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        
A99
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 8.04 1 11.2 1 2.38 1 9.66 2 13.2 2 2.94 2 4.36 1 10.0 6 2.38 3 11.4 2 15.2 2 6.68 2 27.8 2 34.0 2 8.35 13 15.3 3 28.5 4 4.12 4 22.1 3 47.5 4 3.65 9 19.6 2 27.7 3 2.94 1
SoftSplat [169]5.7 8.35 4 11.9 4 2.65 12 11.1 5 15.7 8 3.00 3 4.36 1 8.76 3 2.16 1 11.2 1 15.5 3 6.68 2 31.2 19 39.2 19 8.29 12 16.5 7 29.8 5 4.12 4 23.6 5 50.2 5 3.56 5 19.7 3 28.6 4 2.94 1
EAFI [186]8.3 8.66 8 12.8 7 2.38 1 9.35 1 12.2 1 2.89 1 5.00 5 8.04 1 2.16 1 11.4 2 15.0 1 6.35 1 36.5 27 44.9 27 8.60 22 20.0 20 36.3 21 4.08 1 25.1 15 56.7 19 3.51 1 21.6 10 29.6 6 2.94 1
DistillNet [184]10.5 8.35 4 12.2 5 2.52 6 10.1 3 14.0 3 3.56 11 4.83 3 9.15 5 2.38 3 12.4 6 16.9 6 6.83 4 30.4 12 37.2 11 8.81 28 20.4 24 36.3 21 4.20 7 26.9 20 56.5 18 3.70 15 22.4 12 31.2 10 3.11 14
SepConv++ [185]11.7 9.09 19 15.7 25 2.71 16 11.7 9 16.4 10 3.42 4 10.7 33 11.0 12 3.00 17 14.7 15 21.6 17 7.51 45 29.7 8 36.8 8 7.79 1 14.1 2 27.8 3 4.08 1 22.2 4 47.1 3 3.51 1 20.3 5 34.4 21 2.94 1
FGME [158]12.8 8.37 6 12.8 7 2.38 1 13.8 30 18.1 21 4.65 129 6.35 7 10.0 6 3.00 17 12.1 5 16.3 5 7.14 7 28.2 3 35.1 3 8.10 4 15.5 5 31.7 8 4.24 14 19.6 2 44.9 2 3.56 5 20.4 6 29.6 6 3.00 7
IFRNet [193]13.8 8.19 2 11.4 2 2.65 12 10.6 4 14.7 4 3.87 71 4.83 3 8.68 2 2.38 3 11.6 4 16.0 4 7.85 116 28.6 4 35.1 3 8.60 22 18.4 11 33.5 12 4.24 14 24.1 10 53.2 7 3.51 1 21.1 9 29.2 5 3.00 7
BMBC [171]16.7 9.11 20 12.8 7 2.71 16 11.8 10 16.8 12 3.56 11 9.56 21 14.3 29 3.37 118 13.1 9 18.7 8 7.00 5 30.1 10 37.1 10 9.35 34 16.3 6 29.8 5 4.24 14 23.7 6 50.9 6 3.70 15 20.9 7 30.1 8 3.11 14
STAR-Net [164]17.3 8.39 7 12.4 6 2.71 16 14.7 59 20.0 38 3.92 79 10.2 26 10.4 10 2.94 15 14.1 12 19.8 11 7.05 6 28.6 4 35.2 5 8.35 13 19.0 13 33.0 11 4.20 7 24.3 11 54.7 15 3.70 15 21.9 11 31.8 11 3.11 14
EDSC [173]17.3 9.13 21 15.0 19 2.52 6 12.5 12 17.3 14 4.08 89 9.35 20 12.3 17 2.94 15 14.7 15 21.2 16 7.33 12 30.4 12 37.8 16 8.27 9 19.5 17 38.5 28 4.20 7 23.8 7 53.2 7 3.56 5 23.4 16 36.9 29 3.00 7
AdaCoF [165]22.0 9.18 22 15.6 24 2.83 52 12.2 11 16.6 11 3.87 71 10.3 27 11.4 13 3.00 17 17.1 32 22.6 22 7.72 102 34.7 24 43.0 24 8.35 13 16.9 9 30.9 7 4.12 4 25.0 13 54.0 10 3.51 1 21.0 8 30.7 9 2.94 1
CtxSyn [134]22.9 9.38 23 14.7 17 2.58 10 11.5 7 16.1 9 3.65 35 9.04 19 12.7 20 3.00 17 12.6 8 19.2 10 7.33 12 38.7 31 47.5 28 9.56 35 22.9 30 38.0 27 4.76 30 31.6 34 64.3 32 3.92 29 24.8 31 36.2 27 3.37 28
IDIAL [192]24.8 8.66 8 13.4 12 2.52 6 13.0 19 18.4 23 4.08 89 7.35 9 10.3 8 2.71 6 14.2 14 20.7 13 7.14 7 30.3 11 38.2 17 8.60 22 18.7 12 32.6 10 4.20 7 25.9 17 55.6 17 4.08 78 22.5 13 33.3 18 3.65 159
DSepConv [162]25.8 9.49 25 17.4 33 2.71 16 13.2 24 17.8 20 4.73 134 9.68 22 12.7 20 3.00 17 18.3 63 24.5 31 7.33 12 30.4 12 37.5 13 8.49 17 20.0 20 36.8 23 4.24 14 24.0 8 54.4 11 3.65 9 24.5 28 37.5 33 3.11 14
STSR [170]28.7 9.49 25 14.9 18 2.65 12 11.2 6 15.3 5 4.20 99 8.68 15 12.5 19 2.71 6 13.3 10 20.0 12 8.19 147 38.8 32 48.0 32 8.68 25 23.3 33 40.7 32 4.43 23 30.4 31 63.9 30 3.70 15 24.5 28 34.3 20 3.11 14
MV_VFI [183]28.9 8.98 14 15.4 23 2.83 52 12.9 17 17.4 15 5.07 147 8.68 15 12.7 20 2.71 6 15.8 21 23.3 26 8.60 162 30.5 15 37.4 12 8.23 7 19.1 14 34.9 17 4.24 14 28.5 24 59.7 24 3.65 9 23.6 18 33.0 14 3.00 7
DAIN [152]29.4 9.06 18 15.1 20 2.83 52 13.0 19 17.6 16 5.03 146 8.35 11 12.4 18 2.71 6 15.7 20 22.7 24 8.68 165 30.7 17 37.6 15 8.27 9 19.1 14 34.6 14 4.32 22 28.7 27 59.7 24 3.65 9 23.6 18 33.1 15 3.00 7
TC-GAN [166]29.5 9.04 16 15.2 22 2.83 52 12.9 17 17.6 16 5.07 147 8.68 15 12.7 20 2.71 6 15.8 21 23.2 25 8.76 169 30.5 15 37.5 13 8.23 7 19.1 14 34.7 16 4.24 14 28.5 24 59.8 26 3.65 9 23.7 21 33.1 15 3.00 7
ProBoost-Net [191]32.0 8.76 12 14.4 14 2.38 1 15.9 90 20.4 47 5.35 160 8.00 10 11.7 14 2.71 6 14.1 12 21.7 18 7.85 116 35.1 25 43.3 25 8.76 26 20.7 25 37.9 26 4.51 26 25.3 16 57.6 21 3.70 15 24.0 24 36.0 26 3.11 14
MEMC-Net+ [160]33.4 8.83 13 14.0 13 2.94 94 13.2 24 17.7 18 5.10 156 10.7 33 13.3 25 3.00 17 15.5 19 22.5 21 8.76 169 33.9 23 41.7 22 8.58 21 19.6 18 34.2 13 4.20 7 28.2 23 58.5 22 3.65 9 23.6 18 33.2 17 3.00 7
MAF-net [163]33.9 8.70 10 14.4 14 2.38 1 15.3 72 19.6 32 5.07 147 8.76 18 12.7 20 3.00 17 16.2 23 21.9 19 8.12 141 38.1 28 47.5 28 8.89 30 22.7 29 41.4 34 4.51 26 27.1 21 58.6 23 3.70 15 23.8 22 33.8 19 3.16 24
FRUCnet [153]34.8 9.49 25 16.1 28 3.42 174 13.1 23 17.7 18 4.55 121 9.68 22 12.0 16 3.56 141 15.3 18 21.9 19 7.59 69 31.6 21 39.4 20 7.94 2 18.3 10 34.6 14 4.24 14 25.0 13 54.4 11 3.70 15 22.8 14 32.7 13 3.11 14
CyclicGen [149]35.5 8.29 3 11.7 3 3.46 176 11.6 8 15.3 5 5.94 175 9.68 22 15.0 31 3.42 136 16.7 26 21.0 14 10.3 182 29.8 9 37.0 9 8.04 3 12.4 1 21.2 1 4.65 28 18.4 1 39.9 1 3.70 15 16.6 1 22.9 1 2.94 1
OFRI [154]35.5 8.70 10 12.8 7 3.00 112 13.8 30 18.7 26 4.83 141 7.00 8 9.04 4 2.71 6 13.4 11 18.7 8 8.74 168 31.1 18 38.2 17 8.50 18 22.0 27 37.5 24 4.43 23 28.5 24 61.2 27 4.08 78 23.0 15 32.6 12 3.42 38
ADC [161]36.9 9.68 30 16.1 28 2.94 94 12.7 13 17.1 13 4.43 114 12.0 104 13.4 26 3.00 17 19.3 86 24.9 32 8.04 133 33.7 22 41.9 23 8.27 9 20.0 20 35.9 20 4.20 7 24.0 8 53.9 9 3.56 5 24.4 27 37.3 31 3.11 14
PMMST [112]39.0 11.2 42 21.1 40 2.71 16 13.8 30 19.7 34 3.65 35 10.3 27 19.2 38 2.71 6 16.8 28 30.8 54 7.53 52 41.1 38 51.1 40 10.0 50 24.6 35 43.0 39 4.93 50 34.2 51 70.9 51 4.04 37 28.8 46 45.4 59 3.42 38
MDP-Flow2 [68]39.6 11.0 35 20.7 38 2.71 16 13.9 36 19.9 37 3.46 6 10.3 27 20.3 46 3.00 17 16.7 26 30.0 45 7.35 22 41.0 37 50.7 37 10.1 64 27.1 75 44.9 55 4.97 59 33.6 41 70.1 44 3.92 29 29.2 50 47.0 71 3.42 38
