 143
Efficient-NL [60]116.9 8.71 47 13.5 47 1.68 25 8.66 126 11.2 147 3.65 51 22.5 159 20.0 120 19.9 164 14.3 71 19.3 85 11.0 104 30.5 169 34.7 174 15.0 131 20.1 159 28.4 159 6.27 92 28.5 164 43.7 166 8.92 117 23.8 155 29.9 157 6.66 17
PWC-Net_RVC [143]117.8 11.7 164 18.2 165 2.05 120 8.35 111 10.9 127 3.91 65 13.6 37 17.4 75 6.79 14 18.8 173 25.6 179 8.72 50 30.5 169 34.6 167 15.1 136 19.4 139 27.4 139 5.68 41 23.6 67 36.2 68 7.95 90 24.2 169 30.4 171 11.5 190
FlowFields+ [128]118.7 9.67 110 15.2 116 3.33 167 7.86 63 10.3 78 3.02 28 23.3 167 24.6 167 20.8 171 17.0 156 23.0 163 6.91 20 27.3 73 31.0 73 15.4 178 19.0 123 26.9 125 6.24 86 25.3 108 38.8 112 13.1 167 23.2 128 29.1 126 8.39 143
AggregFlow [95]118.8 12.9 181 20.3 180 1.75 53 8.34 110 10.8 120 4.14 80 20.0 145 24.4 165 19.5 163 16.5 144 22.3 149 12.2 148 25.2 51 28.6 51 12.2 74 16.9 53 23.9 53 6.60 119 29.0 174 43.9 168 16.7 181 23.0 117 28.9 119 8.03 54
RNLOD-Flow [119]119.6 8.93 60 13.8 54 1.65 21 8.48 116 11.0 132 4.06 76 16.3 85 23.2 153 12.8 96 14.1 65 19.1 82 11.1 107 29.7 138 33.7 138 15.6 188 20.3 165 28.7 164 8.92 188 25.7 115 39.4 123 16.4 180 24.2 169 30.4 171 8.20 85
StereoOF-V1MT [117]119.8 11.1 155 17.3 156 1.73 41 8.61 123 10.6 103 5.28 137 23.4 169 17.3 73 17.1 144 16.6 147 19.9 105 12.3 153 27.4 76 31.1 76 15.0 131 17.0 57 23.8 51 6.80 129 30.2 184 46.2 183 12.3 164 21.6 70 26.9 67 9.58 181
TI-DOFE [24]120.4 9.80 122 15.2 116 2.80 159 9.94 189 11.4 160 5.62 162 15.5 71 15.7 52 10.5 61 17.0 156 21.7 144 10.6 93 27.1 68 30.8 70 12.1 55 20.9 177 29.6 178 6.99 138 24.0 77 36.3 69 8.92 117 24.3 172 28.1 91 12.5 193
Occlusion-TV-L1 [63]120.8 10.1 131 15.9 136 2.43 148 9.36 167 11.8 186 5.01 126 12.7 16 14.7 40 7.22 18 17.0 156 22.7 157 11.4 118 28.6 106 32.5 106 12.0 50 18.7 110 26.5 114 7.48 155 25.2 103 37.7 93 10.0 143 24.3 172 30.3 170 9.33 177
Sparse-NonSparse [56]120.8 9.18 84 14.3 86 1.73 41 8.14 94 10.6 103 3.31 40 16.6 92 22.9 149 13.8 113 14.8 91 19.8 103 11.3 112 30.5 169 34.6 167 15.0 131 20.1 159 28.5 162 7.48 155 28.5 164 43.7 166 9.49 131 23.5 147 29.5 147 8.24 94
FlowNet2 [120]120.9 15.6 194 23.6 194 1.96 108 9.34 166 12.1 191 4.72 108 17.3 109 19.2 107 13.0 100 17.1 159 23.1 165 10.1 82 28.0 93 31.8 94 12.3 85 18.6 104 26.3 107 6.35 99 26.7 138 40.8 141 8.04 96 21.7 73 27.2 74 8.30 115
