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        
A95
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
SoftSplat [169]3.0 3.37 1 6.06 1 1.91 7 5.48 1 8.37 4 1.83 1 2.16 1 3.70 1 1.41 1 6.78 1 8.19 1 4.40 1 13.7 11 18.1 12 4.24 2 6.24 4 14.9 3 3.37 2 6.98 8 25.4 3 2.38 1 9.88 3 14.9 2 2.08 1
EAFI [171]7.4 3.70 4 6.68 7 1.91 7 6.19 8 9.66 11 1.91 3 2.71 4 4.69 6 1.73 2 7.44 9 9.33 6 4.65 5 15.0 18 19.9 18 4.32 7 6.83 11 17.7 12 3.37 2 6.95 7 26.8 10 2.38 1 11.6 10 17.3 7 2.16 3
DCM [185]8.0 3.70 4 6.38 4 1.91 7 5.69 2 7.94 1 1.83 1 2.38 2 4.00 3 1.73 2 7.30 5 9.11 4 4.51 3 15.0 18 19.9 18 4.40 9 7.51 17 18.6 18 3.37 2 8.66 29 29.2 14 2.38 1 12.1 15 17.9 11 2.16 3
EDSC [174]9.9 3.79 9 6.98 12 1.83 4 6.06 6 9.63 9 2.16 80 3.00 9 5.00 9 1.73 2 7.83 11 10.7 15 4.69 8 13.1 3 17.4 3 4.43 12 6.48 7 17.6 11 3.37 2 6.56 3 25.7 5 2.38 1 11.3 6 17.4 8 2.16 3
FGME [158]12.6 3.56 2 6.06 1 1.73 1 6.40 10 9.56 8 2.16 80 3.00 9 4.69 6 2.00 114 7.07 2 8.39 2 4.80 16 12.4 1 16.4 1 4.24 2 5.60 2 13.8 2 3.46 16 6.19 1 21.3 2 2.45 16 9.85 2 15.4 3 2.16 3
STSR [170]13.5 3.74 7 7.35 14 1.91 7 5.74 3 8.29 2 1.91 3 3.37 16 5.69 16 1.73 2 7.26 4 9.42 8 4.80 16 16.8 24 22.5 24 4.55 17 8.29 23 21.3 26 3.51 18 8.27 19 32.7 23 2.38 1 12.8 25 19.1 24 2.16 3
STAR-Net [164]14.0 3.70 4 6.16 3 2.08 86 6.58 24 10.9 30 2.16 80 3.00 9 4.08 5 1.73 2 7.62 10 9.59 9 4.40 1 12.9 2 17.0 2 4.20 1 7.05 13 17.4 10 3.37 2 8.35 20 26.4 8 2.38 1 11.3 6 16.9 6 2.16 3
DAI [168]14.8 3.83 10 6.45 5 2.08 86 6.76 36 10.2 22 2.08 5 2.38 2 4.00 3 1.73 2 7.14 3 8.81 3 4.93 19 15.9 20 21.2 20 4.24 2 7.77 19 19.7 19 3.37 2 7.85 13 31.2 21 2.38 1 12.3 19 18.5 20 2.16 3
TC-GAN [166]16.3 3.87 11 7.35 14 2.08 86 6.40 10 9.83 14 2.16 80 2.71 4 5.00 9 1.73 2 7.87 14 10.7 15 4.65 5 13.5 7 17.9 9 4.40 9 7.12 15 17.3 8 3.42 12 7.87 14 30.7 18 2.38 1 12.1 15 18.3 16 2.16 3
DAIN [152]17.3 3.92 15 7.44 18 2.08 86 6.45 16 9.88 16 2.16 80 2.83 8 5.10 12 1.73 2 7.85 12 10.7 15 4.65 5 13.5 7 17.9 9 4.43 12 7.07 14 17.3 8 3.42 12 7.87 14 30.9 20 2.38 1 12.1 15 18.2 15 2.16 3
BMBC [172]18.2 4.08 17 6.68 7 2.08 86 6.03 5 9.04 6 2.16 80 5.00 26 7.05 25 2.00 114 7.39 7 9.33 6 4.55 4 13.5 7 17.7 5 4.32 7 6.35 5 14.9 3 3.37 2 7.14 11 25.4 3 2.38 1 10.3 4 15.8 4 2.16 3
DSepConv [162]18.7 4.08 17 7.75 22 2.00 14 6.68 26 9.93 19 2.16 80 3.37 16 5.35 13 1.73 2 8.76 79 12.0 26 4.76 14 13.3 4 17.7 5 4.51 15 6.68 8 18.1 15 3.42 12 6.58 4 26.1 6 2.45 16 12.0 13 18.5 20 2.16 3
AdaCoF [165]18.8 4.08 17 7.39 17 2.16 123 6.22 9 9.49 7 2.16 80 4.00 21 5.69 16 1.73 2 8.43 44 11.3 19 4.69 8 14.8 16 19.7 16 4.65 19 5.97 3 15.3 5 3.32 1 6.68 6 26.9 11 2.38 1 10.5 5 16.0 5 2.08 1