GDCN [172]40.5 9.04 16 15.1 20 2.65 12 16.0 94 20.4 47 4.55 121 8.35 11 11.7 14 3.37 118 21.2 129 23.7 27 8.16 144 31.3 20 39.5 21 8.16 5 19.8 19 35.3 19 4.43 23 24.4 12 54.7 15 3.79 24 23.9 23 35.8 24 3.11 14
DAI [168]40.7 9.42 24 13.1 11 3.37 165 14.7 59 19.1 29 8.35 195 5.29 6 10.3 8 2.71 6 12.4 6 17.6 7 12.6 191 36.4 26 44.6 26 8.50 18 21.7 26 37.7 25 4.24 14 28.8 28 64.1 31 3.70 15 24.1 25 34.7 22 3.11 14
FeFlow [167]41.0 9.00 15 14.6 16 2.58 10 14.4 48 19.0 28 5.74 168 8.35 11 10.7 11 3.11 109 15.2 17 21.1 15 8.91 172 29.5 7 35.8 6 8.54 20 20.2 23 35.2 18 4.20 7 26.1 18 54.4 11 4.08 78 24.2 26 39.3 34 3.56 115
CoT-AMFlow [174]43.6 11.1 39 21.0 39 2.71 16 14.0 37 20.0 38 3.56 11 10.7 33 24.0 89 3.00 17 16.8 28 30.0 45 7.35 22 41.4 41 51.1 40 10.1 64 26.7 67 45.3 58 4.97 59 34.0 46 70.0 43 4.04 37 29.5 59 47.8 81 3.42 38
MPRN [151]45.5 10.0 32 16.4 31 2.71 16 15.9 90 19.8 36 4.24 102 11.7 88 21.7 62 3.46 137 17.5 41 24.3 29 7.62 76 38.3 29 47.6 30 8.98 31 22.6 28 39.0 30 4.76 30 30.9 33 64.5 33 3.83 25 24.9 32 36.8 28 3.16 24
SuperSlomo [130]48.5 9.66 29 16.1 28 3.37 165 15.4 74 20.4 47 6.06 179 8.43 14 14.4 30 3.00 17 17.1 32 23.8 28 8.58 160 38.5 30 47.8 31 8.76 26 23.1 32 40.8 33 4.80 34 30.2 30 62.5 28 3.87 26 25.2 33 37.4 32 3.32 26
NNF-Local [75]50.8 11.4 48 21.6 43 2.71 16 12.8 14 18.4 23 3.56 11 10.4 31 20.0 44 3.00 17 19.8 99 37.3 135 7.35 22 41.5 44 51.4 42 10.0 50 28.2 108 47.3 79 5.07 93 34.5 54 71.9 66 4.04 37 29.1 49 46.1 65 3.37 28
TOF-M [150]53.8 10.2 33 16.8 32 2.71 16 15.9 90 20.5 53 5.74 168 11.1 61 14.0 28 3.70 142 17.7 46 24.3 29 7.94 125 39.4 33 49.1 33 9.11 33 23.0 31 38.8 29 4.80 34 29.5 29 63.4 29 4.04 37 25.8 34 37.1 30 3.56 115
NN-field [71]54.3 11.5 56 22.9 56 2.71 16 13.0 19 18.6 25 3.42 4 12.3 125 19.7 39 3.00 17 21.1 128 39.8 154 7.44 37 41.4 41 51.4 42 10.0 50 27.5 86 46.4 68 4.97 59 33.8 44 71.0 54 4.04 37 29.3 52 46.2 66 3.37 28
SepConv-v1 [125]54.9 9.68 30 19.1 34 2.52 6 15.4 74 20.1 42 5.26 158 11.0 45 16.7 33 3.87 158 20.4 115 26.8 33 9.59 181 41.9 47 52.5 54 9.00 32 24.7 36 42.4 36 4.69 29 30.7 32 67.4 34 3.92 29 24.7 30 35.8 24 3.32 26
MS-PFT [159]55.3 9.49 25 15.8 26 2.71 16 14.2 42 20.3 44 4.55 121 11.9 102 13.7 27 5.00 173 16.8 28 22.6 22 9.20 179 29.3 6 35.9 7 8.87 29 16.8 8 32.2 9 4.80 34 27.4 22 56.8 20 4.69 184 23.4 16 35.2 23 3.70 165
NNF-EAC [101]61.6 11.5 56 21.7 44 3.11 130 14.5 56 21.0 67 3.70 38 12.3 125 22.6 72 3.00 17 17.7 46 32.4 75 7.55 60 43.2 78 55.1 86 10.1 64 25.1 39 43.8 42 4.90 43 34.0 46 70.5 47 4.08 78 29.4 55 47.5 77 3.42 38
FLAVR [188]62.7 11.7 69 15.8 26 3.00 112 12.8 14 15.6 7 4.65 129 11.3 65 15.0 31 4.00 160 31.5 185 36.5 127 13.5 192 27.7 1 33.7 1 8.35 13 15.3 3 26.0 2 4.08 1 26.5 19 54.4 11 4.24 165 20.0 4 27.5 2 3.70 165
PH-Flow [99]63.8 11.9 90 25.7 103 2.83 52 13.3 26 19.7 34 3.56 11 10.7 33 22.7 74 3.00 17 16.5 25 30.2 47 7.33 12 42.3 55 52.1 50 10.1 64 28.7 126 50.9 141 5.20 123 35.6 79 77.0 108 4.04 37 29.6 63 47.0 71 3.51 91
DeepFlow [85]65.5 11.3 46 24.2 73 3.00 112 16.6 111 23.0 115 4.32 106 11.0 45 20.3 46 3.00 17 19.3 86 28.1 37 7.59 69 42.7 63 54.5 72 10.2 89 25.2 41 44.1 43 5.00 85 32.9 36 68.2 35 4.04 37 28.4 42 44.6 50 3.56 115
DeepFlow2 [106]65.5 11.4 48 23.5 60 3.00 112 16.7 112 23.0 115 4.04 84 11.0 45 20.3 46 3.00 17 19.0 81 29.8 43 7.53 52 42.7 63 54.0 65 10.3 97 25.0 37 43.0 39 4.93 50 35.2 71 73.8 82 4.04 37 28.9 47 44.9 54 3.56 115
CombBMOF [111]65.9 12.0 97 24.3 74 2.83 52 14.3 46 20.6 56 3.56 11 11.3 65 25.7 103 3.00 17 20.3 113 34.9 105 7.55 60 43.2 78 54.0 65 10.1 64 26.4 58 47.7 87 4.90 43 36.2 102 71.4 58 4.08 78 29.5 59 45.7 62 3.37 28
GMFlow_RVC [196]66.2 12.7 150 31.3 161 2.71 16 13.8 30 20.2 43 3.46 6 10.7 33 21.0 55 3.00 17 19.0 81 37.3 135 7.33 12 43.6 87 54.3 69 10.2 89 28.3 111 54.5 171 4.83 37 34.0 46 71.7 62 4.04 37 29.4 55 44.5 47 3.42 38
DF-Auto [113]69.0 10.9 34 19.2 35 3.11 130 17.2 125 23.4 127 4.43 114 10.4 31 20.6 54 3.00 17 18.1 59 29.7 40 7.55 60 41.4 41 52.1 50 10.0 50 26.2 53 47.2 76 4.97 59 35.2 71 79.3 124 4.08 78 29.6 63 44.7 51 3.56 115
LME [70]70.0 11.4 48 22.0 49 2.71 16 15.1 68 21.8 80 3.87 71 11.3 65 36.0 179 3.00 17 17.4 36 32.0 72 7.48 41 44.5 108 57.0 106 11.4 187 27.6 88 47.2 76 4.97 59 33.6 41 69.7 39 4.04 37 30.0 70 48.6 90 3.42 38
IROF++ [58]71.6 11.9 90 24.1 71 2.83 52 14.7 59 21.3 69 3.56 11 12.1 121 29.0 136 3.00 17 16.3 24 27.9 35 7.35 22 43.9 94 56.0 95 11.1 144 26.4 58 47.0 75 4.93 50 34.5 54 72.3 68 4.08 78 30.3 80 49.3 100 3.56 115
MS_RAFT+_RVC [195]71.7 12.3 130 28.1 134 2.83 52 14.2 42 20.5 53 3.56 11 10.0 25 19.7 39 3.00 17 17.5 41 31.5 63 7.35 22 45.9 146 58.6 139 11.2 153 25.4 43 44.4 48 4.76 30 32.7 35 69.8 41 4.04 37 44.0 191 64.5 190 3.42 38
WLIF-Flow [91]72.0 11.5 56 22.1 51 2.83 52 15.2 69 21.6 76 3.79 61 11.3 65 26.4 113 3.00 17 17.4 36 30.3 49 7.59 69 42.5 59 53.5 60 10.4 107 29.0 134 51.1 144 5.29 142 34.8 60 69.7 39 4.04 37 30.0 70 48.4 86 3.46 76
CBF [12]72.1 11.0 35 19.8 36 3.00 112 17.1 120 22.9 111 4.24 102 12.0 104 19.0 35 3.00 17 17.8 52 28.0 36 7.85 116 40.6 36 49.9 35 9.97 42 26.2 53 44.6 50 4.97 59 36.3 104 76.3 100 4.12 137 27.9 37 41.2 37 3.70 165
FMOF [92]72.2 12.2 121 24.5 83 2.94 94 14.0 37 20.0 38 3.56 11 12.3 125 27.7 123 3.00 17 19.8 99 35.4 110 7.70 95 42.4 57 52.1 50 10.1 64 28.1 104 49.1 104 4.93 50 34.6 57 72.7 73 3.87 26 30.2 76 47.6 80 3.42 38
Aniso. Huber-L1 [22]72.9 11.4 48 21.7 44 3.11 130 19.7 166 24.7 164 4.55 121 12.0 104 19.7 39 3.11 109 18.4 66 29.8 43 7.55 60 42.5 59 54.4 71 9.98 47 25.2 41 42.2 35 4.83 37 35.6 79 71.5 59 4.04 37 27.9 37 42.0 39 3.56 115