ACK-Prior [27]121.0 9.81 123 15.1 113 2.07 126 8.01 80 10.4 89 3.86 62 25.1 176 19.1 102 22.0 177 15.1 102 20.1 107 10.1 82 30.4 162 34.4 161 15.4 178 19.1 127 26.9 125 7.57 159 25.8 121 39.3 120 19.5 189 22.3 89 27.9 87 7.73 47
LSM [39]121.5 9.10 80 14.2 83 1.73 41 8.33 108 10.9 127 3.40 43 16.6 92 22.7 146 12.2 84 15.0 101 20.3 112 11.0 104 30.5 169 34.7 174 15.1 136 20.7 174 29.4 175 6.17 78 28.1 156 43.0 157 11.5 158 23.8 155 29.9 157 8.27 106
Classic+CPF [82]122.0 9.07 75 14.0 68 1.80 75 8.09 89 10.5 98 3.71 56 17.0 101 21.5 133 12.9 98 13.9 62 18.8 75 11.4 118 30.7 178 34.9 179 15.4 178 21.2 182 30.0 183 7.73 167 28.2 157 43.2 160 7.80 78 24.7 182 31.0 183 7.89 52
ResPWCR_ROB [140]122.0 11.2 160 17.7 160 1.95 106 8.98 142 11.7 180 4.11 78 15.2 66 17.3 73 10.0 51 23.1 188 31.2 190 10.5 91 30.5 169 34.6 167 14.2 116 20.3 165 28.8 166 5.27 34 23.8 70 36.4 71 7.54 54 25.4 190 31.9 194 7.76 48
TriFlow [93]123.0 13.1 183 20.8 183 2.06 122 9.53 179 12.2 193 5.29 144 16.5 89 18.5 92 10.1 52 17.2 160 22.8 160 7.74 27 27.9 90 31.6 90 15.1 136 19.4 139 27.4 139 6.07 68 24.5 86 37.2 84 10.9 154 23.8 155 29.8 156 8.15 71
3DFlow [133]123.2 9.65 107 14.9 105 1.89 93 7.82 59 10.0 59 4.94 121 16.9 97 19.9 118 13.7 111 16.5 144 22.4 150 15.8 186 29.3 134 33.2 131 12.5 92 18.4 94 25.9 95 8.56 182 27.2 142 41.4 144 10.1 144 23.4 137 29.3 138 8.87 173
PBOFVI [189]123.2 9.77 120 15.2 116 1.79 70 9.44 172 11.9 189 5.45 154 18.3 126 23.9 160 13.6 108 14.9 95 20.1 107 11.5 124 30.1 153 34.2 154 15.2 145 18.2 89 25.7 86 6.03 62 25.7 115 38.5 107 9.59 135 23.0 117 28.8 116 8.36 136
TVL1_RVC [175]123.6 10.6 146 16.6 148 1.87 92 9.87 187 11.6 173 5.57 158 21.5 156 19.8 117 15.9 134 15.2 104 19.6 94 11.6 130 27.1 68 30.7 68 12.1 55 19.2 133 27.2 135 7.16 145 28.2 157 42.8 155 13.2 169 20.9 51 26.2 51 8.37 140
CostFilter [40]123.6 10.8 151 17.0 153 1.80 75 7.90 67 10.3 78 2.66 5 24.6 175 27.7 181 21.9 175 18.7 172 25.4 177 13.7 168 27.5 79 31.1 76 12.6 94 18.2 89 25.8 93 5.87 46 28.9 172 44.2 173 9.34 128 24.4 176 30.7 179 8.20 85
TF+OM [98]123.7 11.8 166 18.7 168 3.19 164 8.23 104 10.8 120 4.54 100 15.1 63 19.7 113 10.4 57 16.3 141 21.9 146 7.87 32 28.9 115 32.8 116 19.1 194 18.6 104 26.3 107 6.68 121 26.5 136 40.7 139 11.5 158 23.8 155 29.9 157 8.23 92
CVENG22+RIC [199]124.4 9.21 87 14.4 95 1.77 63 8.33 108 10.6 103 4.33 91 20.5 148 19.1 102 12.5 91 17.9 168 24.0 173 12.2 148 30.2 155 34.2 154 15.3 151 20.0 156 28.4 159 6.07 68 25.7 115 39.3 120 8.47 109 24.3 172 30.4 171 8.18 78