MEMC-Net+ [160]19.8 4.08 17 7.05 13 2.16 123 6.48 20 9.83 14 2.16 80 3.00 9 5.35 13 1.73 2 8.19 16 10.2 12 4.69 8 14.8 16 19.7 16 4.40 9 7.68 18 18.0 13 3.37 2 8.19 18 30.0 17 2.38 1 12.3 19 18.3 16 2.16 3
GDCN [173]22.6 4.00 16 7.53 20 1.91 7 7.62 101 11.5 50 2.16 80 2.71 4 4.83 8 1.73 2 8.96 112 10.2 12 4.76 14 13.5 7 17.9 9 4.51 15 6.95 12 18.0 13 3.46 16 7.07 10 26.5 9 2.38 1 11.5 8 18.0 13 2.16 3
FeFlow [167]25.5 3.74 7 6.78 9 1.83 4 6.73 34 10.5 25 2.16 80 3.00 9 5.00 9 2.00 114 8.04 15 10.5 14 4.69 8 13.4 5 17.7 5 4.24 2 7.44 16 18.4 17 3.42 12 8.54 22 28.0 13 2.45 16 11.8 12 18.1 14 2.38 149
PMMST [112]27.7 5.00 29 9.68 38 2.00 14 6.88 47 11.0 34 2.08 5 5.69 29 9.00 27 1.73 2 8.21 21 12.0 26 5.07 25 17.4 29 23.4 29 5.07 36 9.29 31 22.6 29 3.74 47 8.66 29 37.1 41 2.45 16 13.9 39 21.3 38 2.16 3
ADC [161]27.9 4.51 27 7.96 24 2.16 123 6.56 22 9.63 9 2.38 133 4.36 22 6.35 21 1.73 2 9.11 124 12.1 29 4.80 16 14.4 15 19.3 15 4.55 17 6.68 8 18.1 15 3.37 2 6.66 5 26.1 6 2.38 1 12.0 13 18.4 18 2.16 3
FRUCnet [153]28.7 4.20 21 7.51 19 2.65 178 6.40 10 9.75 13 2.52 156 3.56 19 5.69 16 2.00 114 8.19 16 10.9 18 4.69 8 13.8 13 18.2 14 4.24 2 6.45 6 16.5 7 3.37 2 7.05 9 27.0 12 2.45 16 11.5 8 17.4 8 2.16 3
MAF-net [163]29.0 3.56 2 6.78 9 1.73 1 6.78 39 10.9 30 2.16 80 3.00 9 5.48 15 2.00 114 7.85 12 10.1 11 5.00 23 16.2 21 21.8 21 4.69 20 7.79 20 20.6 22 3.56 20 7.14 11 29.3 15 2.45 16 12.3 19 18.4 18 2.38 149
MDP-Flow2 [68]30.1 4.97 28 9.42 32 2.00 14 6.68 26 11.0 34 2.08 5 5.69 29 9.04 32 1.73 2 8.19 16 12.0 26 5.10 52 17.5 31 23.5 32 5.07 36 9.95 63 24.7 64 3.74 47 8.60 25 36.4 30 2.45 16 13.9 39 21.5 40 2.16 3
UnDAF [184]30.8 5.00 29 9.56 35 2.00 14 6.68 26 11.0 34 2.08 5 5.69 29 9.68 42 1.73 2 8.23 22 12.2 30 5.07 25 17.6 34 23.6 33 5.07 36 9.97 69 24.6 62 3.74 47 8.66 29 36.7 34 2.45 16 13.9 39 21.6 44 2.16 3
CoT-AMFlow [175]31.5 5.00 29 9.68 38 2.00 14 6.68 26 11.1 39 2.08 5 5.69 29 9.38 39 1.73 2 8.23 22 12.2 30 5.07 25 17.6 34 23.6 33 5.07 36 9.98 72 24.5 59 3.74 47 8.70 37 37.0 39 2.45 16 13.9 39 21.6 44 2.16 3
CyclicGen [149]35.5 4.20 21 6.86 11 2.45 173 6.06 6 8.29 2 3.42 181 4.36 22 7.62 26 2.00 114 8.74 75 11.6 21 5.26 139 13.4 5 17.4 3 4.69 20 5.35 1 11.3 1 3.70 21 6.24 2 19.7 1 2.38 1 8.89 1 13.0 1 2.16 3
CtxSyn [134]37.9 3.87 11 7.35 14 1.83 4 5.80 4 8.96 5 2.08 5 3.11 15 5.69 16 2.00 114 7.33 6 9.95 10 4.97 20 17.1 27 22.5 24 4.93 26 8.70 26 20.9 23 3.74 47 10.2 151 33.7 27 2.52 140 12.6 23 18.8 22 2.38 149
OFRI [154]39.4 3.87 11 6.61 6 2.16 123 6.40 10 9.70 12 2.45 148 2.71 4 3.79 2 1.73 2 7.39 7 9.20 5 4.69 8 13.8 13 18.1 12 4.43 12 7.87 21 19.9 20 3.51 18 10.2 151 30.7 18 2.58 165 12.2 18 17.9 11 2.38 149