CLG-TV [48]75.4 11.1 39 21.8 47 3.11 130 18.8 148 24.0 144 4.43 114 11.3 65 20.0 44 3.70 142 18.6 72 28.9 38 7.72 102 42.8 66 55.0 85 10.0 50 25.0 37 42.9 38 4.93 50 36.0 94 71.6 60 4.04 37 29.0 48 44.0 45 3.56 115
IROF-TV [53]75.9 11.7 69 24.7 90 3.00 112 15.5 78 22.0 91 3.70 38 11.0 45 23.7 84 3.00 17 17.3 34 31.3 58 7.57 68 43.8 92 56.0 95 11.2 153 27.6 88 48.4 95 4.97 59 35.9 92 74.5 91 4.08 78 28.0 39 42.6 41 3.56 115
PRAFlow_RVC [177]76.1 12.6 147 29.8 150 2.71 16 14.7 59 20.4 47 3.70 38 10.7 33 21.7 62 3.00 17 19.2 84 34.7 101 7.75 107 41.7 45 51.6 45 10.2 89 27.1 75 49.6 108 4.93 50 33.1 37 68.9 38 4.04 37 34.5 166 54.9 161 3.56 115
nLayers [57]76.2 11.8 78 22.9 56 2.83 52 14.1 40 20.4 47 3.56 11 11.0 45 19.7 39 3.00 17 18.3 63 34.2 97 7.39 31 46.7 168 60.1 163 11.0 137 27.9 96 50.1 114 5.20 123 35.5 77 72.6 72 4.08 78 30.8 86 49.3 100 3.42 38
RAFT-it+_RVC [198]76.3 12.7 150 36.8 177 2.71 16 13.8 30 20.3 44 3.46 6 10.7 33 24.4 96 3.00 17 20.8 124 41.9 165 7.33 12 42.3 55 52.0 48 10.1 64 29.0 134 52.8 162 8.39 198 33.1 37 68.5 36 4.04 37 30.5 83 46.9 70 3.42 38
Brox et al. [5]76.6 11.4 48 24.9 95 2.94 94 15.9 90 22.2 95 4.04 84 11.3 65 21.0 55 3.37 118 18.4 66 27.0 34 7.59 69 42.2 53 53.3 58 10.0 50 28.2 108 51.5 149 5.00 85 36.8 108 88.0 157 4.04 37 28.4 42 42.3 40 3.42 38
ALD-Flow [66]77.2 12.0 97 28.4 139 3.11 130 16.3 102 22.8 107 3.83 66 11.0 45 21.7 62 3.00 17 17.9 55 33.6 88 7.39 31 43.4 84 54.6 76 10.8 129 25.8 47 44.8 54 5.00 85 34.1 49 70.4 46 4.04 37 31.9 118 50.3 112 3.46 76
HCFN [157]78.4 12.0 97 27.4 126 2.71 16 15.5 78 21.9 87 3.70 38 11.3 65 23.9 88 3.00 17 17.9 55 34.4 98 7.33 12 43.1 74 53.9 64 10.2 89 26.4 58 46.2 65 6.68 194 37.4 116 76.8 105 4.08 78 31.6 108 50.5 115 3.42 38
Layers++ [37]78.5 11.4 48 21.7 44 2.94 94 12.8 14 18.2 22 3.46 6 11.0 45 26.7 116 3.00 17 17.7 46 32.9 80 7.53 52 46.6 166 60.9 176 10.6 121 30.9 177 60.2 187 5.00 85 34.9 66 72.7 73 3.87 26 29.9 69 47.5 77 3.46 76
MDP-Flow [26]78.6 11.2 42 21.2 41 2.71 16 14.2 42 20.5 53 3.70 38 10.7 33 19.0 35 3.00 17 19.7 97 32.4 75 7.70 95 44.2 99 57.0 106 11.2 153 30.0 161 51.4 148 5.51 173 36.1 99 72.9 76 4.08 78 30.8 86 48.4 86 3.42 38
JOF [136]79.2 12.0 97 23.6 62 3.11 130 14.0 37 20.0 38 3.70 38 11.0 45 23.8 87 3.00 17 18.1 59 31.5 63 7.35 22 44.7 111 57.6 115 11.3 174 29.5 151 50.1 114 5.07 93 34.5 54 71.6 60 4.04 37 31.2 95 50.3 112 3.51 91
RAFT-it [194]80.8 12.6 147 36.5 173 2.71 16 13.4 28 19.5 31 3.46 6 10.3 27 22.6 72 3.00 17 19.3 86 37.0 130 7.26 10 41.7 45 51.4 42 10.1 64 30.0 161 51.1 144 7.44 197 33.2 39 70.9 51 3.92 29 46.5 194 66.7 193 3.42 38
COFM [59]82.5 11.8 78 24.3 74 2.94 94 14.5 56 20.9 64 3.65 35 11.0 45 26.4 113 3.00 17 17.4 36 32.3 73 7.35 22 44.2 99 55.1 86 10.1 64 30.0 161 54.4 170 5.20 123 35.8 87 79.3 124 4.08 78 31.2 95 48.8 94 3.51 91
p-harmonic [29]82.5 11.4 48 23.5 60 2.83 52 19.1 153 24.3 153 4.80 138 11.3 65 22.0 66 3.70 142 20.9 126 31.7 66 7.62 76 42.6 62 54.2 68 10.1 64 25.7 46 43.5 41 5.07 93 36.1 99 71.8 63 4.08 78 29.6 63 46.5 67 3.51 91
LDOF [28]82.7 11.4 48 22.5 53 3.56 179 16.1 96 21.4 74 6.35 184 12.0 104 20.3 46 3.70 142 19.0 81 29.7 40 7.94 125 41.2 39 50.9 38 10.1 64 26.8 68 50.2 117 4.90 43 34.8 60 80.2 128 4.08 78 29.4 55 44.5 47 3.46 76
ProbFlowFields [126]83.0 11.6 61 25.4 99 2.83 52 14.4 48 21.1 68 3.56 11 10.7 33 23.7 84 3.00 17 18.4 66 33.4 85 7.59 69 46.2 154 59.2 148 11.2 153 28.5 122 50.7 135 5.32 148 34.7 58 76.9 106 4.08 78 29.4 55 46.5 67 3.46 76
Second-order prior [8]83.2 11.3 46 22.0 49 3.11 130 19.0 152 24.2 151 4.32 106 13.3 142 27.7 123 3.70 142 18.8 76 31.6 65 7.51 45 42.9 69 54.7 79 10.0 50 26.2 53 45.0 56 4.97 59 35.6 79 71.2 55 4.04 37 29.5 59 45.4 59 3.56 115
VCN_RVC [178]83.4 13.1 164 36.7 175 2.71 16 14.4 48 20.6 56 3.56 11 12.1 121 29.5 145 3.00 17 20.8 124 45.5 176 7.53 52 44.2 99 55.1 86 10.1 64 26.4 58 46.9 73 4.83 37 35.2 71 73.6 81 4.04 37 32.4 133 50.7 120 3.42 38
FlowFields [108]83.8 11.8 78 25.6 102 2.83 52 14.4 48 20.9 64 3.56 11 11.3 65 24.3 94 3.00 17 20.0 106 38.1 142 7.51 45 43.6 87 54.5 72 11.0 137 28.2 108 50.7 135 5.16 117 34.8 60 75.1 95 4.04 37 32.0 124 52.0 140 3.46 76
SIOF [67]84.0 11.7 69 23.1 58 3.11 130 19.4 160 24.8 167 4.76 135 11.3 65 25.7 103 3.11 109 18.4 66 31.4 60 8.04 133 40.3 35 50.3 36 9.95 40 25.8 47 45.3 58 4.97 59 33.9 45 71.2 55 4.08 78 30.0 70 47.4 74 3.70 165
EAI-Flow [147]85.0 12.5 143 26.8 118 2.83 52 15.8 88 21.8 80 4.20 99 12.3 125 30.4 156 3.00 17 19.3 86 34.0 94 7.39 31 44.9 118 57.1 110 11.1 144 26.1 52 46.0 62 5.00 85 36.0 94 72.4 70 4.08 78 29.3 52 45.2 57 3.37 28
Local-TV-L1 [65]85.2 11.2 42 21.5 42 3.56 179 19.6 164 24.4 156 5.57 167 11.0 45 19.1 37 3.00 17 18.3 63 30.4 52 7.87 122 42.8 66 54.5 72 10.2 89 26.2 53 44.7 51 5.45 161 34.2 51 76.1 98 4.08 78 28.0 39 42.8 43 3.65 159
TV-L1-MCT [64]87.1 12.4 138 24.7 90 2.83 52 16.4 103 23.1 117 3.83 66 11.9 102 32.7 166 3.00 17 17.6 43 31.7 66 7.53 52 47.0 177 61.2 177 11.0 137 25.5 44 44.7 51 4.97 59 36.0 94 80.7 132 4.04 37 28.4 42 44.8 53 3.46 76
UnDAF [187]87.3 12.7 150 29.8 150 2.71 16 15.6 82 22.1 92 3.70 38 13.0 138 34.3 173 3.00 17 24.8 167 43.3 172 7.55 60 42.0 48 52.0 48 10.0 50 26.6 65 44.3 47 5.07 93 37.2 115 73.5 80 4.08 78 30.8 86 48.7 93 3.42 38
HAST [107]87.8 11.7 69 23.6 62 2.94 94 13.8 30 19.6 32 3.56 11 12.0 104 31.7 162 3.00 17 17.8 52 31.7 66 7.14 7 45.3 126 57.0 106 9.97 42 33.7 190 62.8 193 5.10 111 38.4 132 88.4 159 4.04 37 33.0 145 51.0 122 3.42 38