FFV1MT [104]124.5 11.6 162 17.7 160 2.19 135 9.20 159 10.9 127 5.96 174 22.6 160 30.3 189 16.3 136 15.5 118 18.8 75 12.4 156 27.5 79 31.2 80 11.6 40 18.6 104 25.7 86 7.42 154 27.2 142 40.7 139 8.88 115 21.2 60 26.4 56 9.73 182
Ramp [62]125.1 9.22 88 14.3 86 1.73 41 8.19 100 10.7 115 4.24 87 21.9 158 28.8 186 21.1 174 14.2 67 19.2 83 11.6 130 30.6 176 34.8 177 14.8 127 20.4 169 29.0 172 7.40 152 28.0 155 42.9 156 7.57 57 23.0 117 28.9 119 8.28 111
AugFNG_ROB [139]125.3 12.1 170 19.0 171 1.94 104 8.44 115 10.6 103 5.42 150 17.3 109 23.9 160 10.8 66 26.2 194 34.7 193 11.5 124 31.6 190 35.9 190 15.3 151 18.7 110 26.4 111 6.38 102 24.9 97 38.2 100 7.91 87 19.8 37 24.8 37 8.36 136
IAOF2 [51]126.2 10.7 150 16.6 148 2.36 145 9.40 168 11.6 173 5.33 145 17.4 114 18.0 86 12.4 89 14.1 65 18.2 64 9.32 68 30.3 161 34.4 161 14.0 114 20.5 173 29.1 173 8.20 176 25.2 103 38.3 102 8.49 110 23.1 121 29.1 126 8.24 94
SVFilterOh [109]127.0 10.5 145 16.4 146 1.97 110 7.65 49 9.98 58 3.05 31 28.0 181 30.4 190 25.4 188 15.6 122 21.2 133 14.7 178 28.9 115 32.7 110 15.4 178 20.1 159 28.4 159 6.61 120 25.8 121 39.5 125 7.84 83 22.5 93 28.3 95 8.49 159
TV-L1-improved [17]127.5 9.53 102 14.9 105 1.99 113 9.46 173 11.7 180 5.17 132 22.6 160 14.8 41 20.1 167 13.4 49 17.8 56 8.05 36 30.2 155 34.3 157 11.9 44 19.6 145 27.7 145 8.09 174 29.9 180 45.8 180 9.73 139 23.4 137 29.3 138 8.42 152
Adaptive [20]127.6 11.0 153 17.3 156 1.89 93 9.41 170 11.6 173 5.19 134 14.8 58 17.1 70 11.1 72 15.7 128 21.1 130 12.1 144 31.1 187 35.3 187 12.0 50 18.8 114 26.6 115 8.00 172 27.8 151 42.3 149 8.01 93 22.6 98 28.4 99 8.63 166
EPMNet [131]127.7 16.1 196 24.7 196 2.22 137 9.04 145 11.7 180 4.55 101 17.3 109 19.2 107 13.0 100 26.7 196 36.3 197 12.1 144 28.0 93 31.8 94 12.3 85 18.4 94 26.0 97 6.25 89 26.7 138 40.8 141 8.04 96 22.6 98 28.4 99 8.35 133
Classic+NL [31]128.2 8.97 66 13.9 61 1.79 70 8.11 91 10.5 98 4.01 71 20.8 151 28.3 183 19.9 164 14.3 71 19.3 85 11.5 124 30.7 178 34.8 177 14.6 123 20.3 165 28.8 166 7.40 152 28.3 160 43.4 162 11.9 162 23.5 147 29.6 150 8.25 99
Dynamic MRF [7]128.4 10.1 131 15.9 136 1.81 80 8.42 114 10.8 120 4.73 112 19.5 138 19.1 102 12.2 84 15.6 122 19.3 85 12.8 162 27.2 71 30.8 70 15.2 145 18.6 104 26.3 107 7.28 148 28.8 171 44.1 172 12.4 166 24.6 180 30.7 179 9.73 182
TriangleFlow [30]128.6 9.59 105 14.8 102 2.06 122 9.07 150 11.4 160 5.47 155 19.2 134 20.2 123 13.9 114 13.6 53 18.2 64 8.31 41 30.0 150 34.1 152 9.31 35 17.8 73 25.2 76 7.56 158 30.8 186 47.2 186 13.9 172 25.5 193 31.9 194 11.3 189