Sparse-NonSparse [56]88.2 12.0 97 24.3 74 2.83 52 15.0 66 21.3 69 3.56 11 11.7 88 29.0 136 3.00 17 17.6 43 29.7 40 7.39 31 45.7 137 59.3 149 11.0 137 28.8 127 48.7 100 5.07 93 38.6 137 90.1 168 4.04 37 32.4 133 51.8 136 3.42 38
SegFlow [156]88.8 11.9 90 28.2 136 2.83 52 14.4 48 20.6 56 3.70 38 11.3 65 22.4 70 3.00 17 20.4 115 42.0 166 7.62 76 45.9 146 58.7 143 11.2 153 27.2 77 46.8 72 5.23 131 35.1 70 70.8 49 4.08 78 30.8 86 50.1 106 3.51 91
RAFT-TF_RVC [179]88.9 12.9 157 33.5 167 2.71 16 14.4 48 20.7 61 3.56 11 10.7 33 25.7 103 3.00 17 19.5 93 36.1 120 7.62 76 42.8 66 52.7 55 10.0 50 29.7 154 56.4 176 6.81 196 34.1 49 73.2 77 3.92 29 37.5 175 59.3 177 3.37 28
CPM-Flow [114]90.0 11.8 78 27.3 122 2.83 52 14.4 48 20.4 47 3.70 38 11.7 88 24.0 89 3.00 17 21.4 138 40.1 157 7.77 108 45.5 132 58.1 126 11.2 153 26.6 65 48.0 91 5.07 93 36.0 94 72.3 68 4.04 37 30.9 91 50.4 114 3.56 115
FlowFields+ [128]90.2 11.8 78 26.1 113 2.71 16 14.1 40 20.6 56 3.70 38 11.2 63 24.8 99 3.00 17 20.1 108 40.2 159 7.53 52 45.5 132 58.0 123 11.2 153 28.6 125 50.6 130 5.20 123 35.6 79 77.5 113 4.04 37 32.2 128 52.5 145 3.42 38
OAR-Flow [123]90.4 12.0 97 24.9 95 3.00 112 16.4 103 22.4 98 4.08 89 11.0 45 20.5 53 3.00 17 17.4 36 33.6 88 7.33 12 46.2 154 60.0 162 11.3 174 27.0 71 47.6 84 5.23 131 37.6 119 74.0 85 4.08 78 31.0 93 49.2 98 3.46 76
AGIF+OF [84]91.0 12.2 121 24.3 74 2.71 16 15.2 69 21.8 80 3.70 38 11.7 88 27.7 123 3.00 17 18.0 57 33.0 82 7.55 60 45.8 141 58.8 145 11.2 153 30.0 161 53.4 164 5.07 93 35.4 74 74.8 93 3.92 29 32.2 128 52.6 149 3.37 28
ComponentFusion [94]91.0 12.0 97 29.6 148 2.71 16 14.5 56 21.3 69 3.56 11 11.0 45 22.0 66 3.00 17 18.8 76 36.2 125 7.33 12 45.5 132 58.2 132 10.7 126 27.2 77 46.3 66 4.97 59 40.5 164 93.3 178 4.12 137 34.4 163 58.3 175 3.42 38
2DHMM-SAS [90]91.8 12.2 121 24.5 83 2.83 52 17.9 135 24.1 148 3.87 71 12.0 104 28.7 133 3.00 17 17.3 34 31.4 60 7.51 45 45.1 122 58.2 132 11.2 153 27.9 96 49.0 102 4.83 37 37.0 110 76.1 98 4.08 78 31.9 118 50.5 115 3.42 38
BlockOverlap [61]92.9 11.1 39 20.1 37 3.56 179 19.3 157 23.7 136 6.16 180 11.3 65 20.4 52 3.70 142 18.4 66 29.6 39 8.72 166 43.1 74 54.5 72 10.2 89 27.4 83 48.6 98 5.35 155 34.8 60 72.8 75 4.08 78 27.2 36 40.9 36 3.56 115
TC/T-Flow [77]93.9 12.4 138 26.4 115 2.83 52 16.5 109 23.1 117 3.83 66 11.0 45 22.4 70 3.00 17 18.9 78 34.5 99 7.33 12 45.5 132 58.1 126 11.4 187 27.3 82 47.6 84 4.93 50 41.1 167 80.4 130 4.20 154 30.9 91 49.7 104 3.37 28
Modified CLG [34]94.5 11.0 35 21.9 48 3.11 130 19.6 164 23.9 140 5.94 175 12.4 131 26.3 110 3.87 158 19.8 99 30.8 54 8.12 141 42.1 50 52.9 56 10.1 64 27.0 71 48.1 93 5.23 131 34.7 58 70.8 49 4.08 78 29.5 59 45.3 58 3.56 115
DPOF [18]94.5 12.3 130 29.4 146 3.11 130 13.3 26 19.1 29 3.56 11 15.7 159 25.2 101 3.70 142 19.4 91 37.5 138 7.59 69 43.1 74 54.6 76 10.0 50 29.1 140 49.7 109 4.90 43 36.6 106 77.0 108 4.08 78 31.5 106 50.5 115 3.51 91
F-TV-L1 [15]94.8 12.0 97 26.5 116 3.56 179 19.2 155 24.7 164 4.83 141 11.7 88 21.5 60 4.00 160 19.3 86 32.7 78 7.68 88 43.1 74 55.3 90 9.83 36 25.1 39 42.8 37 5.07 93 34.8 60 74.0 85 4.16 147 28.5 45 42.7 42 3.56 115
AdaConv-v1 [124]94.8 15.0 185 28.2 136 3.70 183 17.6 132 20.7 61 7.68 192 17.4 170 22.0 66 7.00 187 27.5 176 33.7 92 17.0 194 39.9 34 49.8 34 8.19 6 23.8 34 39.5 31 4.76 30 34.2 51 68.5 36 4.12 137 26.9 35 39.5 35 3.42 38
PMF [73]95.5 12.2 121 25.9 107 2.71 16 15.4 74 21.8 80 3.56 11 12.7 133 35.7 177 3.00 17 20.2 111 35.9 117 7.51 45 44.4 106 54.9 83 10.1 64 28.4 114 50.5 128 5.32 148 37.9 125 81.1 135 4.04 37 34.2 160 54.1 156 3.37 28
PGM-C [118]96.0 11.8 78 27.3 122 2.83 52 14.4 48 20.7 61 3.70 38 12.3 125 23.0 78 3.00 17 20.6 120 42.3 167 7.62 76 45.8 141 59.5 156 11.2 153 27.2 77 47.4 80 4.97 59 37.1 112 79.2 121 4.04 37 32.4 133 55.0 163 3.51 91
Ramp [62]96.7 12.0 97 24.6 86 2.94 94 14.8 64 21.3 69 3.70 38 11.7 88 29.4 142 3.00 17 16.9 31 30.3 49 7.39 31 45.4 129 58.5 135 11.0 137 30.2 169 50.9 141 5.23 131 39.8 154 89.6 165 4.04 37 32.4 133 52.5 145 3.42 38
OFLAF [78]97.0 11.7 69 24.5 83 2.71 16 13.6 29 20.3 44 3.56 11 11.0 45 23.0 78 3.00 17 17.6 43 31.3 58 7.39 31 47.3 179 61.7 182 11.2 153 29.6 152 51.9 156 5.32 148 41.8 173 95.6 183 4.16 147 33.6 152 52.1 142 3.42 38
ProFlow_ROB [142]97.8 11.8 78 27.5 127 2.83 52 15.8 88 22.6 102 3.79 61 11.4 84 20.3 46 3.00 17 18.9 78 37.0 130 7.35 22 47.3 179 61.8 185 11.2 153 25.5 44 44.2 44 4.83 37 40.0 160 81.4 137 4.08 78 34.3 162 56.5 169 3.56 115
S2F-IF [121]97.9 12.1 113 29.8 150 2.71 16 14.2 42 20.6 56 3.56 11 11.3 65 26.3 110 3.00 17 20.2 111 40.1 157 7.53 52 45.9 146 58.7 143 11.3 174 28.4 114 50.7 135 5.20 123 35.7 84 76.0 96 4.08 78 32.3 131 53.1 150 3.46 76
TF+OM [98]98.3 11.6 61 30.1 155 3.11 130 15.0 66 21.6 76 4.04 84 11.7 88 24.0 89 3.00 17 21.3 134 39.0 152 7.68 88 44.3 102 56.7 104 10.3 97 28.8 127 50.4 124 5.07 93 37.7 120 83.5 147 4.08 78 29.2 50 46.0 63 3.56 115
ComplOF-FED-GPU [35]99.5 12.0 97 27.9 131 2.94 94 15.7 85 22.2 95 3.79 61 16.0 160 21.4 58 3.70 142 18.4 66 33.6 88 7.48 41 44.9 118 57.7 116 10.7 126 27.4 83 45.9 61 5.00 85 36.6 106 78.7 119 4.08 78 32.6 143 52.3 143 3.51 91
AggregFlow [95]99.8 13.7 171 37.1 179 3.11 130 16.2 100 22.6 102 4.04 84 11.0 45 23.3 83 3.00 17 21.8 141 40.7 161 7.66 86 43.2 78 53.5 60 10.3 97 27.0 71 46.0 62 5.00 85 38.0 126 82.4 143 4.08 78 31.9 118 51.9 139 3.42 38
Classic+NL [31]99.9 12.1 113 24.3 74 3.00 112 15.3 72 21.8 80 3.70 38 11.7 88 29.4 142 3.00 17 17.4 36 31.4 60 7.53 52 45.7 137 59.4 151 10.8 129 29.0 134 49.8 112 5.10 111 39.6 151 90.4 170 4.08 78 32.2 128 51.8 136 3.46 76
Ad-TV-NDC [36]99.9 12.2 121 22.5 53 4.32 192 20.6 185 24.8 167 5.80 171 11.7 88 21.6 61 3.37 118 21.6 139 31.8 69 8.04 133 42.5 59 53.4 59 9.97 42 26.4 58 47.6 84 5.16 117 36.8 108 70.9 51 4.08 78 28.3 41 41.8 38 3.70 165
FC-2Layers-FF [74]100.1 12.1 113 26.0 112 2.83 52 13.0 19 18.7 26 3.56 11 11.4 84 25.7 103 3.00 17 17.8 52 33.5 87 7.48 41 46.5 162 60.3 169 11.2 153 30.4 172 52.3 161 5.32 148 39.8 154 90.0 167 4.08 78 31.8 114 51.6 132 3.46 76
LSM [39]101.0 12.3 130 24.7 90 2.83 52 15.4 74 21.9 87 3.56 11 12.0 104 30.3 154 3.00 17 18.7 74 33.2 84 7.44 37 46.1 153 59.4 151 11.1 144 29.3 144 51.9 156 5.07 93 39.2 144 91.0 173 4.04 37 32.3 131 52.5 145 3.42 38
Classic++ [32]101.6 11.6 61 23.7 64 3.11 130 17.8 134 24.4 156 4.08 89 11.7 88 20.3 46 3.37 118 20.1 108 33.8 93 7.62 76 44.7 111 57.8 119 10.0 50 28.0 99 49.7 109 5.35 155 37.4 116 81.4 137 4.08 78 30.7 85 49.5 102 3.56 115
DMF_ROB [135]101.8 11.9 90 25.4 99 3.00 112 17.1 120 22.8 107 4.08 89 19.4 179 29.7 146 3.70 142 20.4 115 34.5 99 7.68 88 45.3 126 58.1 126 11.1 144 26.4 58 45.6 60 4.97 59 35.7 84 73.8 82 4.08 78 31.2 95 50.2 107 3.42 38
MLDP_OF [87]103.4 11.9 90 24.7 90 2.83 52 17.4 128 23.8 138 3.87 71 10.7 33 24.6 97 3.00 17 20.5 119 33.6 88 8.35 154 44.1 96 56.5 100 10.1 64 29.3 144 50.5 128 5.57 174 35.8 87 73.4 79 4.20 154 31.2 95 50.6 119 3.70 165
MCPFlow_RVC [197]103.9 14.9 183 36.3 172 2.83 52 14.7 59 21.4 74 3.74 56 11.2 63 26.3 110 3.00 17 19.8 99 37.2 134 7.70 95 43.4 84 54.0 65 10.1 64 31.9 185 59.9 184 5.03 92 33.2 39 70.1 44 4.04 37 52.6 197 69.2 194 4.20 194
C-RAFT_RVC [181]104.5 15.3 186 39.1 184 2.94 94 15.7 85 21.8 80 4.08 89 12.7 133 30.0 151 3.11 109 21.2 129 37.1 133 7.70 95 42.1 50 52.4 53 9.97 42 28.8 127 51.1 144 4.97 59 35.0 69 72.2 67 4.04 37 33.8 156 52.5 145 3.51 91
TCOF [69]104.8 12.0 97 24.7 90 2.83 52 20.3 180 26.4 195 5.07 147 11.1 61 29.0 136 3.00 17 17.7 46 32.4 75 7.68 88 43.2 78 55.5 91 9.97 42 28.8 127 46.3 66 5.07 93 41.2 170 94.9 181 4.08 78 31.8 114 51.3 126 3.70 165
FlowNetS+ft+v [110]104.9 11.5 56 23.7 64 3.46 176 19.9 171 24.6 162 7.87 194 12.0 104 21.1 57 3.37 118 19.5 93 30.6 53 8.91 172 43.7 90 56.6 103 11.2 153 26.0 49 44.5 49 4.97 59 38.6 137 87.8 155 4.08 78 30.0 70 46.0 63 3.51 91
RNLOD-Flow [119]105.2 11.8 78 24.6 86 2.89 90 17.3 127 24.0 144 3.74 56 12.7 133 36.0 179 3.11 109 18.1 59 31.2 57 7.48 41 45.8 141 59.6 157 11.1 144 29.3 144 50.6 130 5.16 117 35.4 74 74.1 88 4.08 78 32.0 124 51.6 132 3.42 38
Fusion [6]105.8 11.6 61 24.3 74 2.89 90 15.6 82 21.9 87 3.83 66 11.0 45 23.7 84 3.37 118 21.0 127 33.4 85 7.62 76 44.1 96 56.3 99 10.1 64 30.3 171 54.1 168 5.45 161 38.0 126 83.7 148 4.08 78 34.0 159 54.7 158 3.56 115
CRTflow [81]106.0 11.7 69 24.4 81 3.32 161 19.5 163 24.9 171 4.51 117 12.0 104 22.7 74 4.00 160 18.1 59 30.3 49 7.68 88 45.0 120 58.1 126 11.3 174 26.0 49 45.1 57 4.97 59 37.7 120 87.9 156 4.08 78 30.8 86 50.2 107 3.56 115
Sparse Occlusion [54]106.2 11.7 69 25.9 107 3.00 112 18.1 139 24.6 162 3.83 66 11.3 65 22.7 74 3.11 109 18.7 74 34.1 96 7.70 95 45.0 120 58.0 123 11.1 144 28.5 122 44.2 44 5.26 136 39.3 148 83.7 148 3.92 29 31.9 118 51.7 134 3.56 115
S2D-Matching [83]106.2 12.3 130 25.7 103 2.94 94 17.2 125 23.7 136 4.00 81 11.7 88 28.7 133 3.00 17 17.7 46 31.9 71 7.55 60 46.8 172 60.1 163 10.4 107 30.0 161 51.5 149 5.29 142 37.0 110 77.7 114 4.04 37 31.8 114 50.9 121 3.46 76
RFlow [88]106.3 11.6 61 24.3 74 3.00 112 19.3 157 24.8 167 4.36 109 11.6 87 29.7 146 3.37 118 20.0 106 36.1 120 7.72 102 43.0 70 55.2 89 10.1 64 27.9 96 51.8 155 4.97 59 37.1 112 82.8 145 4.08 78 31.6 108 49.5 102 3.56 115
SVFilterOh [109]106.5 11.9 90 26.1 113 2.94 94 14.3 46 20.9 64 3.70 38 12.0 104 26.7 116 3.00 17 19.9 104 36.1 120 7.62 76 46.7 168 59.8 160 11.4 187 30.7 176 55.1 172 5.07 93 36.0 94 77.2 110 4.04 37 32.4 133 53.2 152 3.51 91
TC-Flow [46]107.6 12.0 97 30.3 157 2.89 90 16.8 114 23.4 127 3.92 79 11.7 88 21.4 58 3.00 17 19.5 93 36.1 120 8.12 141 46.5 162 59.8 160 11.3 174 27.0 71 48.4 95 5.26 136 35.5 77 74.6 92 4.04 37 33.3 149 54.5 157 3.51 91
HBM-GC [103]107.7 11.8 78 23.8 67 3.11 130 16.8 114 24.2 151 3.87 71 10.7 33 18.7 34 3.00 17 18.9 78 32.9 80 7.68 88 46.8 172 60.8 173 11.5 193 34.5 194 61.7 189 5.48 169 37.7 120 81.9 142 4.04 37 30.5 83 47.8 81 3.51 91
Classic+CPF [82]108.5 12.2 121 24.6 86 2.83 52 15.6 82 22.1 92 3.74 56 12.0 104 30.7 157 3.00 17 17.7 46 30.9 56 7.44 37 47.2 178 61.3 178 11.2 153 31.2 180 55.9 173 5.26 136 39.9 157 88.8 162 4.04 37 33.6 152 54.0 155 3.42 38
3DFlow [133]108.7 12.4 138 27.1 121 2.83 52 15.5 78 22.1 92 3.87 71 13.7 144 24.0 89 3.00 17 19.2 84 38.7 149 7.68 88 44.0 95 56.0 95 10.1 64 31.2 180 53.8 167 5.60 176 39.5 149 79.2 121 4.16 147 31.1 94 48.0 83 3.56 115
FESL [72]108.9 12.2 121 25.1 98 2.83 52 14.9 65 21.6 76 3.70 38 12.1 121 33.7 171 3.00 17 19.7 97 35.0 107 7.72 102 46.2 154 60.2 168 11.3 174 29.3 144 50.4 124 5.32 148 39.6 151 88.6 161 3.92 29 32.4 133 51.2 124 3.42 38
CostFilter [40]109.8 13.1 164 33.1 165 2.71 16 15.2 69 21.3 69 3.56 11 14.0 148 42.7 192 3.00 17 22.0 143 44.4 175 7.26 10 45.8 141 57.2 112 10.4 107 27.2 77 48.1 93 5.45 161 39.9 157 89.4 164 4.08 78 35.6 170 56.1 167 3.37 28
Black & Anandan [4]110.5 12.3 130 24.0 69 3.46 176 21.2 188 25.4 179 5.35 160 18.1 174 25.0 100 5.35 177 24.4 164 34.9 105 7.77 108 42.2 53 53.5 60 10.1 64 26.9 70 46.5 69 4.97 59 39.5 149 77.2 110 4.08 78 29.3 52 42.8 43 3.56 115
Efficient-NL [60]112.0 11.8 78 23.8 67 2.83 52 16.7 112 23.3 123 3.70 38 18.4 176 29.0 136 3.70 142 19.4 91 34.0 94 7.51 45 45.1 122 58.5 135 11.1 144 30.0 161 51.5 149 5.07 93 40.1 161 88.9 163 4.08 78 33.0 145 52.4 144 3.42 38