Heeger++ [102]128.9 14.5 190 21.7 188 4.63 186 9.50 176 11.0 132 5.73 168 25.4 178 23.5 159 14.4 118 15.5 118 18.8 75 12.4 156 28.7 108 32.5 106 15.2 145 15.8 36 22.2 35 6.73 124 27.6 148 39.8 131 9.28 127 22.1 82 27.6 81 8.34 127
IAOF [50]129.4 11.1 155 16.6 148 5.32 191 10.6 195 12.3 195 5.87 171 23.3 167 24.2 162 19.4 160 15.4 114 19.7 101 12.0 142 28.9 115 32.8 116 12.1 55 18.8 114 26.6 115 7.26 147 25.6 114 39.1 117 7.35 41 22.1 82 27.8 85 8.26 103
ROF-ND [105]129.6 9.00 69 13.9 61 1.62 15 9.53 179 10.8 120 10.7 197 16.4 88 22.9 149 12.7 95 18.3 170 24.1 174 11.9 138 29.4 136 33.3 136 15.2 145 18.6 104 26.2 102 7.60 163 24.5 86 37.3 86 13.2 169 24.4 176 30.5 175 9.33 177
Steered-L1 [116]129.6 8.76 49 13.7 52 1.82 83 8.00 79 10.3 78 4.72 108 31.9 190 33.2 196 29.2 195 17.4 162 22.8 160 14.1 172 29.5 137 33.5 137 14.2 116 19.7 149 27.9 151 6.28 96 26.4 131 40.4 133 18.7 187 23.8 155 29.9 157 7.04 38
FOLKI [16]130.1 10.6 146 16.5 147 2.43 148 9.94 189 11.2 147 6.70 181 19.6 141 21.6 134 19.9 164 18.3 170 19.4 89 17.3 192 28.0 93 31.7 92 13.6 104 19.1 127 27.1 133 10.9 196 24.2 78 36.9 80 17.3 184 21.3 63 26.7 62 8.10 62
LocallyOriented [52]130.5 10.1 131 15.7 132 1.79 70 9.46 173 11.6 173 5.28 137 23.1 165 24.2 162 20.9 173 19.3 179 23.2 166 7.35 23 30.4 162 34.6 167 12.6 94 18.9 118 26.8 122 6.27 92 25.7 115 38.6 109 7.89 85 23.6 150 29.6 150 8.19 83
FF++_ROB [141]130.6 10.6 146 16.7 152 1.70 33 8.19 100 10.6 103 3.67 52 21.6 157 22.6 144 17.0 140 19.0 175 25.5 178 14.9 182 28.9 115 32.8 116 15.4 178 19.3 137 27.4 139 6.24 86 25.7 115 39.5 125 11.8 161 23.5 147 29.5 147 8.27 106
SILK [80]131.7 9.72 116 15.1 113 2.69 156 10.2 193 11.4 160 7.82 186 39.2 198 32.9 195 28.5 194 14.6 86 18.4 67 9.73 77 29.0 125 32.9 125 10.4 38 21.2 182 30.0 183 7.00 139 24.5 86 37.5 89 8.03 95 23.1 121 28.9 119 8.31 118
GraphCuts [14]134.5 11.7 164 17.8 162 2.02 116 8.15 95 10.5 98 4.65 104 25.3 177 15.2 45 19.4 160 14.9 95 19.6 94 11.9 138 29.8 144 33.8 143 17.8 192 19.6 145 27.8 148 6.50 114 28.6 167 43.9 168 11.1 155 24.0 166 30.2 167 8.15 71
S2D-Matching [83]134.7 9.57 104 14.9 105 1.76 56 8.37 112 10.8 120 4.36 92 20.1 147 24.9 170 18.2 152 15.7 128 21.3 138 15.7 185 28.8 110 32.7 110 14.5 120 21.5 187 30.4 187 11.0 197 25.7 115 39.3 120 11.5 158 23.1 121 29.1 126 8.75 172