EpicFlow [100]112.0 11.9 90 27.6 128 2.83 52 16.0 94 22.2 95 3.79 61 11.8 101 21.7 62 3.00 17 21.3 134 42.9 169 7.85 116 46.3 157 59.4 151 11.2 153 27.4 83 47.5 82 5.16 117 38.2 129 76.6 102 4.12 137 35.2 169 58.0 173 3.56 115
SRR-TVOF-NL [89]113.7 12.9 157 28.7 140 3.00 112 16.9 118 23.1 117 4.69 132 11.5 86 27.0 120 3.00 17 22.2 145 37.3 135 7.59 69 44.8 116 57.9 121 11.0 137 29.1 140 51.9 156 4.90 43 35.7 84 77.7 114 4.08 78 33.0 145 51.5 131 3.56 115
Bartels [41]114.8 12.2 121 29.9 153 3.37 165 17.4 128 24.3 153 4.83 141 11.3 65 24.7 98 3.70 142 21.2 129 35.4 110 9.15 178 41.3 40 51.0 39 9.87 37 29.7 154 50.2 117 6.32 191 33.7 43 70.7 48 4.20 154 30.2 76 48.4 86 3.79 186
Filter Flow [19]114.9 11.8 78 23.1 58 3.37 165 20.0 173 25.1 173 5.23 157 12.2 124 26.0 107 3.70 142 22.1 144 32.7 78 7.94 125 42.1 50 51.9 46 10.4 107 28.1 104 49.0 102 5.07 93 38.4 132 81.6 139 4.16 147 30.0 70 45.5 61 3.74 183
2D-CLG [1]115.7 11.6 61 24.1 71 3.11 130 19.4 160 23.3 123 6.24 182 18.7 177 24.3 94 4.69 170 22.4 147 31.8 69 8.66 164 43.3 83 56.1 98 10.4 107 26.0 49 44.2 44 5.35 155 40.2 162 91.5 175 4.20 154 29.6 63 44.5 47 3.51 91
Steered-L1 [116]116.9 11.2 42 22.6 55 2.89 90 16.2 100 22.6 102 4.55 121 21.7 180 32.4 165 5.00 173 23.4 157 38.3 144 10.7 184 44.7 111 57.4 113 9.88 38 28.0 99 48.5 97 5.32 148 37.1 112 79.2 121 4.12 137 31.4 102 51.1 123 3.51 91
OFH [38]118.2 12.0 97 27.3 122 3.00 112 18.1 139 23.4 127 4.20 99 12.4 131 32.7 166 3.00 17 18.6 72 35.4 110 7.35 22 46.5 162 60.1 163 10.8 129 27.5 86 47.2 76 5.26 136 41.1 167 81.1 135 4.20 154 35.7 171 56.1 167 3.46 76
EPPM w/o HM [86]118.4 12.7 150 30.9 159 2.71 16 16.1 96 23.1 117 3.70 38 17.7 171 42.4 191 3.70 142 21.3 134 42.5 168 7.70 95 43.0 70 53.1 57 10.3 97 30.2 169 57.1 179 4.97 59 38.5 135 89.6 165 4.12 137 32.4 133 51.3 126 3.42 38
Occlusion-TV-L1 [63]119.0 11.6 61 25.0 97 3.11 130 19.8 169 26.0 190 4.83 141 11.3 65 23.0 78 3.46 137 22.5 150 43.0 171 7.94 125 43.0 70 54.8 82 9.88 38 28.0 99 50.7 135 5.32 148 39.6 151 76.6 102 4.62 182 31.5 106 50.5 115 3.56 115
FF++_ROB [141]119.2 12.1 113 28.2 136 2.71 16 15.5 78 21.6 76 3.74 56 12.0 104 29.4 142 3.00 17 23.3 156 49.1 183 7.83 115 48.1 185 61.6 181 11.3 174 29.1 140 49.5 107 5.94 187 36.5 105 76.4 101 4.08 78 32.1 126 51.3 126 3.65 159
Adaptive [20]119.8 11.6 61 26.7 117 3.11 130 20.2 177 25.9 186 5.07 147 12.0 104 23.0 78 3.37 118 20.4 115 36.6 128 7.77 108 44.3 102 58.5 135 9.98 47 28.3 111 49.1 104 5.16 117 42.5 178 90.6 172 4.08 78 31.6 108 48.8 94 3.65 159
LFNet_ROB [145]120.6 13.4 168 37.5 181 2.71 16 16.1 96 21.8 80 4.08 89 12.0 104 36.3 182 3.37 118 20.7 121 36.0 118 7.94 125 45.4 129 57.8 119 11.6 196 30.6 173 57.4 180 5.20 123 34.9 66 71.8 63 4.08 78 31.3 100 49.9 105 3.70 165
PBOFVI [189]121.9 12.8 156 27.9 131 2.83 52 19.4 160 25.6 182 4.51 117 16.3 162 35.0 175 3.00 17 20.3 113 37.9 139 8.04 133 45.5 132 59.4 151 11.3 174 28.0 99 47.5 82 4.97 59 39.8 154 78.5 117 4.08 78 31.7 112 52.0 140 3.51 91
PWC-Net_RVC [143]122.5 13.5 170 35.8 171 2.71 16 16.4 103 23.3 123 3.74 56 12.0 104 30.3 154 3.00 17 21.3 134 45.6 178 7.51 45 48.8 192 63.0 188 11.2 153 29.7 154 53.0 163 5.29 142 35.8 87 74.9 94 4.08 78 34.2 160 56.0 166 3.51 91
CNN-flow-warp+ref [115]122.5 11.0 35 22.4 52 3.11 130 17.6 132 22.9 111 5.92 174 16.1 161 28.3 132 4.00 160 23.5 158 30.2 47 10.7 184 44.8 116 58.5 135 11.3 174 26.5 64 46.5 69 5.29 142 41.5 171 91.5 175 4.32 170 30.4 81 47.5 77 3.51 91
TriFlow [93]123.0 12.5 143 36.7 175 3.00 112 18.7 146 24.5 159 4.76 135 11.7 88 28.1 130 3.00 17 21.7 140 41.4 163 7.62 76 46.8 172 60.4 170 11.2 153 29.9 158 51.7 154 4.97 59 37.8 124 76.9 106 4.08 78 31.7 112 48.6 90 3.51 91
CompactFlow_ROB [155]123.2 14.6 182 39.6 186 2.83 52 16.4 103 22.7 105 4.32 106 14.3 153 38.7 184 3.00 17 31.2 184 71.5 195 8.08 140 43.6 87 54.6 76 10.3 97 29.7 154 55.9 173 4.93 50 37.7 120 83.9 150 4.08 78 33.0 145 51.4 129 3.51 91
IAOF [50]123.6 13.0 161 29.2 144 3.37 165 23.7 196 27.4 198 6.45 186 16.4 164 28.7 133 3.46 137 22.7 151 33.1 83 8.37 155 43.4 84 55.6 93 10.0 50 27.6 88 50.1 114 4.97 59 38.3 130 82.7 144 4.08 78 30.0 70 46.8 69 3.56 115
Horn & Schunck [3]123.8 12.1 113 23.7 64 3.32 161 21.4 190 25.6 182 5.89 173 17.0 167 28.2 131 5.35 177 27.3 175 37.9 139 8.04 133 42.4 57 54.3 69 10.3 97 26.2 53 44.7 51 5.07 93 40.9 165 81.7 140 4.20 154 30.2 76 44.3 46 3.70 165
HBpMotionGpu [43]124.2 12.3 130 32.0 163 3.79 187 20.6 185 25.4 179 6.00 177 11.3 65 26.1 109 3.00 17 23.2 154 44.0 174 7.85 116 44.3 102 56.9 105 10.8 129 29.0 134 53.5 166 5.26 136 34.9 66 69.8 41 4.04 37 31.8 114 51.4 129 3.70 165
TV-L1-improved [17]124.5 11.5 56 25.4 99 3.11 130 20.1 176 26.0 190 5.26 158 16.8 165 19.7 39 4.04 166 19.5 93 32.3 73 7.79 112 43.8 92 56.5 100 10.0 50 28.9 133 51.1 144 5.07 93 43.2 181 98.9 187 4.43 177 31.4 102 50.2 107 3.70 165
Nguyen [33]126.1 12.0 97 25.9 107 3.37 165 21.2 188 24.5 159 6.27 183 12.7 133 28.0 128 3.70 142 23.8 159 34.7 101 8.58 160 43.0 70 54.7 79 10.1 64 27.7 93 50.7 135 4.97 59 43.4 183 93.7 179 4.43 177 30.2 76 47.4 74 3.56 115
TVL1_RVC [175]126.8 11.8 78 25.9 107 3.70 183 21.7 191 25.9 186 6.03 178 12.3 125 26.8 119 3.70 142 22.9 153 35.4 110 8.33 151 43.2 78 54.9 83 10.1 64 28.4 114 50.6 130 5.10 111 41.0 166 91.6 177 4.24 165 29.6 63 44.9 54 3.56 115
GraphCuts [14]127.0 13.9 176 30.2 156 3.32 161 16.4 103 22.5 99 4.36 109 33.4 194 24.1 93 5.35 177 22.3 146 34.7 101 7.87 122 44.5 108 57.0 106 9.98 47 28.3 111 50.3 122 4.90 43 38.5 135 88.2 158 4.20 154 33.9 158 53.6 154 3.56 115
BriefMatch [122]128.2 12.1 113 29.2 144 3.11 130 16.5 109 22.5 99 6.61 188 18.0 173 22.7 74 5.69 180 26.2 171 35.5 115 18.2 196 43.7 90 54.7 79 10.4 107 29.6 152 50.2 117 5.94 187 35.8 87 72.5 71 4.16 147 32.1 126 50.2 107 3.56 115
FlowNet2 [120]129.8 19.1 192 47.5 193 3.11 130 17.1 120 24.1 148 4.55 121 14.2 151 29.8 149 3.37 118 23.8 159 42.9 169 8.33 151 45.9 146 58.1 126 10.6 121 27.6 88 49.4 106 4.93 50 39.2 144 81.0 133 4.08 78 31.6 108 49.2 98 3.56 115
TI-DOFE [24]129.9 12.7 150 27.6 128 3.87 191 22.2 194 25.3 175 6.66 189 14.1 150 25.3 102 4.36 168 27.7 177 38.7 149 9.06 177 42.7 63 53.6 63 10.1 64 26.8 68 48.8 101 4.97 59 38.3 130 76.0 96 4.24 165 31.9 118 44.7 51 3.87 189
CVENG22+RIC [199]130.3 12.0 97 25.8 105 3.00 112 17.1 120 23.1 117 3.87 71 13.0 138 27.3 121 3.00 17 24.2 162 45.5 176 7.87 122 46.3 157 60.5 172 11.3 174 28.8 127 50.4 124 5.10 111 40.2 162 79.0 120 4.12 137 41.6 185 62.5 185 3.56 115
ROF-ND [105]131.2 12.4 138 24.4 81 2.83 52 17.9 135 23.9 140 4.08 89 12.0 104 26.6 115 3.00 17 29.5 183 48.9 182 8.72 166 45.4 129 58.6 139 11.1 144 31.1 179 53.4 164 5.26 136 38.9 142 74.2 89 4.20 154 38.0 177 60.3 179 3.56 115
AugFNG_ROB [139]131.2 13.7 171 36.6 174 3.00 112 17.5 131 22.9 111 4.80 138 14.3 153 36.0 179 3.37 118 27.8 178 64.0 190 7.96 132 48.6 191 63.0 188 11.4 187 28.0 99 51.6 153 4.83 37 36.1 99 76.6 102 4.08 78 31.9 118 47.2 73 3.42 38
Correlation Flow [76]132.3 12.6 147 28.0 133 2.71 16 20.0 173 25.8 184 4.36 109 11.3 65 22.3 69 3.00 17 20.7 121 38.6 148 7.72 102 45.7 137 59.0 147 10.3 97 33.4 188 60.4 188 5.45 161 45.6 188 99.9 188 4.40 172 33.4 150 54.9 161 3.56 115
NL-TV-NCC [25]134.1 13.7 171 27.3 122 2.94 94 18.5 141 24.7 164 4.04 84 15.0 157 29.0 136 3.70 142 25.6 168 46.4 180 7.94 125 42.0 48 51.9 46 10.4 107 30.6 173 51.9 156 5.29 142 41.9 174 81.7 140 4.40 172 31.3 100 48.6 90 3.79 186
Complementary OF [21]134.2 12.4 138 34.5 169 2.83 52 16.4 103 23.5 131 3.79 61 30.7 187 32.2 164 7.05 190 19.9 104 43.9 173 7.44 37 46.9 175 60.4 170 10.7 126 28.1 104 47.7 87 5.23 131 41.1 167 80.3 129 4.12 137 42.0 186 62.0 184 3.56 115
TriangleFlow [30]134.2 12.5 143 25.9 107 3.11 130 18.8 148 24.3 153 4.24 102 13.2 141 29.7 146 3.46 137 21.2 129 35.4 110 7.94 125 44.4 106 57.7 116 9.95 40 29.4 149 48.6 98 5.07 93 43.9 184 99.9 188 4.43 177 42.1 188 69.7 195 3.56 115
LocallyOriented [52]135.0 12.2 121 28.1 134 3.27 159 20.5 183 25.9 186 5.07 147 14.3 153 30.0 151 3.37 118 24.2 162 41.7 164 7.66 86 44.7 111 57.1 110 10.1 64 28.8 127 47.4 80 5.48 169 42.4 176 80.6 131 4.12 137 32.4 133 51.2 124 3.56 115
IAOF2 [51]136.0 12.7 150 28.7 140 3.32 161 20.4 181 25.9 186 4.76 135 12.7 133 31.7 162 3.11 109 22.4 147 35.8 116 8.06 139 45.9 146 59.6 157 10.8 129 29.9 158 51.5 149 5.10 111 39.0 143 79.7 126 4.08 78 31.2 95 49.0 97 3.56 115
LSM_FLOW_RVC [182]136.5 16.3 188 45.1 191 2.94 94 17.4 128 23.3 123 4.36 109 13.7 144 39.4 186 3.00 17 25.7 169 64.9 192 7.77 108 46.4 161 60.1 163 11.0 137 27.7 93 46.6 71 5.16 117 38.1 128 78.5 117 4.12 137 35.1 168 56.5 169 3.70 165
ContinualFlow_ROB [148]137.3 14.3 179 37.0 178 2.94 94 17.0 119 23.6 133 4.51 117 13.8 147 33.5 170 3.37 118 23.2 154 53.7 186 7.70 95 49.9 193 66.1 194 11.3 174 27.2 77 49.8 112 4.90 43 38.7 140 86.6 153 4.04 37 42.0 186 61.1 181 3.56 115
H+S_RVC [176]137.8 13.7 171 27.7 130 3.11 130 18.5 141 22.5 99 5.74 168 17.7 171 27.7 123 5.74 183 27.2 174 34.7 101 9.04 176 44.1 96 56.5 100 10.4 107 27.7 93 47.9 89 5.35 155 39.2 144 83.4 146 4.80 186 32.5 142 48.8 94 3.83 188
EPMNet [131]139.5 19.3 193 47.9 194 3.11 130 16.8 114 23.2 122 4.55 121 14.2 151 29.8 149 3.37 118 33.0 190 78.1 197 8.29 149 45.9 146 58.1 126 10.6 121 30.0 161 51.9 156 4.97 59 39.2 144 81.0 133 4.08 78 33.8 156 53.1 150 3.51 91
IIOF-NLDP [129]139.6 12.9 157 29.0 143 2.71 16 18.6 145 24.8 167 4.08 89 13.4 143 26.7 116 3.00 17 21.9 142 39.8 154 8.16 144 45.8 141 59.4 151 10.4 107 31.6 183 59.9 184 6.06 190 54.7 197 99.9 188 6.03 196 35.7 171 57.2 172 3.42 38
ACK-Prior [27]140.4 12.5 143 29.7 149 2.83 52 16.1 96 22.7 105 4.00 81 25.6 183 27.7 123 5.72 182 22.4 147 36.0 118 10.7 184 45.7 137 59.3 149 11.4 187 31.8 184 50.6 130 5.35 155 38.8 141 79.9 127 4.16 147 33.5 151 51.7 134 3.70 165
Rannacher [23]140.9 11.7 69 28.7 140 3.16 158 20.4 181 26.3 193 5.07 147 19.0 178 26.0 107 4.80 172 19.8 99 38.1 142 7.79 112 44.5 108 57.4 113 10.1 64 29.0 134 50.3 122 5.20 123 42.6 179 97.0 184 4.40 172 33.7 154 55.9 165 3.70 165
LiteFlowNet [138]142.1 14.1 178 39.6 186 2.71 16 15.7 85 21.9 87 4.00 81 14.0 148 43.0 193 3.00 17 36.3 195 70.9 194 9.02 174 48.3 187 63.2 191 11.5 193 30.1 168 57.7 181 5.10 111 42.1 175 87.4 154 4.24 165 32.4 133 50.2 107 3.51 91
Learning Flow [11]143.2 12.1 113 24.6 86 3.27 159 19.7 166 25.2 174 5.00 145 39.7 196 47.7 197 7.68 192 24.6 165 35.0 107 8.19 147 45.2 125 58.6 139 10.5 120 28.4 114 48.0 91 5.45 161 38.4 132 77.8 116 4.40 172 32.6 143 48.4 86 3.92 191
2bit-BM-tele [96]143.6 11.7 69 27.0 120 3.79 187 20.2 177 26.3 193 5.07 147 12.0 104 23.2 82 4.00 160 21.2 129 36.1 120 8.16 144 45.3 126 58.0 123 10.3 97 34.0 192 61.8 190 5.92 184 54.1 196 99.9 188 5.72 194 29.8 68 47.4 74 3.74 183
SimpleFlow [49]145.2 12.0 97 24.0 69 2.94 94 18.5 141 24.4 156 4.24 102 32.7 190 39.0 185 5.69 180 18.0 57 36.2 125 7.55 60 46.9 175 60.8 173 11.1 144 31.4 182 58.1 182 5.35 155 49.4 192 99.9 188 5.16 192 40.0 181 63.0 188 3.46 76
FOLKI [16]146.2 13.0 161 30.9 159 4.97 196 22.2 194 24.9 171 9.00 196 17.3 169 33.0 168 7.00 187 33.4 191 38.7 149 17.0 194 44.3 102 55.8 94 10.4 107 27.6 88 49.7 109 5.48 169 36.2 102 74.2 89 4.80 186 30.4 81 44.9 54 4.08 193