ContinualFlow_ROB [148]135.2 12.2 172 19.3 172 2.23 139 8.71 128 11.3 155 4.73 112 17.5 115 19.9 118 13.3 102 22.6 187 30.7 189 8.65 47 32.4 193 36.8 194 15.3 151 18.5 100 26.2 102 6.12 76 28.6 167 43.9 168 8.50 111 22.7 104 28.4 99 8.39 143
BriefMatch [122]135.4 9.89 128 15.5 129 2.11 130 8.05 84 10.2 69 5.90 172 23.5 170 18.0 86 22.7 181 18.2 169 18.6 70 18.7 195 28.1 98 31.9 100 13.8 110 19.5 143 27.7 145 7.05 142 26.7 138 39.4 123 21.6 195 23.4 137 29.3 138 14.3 197
RFlow [88]135.5 9.71 114 15.2 116 1.91 100 9.06 148 11.2 147 5.42 150 22.8 164 22.6 144 17.9 149 15.8 132 21.2 133 12.7 161 29.2 129 33.2 131 11.9 44 19.2 133 27.2 135 7.63 164 28.9 172 44.4 174 7.73 71 23.4 137 29.5 147 8.46 156
ComponentFusion [94]135.5 12.3 173 19.5 173 1.66 22 8.65 125 11.4 160 2.88 22 19.7 142 21.0 132 15.1 130 15.4 114 20.9 126 14.4 173 29.7 138 33.7 138 14.5 120 18.6 104 26.3 107 7.67 165 31.9 188 49.0 190 20.5 191 24.2 169 30.4 171 8.18 78
Learning Flow [11]136.2 8.99 68 14.1 76 1.85 90 9.10 154 11.3 155 4.99 123 40.2 199 42.5 199 31.6 199 14.9 95 17.2 48 12.2 148 30.8 180 35.0 181 15.1 136 18.7 110 26.4 111 7.58 161 25.1 101 38.3 102 11.4 157 25.5 193 31.7 190 8.24 94
Adaptive flow [45]136.9 10.3 138 14.8 102 2.37 146 9.87 187 11.5 170 5.57 158 18.0 123 17.9 85 17.1 144 16.4 142 20.0 106 14.8 180 32.3 192 36.7 192 16.6 190 21.1 179 29.8 179 8.41 180 23.8 70 36.4 71 13.1 167 21.7 73 27.1 71 7.17 41
FC-2Layers-FF [74]137.4 9.71 114 14.9 105 2.11 130 7.51 39 9.66 48 4.67 105 20.5 148 25.1 172 20.2 168 15.6 122 21.1 130 11.9 138 30.5 169 34.6 167 15.3 151 20.8 176 29.4 175 7.31 149 29.7 177 45.6 179 9.76 140 23.6 150 29.7 154 8.22 91
SLK [47]138.0 9.63 106 15.0 110 1.90 97 9.14 157 10.3 78 5.63 164 34.7 192 19.7 113 22.4 179 18.9 174 24.2 175 20.4 197 29.8 144 33.8 143 12.2 74 18.1 84 25.5 85 6.93 133 31.9 188 48.8 188 9.12 121 22.8 108 28.5 107 14.2 196
Shiralkar [42]138.2 12.0 169 18.8 169 1.72 39 9.11 155 11.1 142 5.14 131 21.2 154 16.6 64 13.7 111 19.2 178 24.3 176 10.6 93 29.7 138 33.7 138 12.8 98 18.0 82 25.4 81 7.19 146 29.4 175 44.9 175 10.4 149 25.1 189 31.5 189 9.03 176
EPPM w/o HM [86]139.0 10.4 142 16.2 142 2.97 162 8.62 124 11.3 155 2.76 15 29.0 185 27.4 179 22.2 178 16.8 151 22.6 153 10.8 98 25.8 56 29.2 55 12.1 55 20.2 163 28.6 163 6.49 113 29.8 179 45.8 180 18.0 185 24.0 166 30.2 167 8.72 170
UnFlow [127]140.8 13.4 184 21.2 186 2.71 158 8.81 132 10.7 115 6.35 178 18.7 130 18.9 98 14.8 124 14.6 86 19.6 94 7.77 28 31.8 191 36.1 191 15.0 131 22.2 194 31.4 194 7.79 168 24.2 78 37.0 81 7.49 49 28.1 198 33.7 199 11.6 192