SILK [80]146.7 13.3 167 30.7 158 3.83 190 22.0 193 25.3 175 7.16 190 34.7 195 40.0 188 7.77 194 26.6 172 36.6 128 8.60 162 45.1 122 57.9 121 10.0 50 28.4 114 50.9 141 6.03 189 34.8 60 71.8 63 4.51 181 31.4 102 48.0 83 3.74 183
ResPWCR_ROB [140]147.9 12.9 157 34.8 170 2.94 94 17.1 120 24.0 144 4.36 109 16.8 165 31.4 161 3.37 118 25.7 169 57.3 188 8.29 149 46.7 168 60.8 173 11.2 153 29.9 158 58.2 183 5.92 184 35.6 79 74.0 85 4.20 154 36.6 174 60.5 180 3.56 115
IRR-PWC_RVC [180]148.1 16.8 189 47.4 192 3.11 130 16.8 114 23.9 140 4.55 121 14.4 156 38.1 183 3.11 109 38.2 196 83.8 199 7.85 116 47.8 183 61.8 185 11.8 198 30.6 173 56.6 177 4.97 59 38.6 137 85.0 152 4.04 37 42.6 189 61.3 182 3.42 38
StereoFlow [44]148.7 22.8 198 48.3 195 3.74 186 20.5 183 26.8 196 5.07 147 11.3 65 29.3 141 3.37 118 20.1 108 37.0 130 7.62 76 59.3 196 75.2 196 10.8 129 39.3 198 71.4 197 5.45 161 35.8 87 73.9 84 4.08 78 35.7 171 55.1 164 3.70 165
OFRF [132]151.2 14.4 180 38.4 183 3.70 183 19.9 171 25.3 175 5.48 164 13.0 138 33.0 168 3.11 109 20.7 121 38.4 145 7.79 112 47.8 183 61.4 179 10.9 135 31.9 185 56.8 178 5.29 142 41.5 171 90.5 171 4.08 78 34.4 163 54.7 158 3.42 38
Shiralkar [42]151.4 13.2 166 31.6 162 3.00 112 19.7 166 24.5 159 4.65 129 17.0 167 30.7 157 4.08 167 32.1 188 53.1 185 8.04 133 46.3 157 59.7 159 10.3 97 28.4 114 50.2 117 5.45 161 45.5 187 95.2 182 4.24 165 39.2 180 62.6 186 3.42 38
StereoOF-V1MT [117]151.5 13.7 171 32.7 164 3.00 112 18.7 146 23.6 133 4.80 138 21.8 182 28.0 128 5.07 176 31.6 186 40.6 160 9.57 180 46.5 162 58.9 146 11.5 193 29.2 143 50.2 117 6.45 193 42.4 176 94.7 180 4.80 186 31.4 102 48.3 85 3.46 76
Dynamic MRF [7]153.5 12.1 113 26.8 118 2.94 94 18.0 138 23.9 140 4.16 98 18.3 175 30.7 157 5.00 173 28.9 180 39.8 154 10.5 183 45.9 146 58.6 139 11.2 153 30.9 177 56.0 175 5.80 183 43.0 180 90.3 169 4.65 183 33.7 154 51.8 136 3.70 165
Adaptive flow [45]154.5 13.4 168 25.8 105 4.51 193 21.8 192 25.4 179 7.26 191 13.7 144 27.5 122 4.69 170 24.1 161 35.2 109 8.76 169 47.3 179 61.5 180 10.2 89 33.8 191 61.9 191 5.45 161 35.9 92 73.2 77 4.20 154 34.7 167 54.7 158 3.70 165
UnFlow [127]158.7 14.9 183 40.2 188 3.11 130 18.5 141 23.4 127 5.48 164 15.3 158 31.3 160 4.36 168 22.8 152 38.0 141 8.45 157 48.3 187 63.0 188 10.9 135 32.4 187 62.0 192 5.72 178 35.4 74 71.2 55 4.32 170 45.5 193 66.0 192 3.87 189
SPSA-learn [13]160.5 12.3 130 33.7 168 3.37 165 19.2 155 23.6 133 5.45 163 30.0 186 39.7 187 7.00 187 26.9 173 41.3 162 8.41 156 46.7 168 60.1 163 10.2 89 29.4 149 50.6 130 5.20 123 53.7 195 99.9 188 8.43 198 51.4 196 72.0 197 3.51 91
SegOF [10]162.8 12.3 130 33.1 165 3.11 130 17.9 135 23.8 138 4.51 117 29.0 185 34.3 173 6.16 184 32.8 189 78.9 198 8.33 151 48.1 185 63.6 192 11.2 153 28.5 122 54.3 169 5.72 178 44.6 185 99.9 188 4.97 190 37.9 176 61.4 183 3.51 91
WRT [146]163.4 13.0 161 29.4 146 2.83 52 18.8 148 23.5 131 4.69 132 32.7 190 30.0 151 6.73 185 24.7 166 39.3 153 9.02 174 47.4 182 61.7 182 10.4 107 34.4 193 63.1 194 5.92 184 57.2 198 99.9 188 7.68 197 49.8 195 72.2 198 3.56 115
HCIC-L [97]164.6 21.0 197 41.8 189 5.07 197 20.2 177 26.1 192 5.80 171 16.3 162 42.3 190 4.00 160 31.7 187 51.0 184 8.50 158 44.7 111 55.5 91 10.4 107 35.2 195 69.8 196 5.07 93 39.9 157 91.2 174 4.16 147 40.4 184 58.0 173 3.65 159
FFV1MT [104]166.1 17.0 190 37.6 182 3.37 165 19.3 157 22.9 111 6.40 185 28.2 184 46.7 196 6.95 186 29.3 181 38.4 145 11.4 188 46.3 157 58.2 132 10.4 107 29.0 134 50.4 124 5.72 178 46.7 189 88.5 160 4.93 189 39.0 179 56.9 171 4.43 196
PGAM+LK [55]166.5 15.5 187 39.4 185 4.55 194 19.8 169 24.0 144 7.68 192 33.1 193 43.4 194 8.00 195 34.5 193 45.7 179 11.2 187 46.6 166 57.7 116 10.6 121 29.3 144 50.8 140 5.74 182 37.4 116 77.2 110 4.43 177 34.4 163 53.3 153 4.24 195
Heeger++ [102]167.6 19.8 194 44.7 190 3.11 130 18.9 151 22.8 107 6.45 186 33.0 192 35.2 176 7.16 191 29.3 181 38.4 145 11.4 188 51.5 194 65.2 193 11.3 174 28.4 114 46.9 73 6.78 195 47.9 191 84.5 151 4.69 184 40.1 182 58.8 176 3.70 165
SLK [47]168.7 13.9 176 29.9 153 3.79 187 20.0 173 22.8 107 6.22 181 32.0 189 33.7 171 7.72 193 33.4 191 46.4 180 16.1 193 48.5 190 61.7 182 10.3 97 28.4 114 47.9 89 5.72 178 43.2 181 97.9 185 4.97 190 38.7 178 59.8 178 4.04 192
WOLF_ROB [144]178.6 19.8 194 50.0 197 3.37 165 21.0 187 25.8 184 5.42 162 21.7 180 43.4 194 3.37 118 28.0 179 54.1 187 8.54 159 48.3 187 62.7 187 11.3 174 33.4 188 60.0 186 5.57 174 49.5 193 99.9 188 4.40 172 40.3 183 64.3 189 3.65 159
Pyramid LK [2]179.0 14.4 180 37.3 180 4.93 195 23.7 196 25.3 175 9.98 198 42.2 197 35.7 177 12.3 197 56.2 198 64.2 191 35.8 198 65.6 197 83.9 197 10.6 121 28.1 104 46.1 64 5.48 169 45.2 186 99.9 188 5.89 195 53.6 198 75.1 199 5.42 197
GroupFlow [9]180.9 19.9 196 49.6 196 3.42 174 19.1 153 24.1 148 5.48 164 31.4 188 40.0 188 8.19 196 36.2 194 61.9 189 12.1 190 55.6 195 71.3 195 11.4 187 36.3 196 67.0 195 5.60 176 46.7 189 98.5 186 4.20 154 43.6 190 62.8 187 3.56 115
Periodicity [79]195.8 17.6 191 55.7 198 5.45 198 26.8 198 27.0 197 9.75 197 49.4 199 51.5 199 17.7 198 51.3 197 70.3 193 27.9 197 66.6 198 86.3 198 11.7 197 38.7 197 82.5 198 6.38 192 51.8 194 99.9 188 5.48 193 44.3 192 65.5 191 5.80 198
AVG_FLOW_ROB [137]198.2 64.1 199 67.2 199 12.2 199 44.0 199 47.3 199 16.5 199 48.3 198 50.5 198 29.0 199 68.4 199 77.2 196 51.4 199 78.9 199 90.3 199 20.4 199 80.7 199 99.9 199 17.7 199 73.1 199 99.9 188 14.0 199 64.2 199 71.2 196 16.7 199
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.