Correlation Flow [76]141.0 9.75 118 15.3 125 1.84 88 9.28 164 11.6 173 5.17 132 17.5 115 18.9 98 15.2 131 16.1 138 21.7 144 11.3 112 30.2 155 34.3 157 12.5 92 21.2 182 29.9 180 8.24 177 31.3 187 47.8 187 9.82 141 24.9 185 31.3 188 6.61 14
HBpMotionGpu [43]145.1 12.7 177 19.5 173 2.69 156 9.65 183 11.7 180 5.48 156 20.0 145 23.3 156 17.0 140 17.6 166 23.4 167 10.6 93 30.8 180 35.0 181 25.1 199 20.4 169 28.9 171 7.95 170 22.0 37 33.7 38 7.44 44 23.2 128 29.1 126 8.40 148
LiteFlowNet [138]145.5 12.6 176 19.7 177 2.06 122 8.19 100 10.7 115 3.96 67 20.8 151 26.3 176 15.4 132 26.2 194 35.0 195 12.2 148 30.9 186 35.0 181 14.9 130 20.4 169 28.8 166 6.74 127 28.3 160 43.1 158 7.70 70 22.8 108 28.6 110 8.87 173
2bit-BM-tele [96]146.7 11.1 155 17.2 155 2.34 143 9.40 168 11.7 180 5.36 147 28.5 183 37.1 197 31.0 197 15.7 128 20.8 124 9.18 64 28.6 106 32.5 106 15.0 131 22.0 193 31.1 193 9.53 192 39.1 199 59.9 199 26.9 199 20.8 48 26.1 48 8.11 66
PGAM+LK [55]147.6 11.9 168 18.0 163 7.26 198 9.48 175 10.8 120 7.62 184 31.5 188 39.9 198 31.4 198 19.0 175 23.6 169 16.3 191 29.1 127 33.0 126 12.6 94 18.4 94 26.0 97 6.80 129 25.5 111 39.0 114 14.8 175 22.6 98 28.4 99 8.41 151
Rannacher [23]148.1 11.1 155 17.5 159 1.89 93 9.59 181 11.8 186 5.28 137 24.3 174 18.0 86 20.8 171 15.9 134 21.2 133 11.6 130 30.4 162 34.5 163 12.3 85 19.7 149 27.9 151 7.98 171 29.6 176 45.3 176 9.57 134 24.7 182 31.0 183 8.19 83
OFRF [132]148.7 13.6 185 21.1 185 2.23 139 9.25 162 11.4 160 5.60 160 19.2 134 19.5 111 14.1 116 16.9 154 22.8 160 14.6 174 30.8 180 34.9 179 14.4 119 19.6 145 27.7 145 6.07 68 28.3 160 43.4 162 7.78 77 24.7 182 31.1 185 8.34 127
StereoFlow [44]148.8 14.9 191 22.2 190 3.28 165 10.0 191 12.7 197 4.99 123 16.8 95 18.9 98 12.1 83 15.2 104 20.4 115 10.4 90 33.4 196 37.9 196 20.8 196 23.8 196 33.5 196 8.41 180 25.3 108 38.8 112 7.81 80 23.6 150 29.6 150 8.67 168
IRR-PWC_RVC [180]149.4 15.4 193 24.1 195 2.44 152 9.31 165 12.2 193 4.74 114 19.0 133 22.9 149 13.4 105 29.5 198 39.3 199 8.93 59 30.4 162 34.5 163 15.3 151 21.1 179 29.9 180 6.75 128 28.3 160 43.2 160 7.73 71 22.8 108 28.5 107 8.50 161
SimpleFlow [49]151.2 9.15 82 14.3 86 1.73 41 9.05 147 11.4 160 5.35 146 36.0 196 32.6 194 29.4 196 14.9 95 20.2 109 11.2 111 30.6 176 34.7 174 15.1 136 22.6 195 32.0 195 9.11 189 34.7 193 53.2 194 13.8 171 23.9 162 29.9 157 8.33 124
SPSA-learn [13]153.7 15.1 192 22.9 192 1.93 101 9.08 152 11.0 132 5.42 150 33.0 191 24.8 168 23.8 184 17.6 166 22.4 150 12.1 144 29.3 134 33.2 131 15.1 136 17.8 73 25.1 74 6.73 124 37.7 195 57.7 196 25.5 198 25.4 190 31.8 191 8.33 124
SegOF [10]154.1 11.8 166 18.2 165 5.53 193 8.88 137 11.4 160 4.62 103 31.1 187 20.5 126 23.7 183 25.8 192 34.8 194 18.2 194 30.2 155 34.2 154 15.3 151 19.1 127 27.0 128 7.08 143 32.5 191 49.7 191 16.8 182 22.8 108 28.6 110 8.08 58
HCIC-L [97]160.2 14.3 189 20.9 184 2.86 160 11.2 196 13.3 198 7.62 184 23.9 171 31.6 192 25.6 189 21.0 183 28.2 184 14.8 180 25.6 53 29.0 53 12.2 74 24.0 197 33.9 197 10.5 195 30.5 185 46.8 185 18.5 186 23.3 135 29.2 133 7.37 42
IIOF-NLDP [129]161.5 10.2 136 15.8 134 2.10 129 9.06 148 11.2 147 5.60 160 20.6 150 24.8 168 16.9 139 16.7 149 22.6 153 14.6 174 30.4 162 34.5 163 20.8 196 20.4 169 28.8 166 8.81 186 37.7 195 57.6 195 16.8 182 24.9 185 31.2 186 8.26 103
WOLF_ROB [144]161.7 16.7 197 24.7 196 3.17 163 9.76 185 11.8 186 5.28 137 22.6 160 24.5 166 19.4 160 21.5 185 28.4 185 8.71 49 30.8 180 35.0 181 15.2 145 20.1 159 28.3 157 7.04 140 32.0 190 48.8 188 8.28 105 25.4 190 31.8 191 8.20 85
WRT [146]169.2 10.3 138 15.8 134 2.35 144 9.41 170 10.6 103 9.35 189 35.2 194 27.6 180 26.8 191 21.2 184 21.4 139 13.6 167 31.3 189 35.6 189 13.7 108 21.5 187 30.4 187 8.56 182 39.0 198 59.6 198 16.0 178 26.1 196 32.6 197 8.31 118
GroupFlow [9]170.8 15.6 194 23.3 193 3.31 166 9.20 159 11.4 160 6.26 176 30.9 186 22.4 140 18.9 157 25.4 191 30.0 188 21.2 198 32.4 193 36.7 192 15.3 151 20.9 177 29.4 175 7.71 166 29.9 180 45.5 177 9.50 132 23.3 135 29.1 126 10.6 186
Pyramid LK [2]178.5 14.0 187 21.7 188 4.34 180 13.7 197 11.5 170 9.94 194 37.6 197 26.8 178 24.6 187 25.9 193 29.3 186 18.7 195 35.0 197 39.7 197 13.3 103 19.9 155 24.8 66 9.57 193 33.3 192 51.1 192 10.7 151 26.0 195 32.4 196 13.0 194
Periodicity [79]195.7 18.1 198 27.0 198 6.22 195 17.4 198 12.4 196 10.2 195 35.2 194 30.7 191 27.8 192 24.1 189 31.6 191 17.5 193 37.6 199 42.6 199 18.8 193 27.7 198 39.3 198 11.2 198 38.6 197 58.9 197 22.9 196 27.3 197 33.2 198 14.3 197
AVG_FLOW_ROB [137]196.6 31.2 199 31.0 199 11.6 199 19.8 199 21.4 199 12.0 199 34.9 193 32.0 193 28.1 193 31.2 199 36.2 196 23.9 199 36.4 198 41.0 198 16.9 191 39.5 199 55.0 199 16.9 199 36.8 194 52.3 193 20.8 192 30.2 199 31.8 191 15.5 199
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.