NNF-Local [75]39.9 5.07 38 10.1 53 2.00 14 6.40 10 10.0 20 2.08 5 5.69 29 9.00 27 1.73 2 8.66 60 14.5 109 5.10 52 17.6 34 23.8 42 5.07 36 10.4 102 25.8 99 3.74 47 8.66 29 37.5 47 2.45 16 13.9 39 21.6 44 2.16 3
PH-Flow [99]40.6 5.20 69 10.7 82 2.00 14 6.45 16 10.3 23 2.08 5 5.69 29 9.38 39 1.73 2 8.19 16 11.9 23 5.07 25 17.7 48 24.0 53 5.03 32 10.6 119 26.5 120 3.70 21 8.68 36 38.8 86 2.45 16 14.0 48 21.7 50 2.16 3
NN-field [71]41.6 5.07 38 10.4 68 2.00 14 6.45 16 10.0 20 2.08 5 5.97 83 9.00 27 1.73 2 8.76 79 15.0 124 5.10 52 17.6 34 23.7 39 5.07 36 10.1 78 25.0 75 3.74 47 8.54 22 36.9 37 2.45 16 13.9 39 21.6 44 2.16 3
MPRN [151]44.6 4.43 25 8.35 26 2.08 86 7.39 81 10.8 29 2.16 80 6.06 130 10.4 109 2.00 114 8.70 68 12.4 35 4.97 20 16.7 22 22.2 22 4.83 24 8.23 22 20.5 21 3.70 21 8.81 46 33.2 25 2.45 16 12.4 22 18.9 23 2.16 3
NNF-EAC [101]45.0 5.35 106 10.0 49 2.08 86 7.05 61 11.6 53 2.08 5 6.00 84 9.35 36 1.73 2 8.35 27 12.4 35 5.23 121 17.7 48 23.9 50 5.07 36 9.47 32 22.9 30 3.70 21 8.83 49 37.0 39 2.45 16 14.0 48 21.6 44 2.16 3
IROF++ [58]46.3 5.23 90 10.8 91 2.00 14 6.88 47 11.5 50 2.08 5 6.00 84 10.0 58 1.73 2 8.19 16 11.9 23 5.07 25 17.9 73 24.4 81 5.10 60 9.49 34 24.2 52 3.74 47 9.09 83 37.2 44 2.45 16 14.0 48 22.1 65 2.16 3
SepConv-v1 [125]48.4 3.87 11 8.50 27 1.73 1 7.05 61 11.4 43 2.16 80 3.46 18 6.56 23 2.00 114 8.58 54 12.6 45 5.26 139 17.5 31 23.6 33 4.97 27 8.35 25 22.4 28 3.70 21 8.08 17 33.3 26 2.52 140 12.8 25 19.1 24 2.38 149
SuperSlomo [130]51.6 4.24 23 7.53 20 2.16 123 7.14 67 11.4 43 2.71 165 4.36 22 6.45 22 2.00 114 8.27 24 11.3 19 5.10 52 16.7 22 22.2 22 4.80 23 8.29 23 21.0 24 3.74 47 8.60 25 32.7 23 2.52 140 12.6 23 19.1 24 2.38 149
DeepFlow2 [106]52.6 5.07 38 9.85 44 2.08 86 7.53 95 13.1 99 2.16 80 5.69 29 10.0 58 1.73 2 8.83 99 13.4 74 5.10 52 17.6 34 23.7 39 5.20 101 9.24 30 23.0 31 3.74 47 9.00 66 37.9 60 2.45 16 13.9 39 21.5 40 2.16 3
DF-Auto [113]53.0 5.03 35 8.87 28 2.16 123 7.72 103 13.1 99 2.38 133 5.69 29 9.20 35 1.73 2 8.68 63 12.5 40 5.10 52 17.4 29 23.4 29 5.16 91 9.47 32 24.0 44 3.74 47 8.98 63 38.4 73 2.45 16 14.0 48 21.8 54 2.16 3
COFM [59]53.0 5.07 38 10.7 82 2.00 14 6.86 46 11.4 43 2.08 5 5.69 29 9.75 49 1.73 2 8.35 27 12.5 40 5.07 25 18.1 98 24.7 101 5.03 32 11.0 148 27.5 150 3.70 21 8.06 16 39.1 90 2.45 16 14.4 102 22.7 96 2.16 3
TOF-M [150]53.2 4.24 23 8.10 25 1.91 7 7.33 74 11.6 53 2.52 156 4.36 22 6.95 24 2.00 114 8.43 44 11.7 22 5.07 25 16.9 26 22.6 27 4.97 27 8.74 27 21.2 25 3.74 47 9.47 118 31.8 22 2.58 165 13.2 27 19.7 27 2.38 149
WLIF-Flow [91]54.5 5.10 59 10.2 59 2.00 14 7.00 60 11.9 67 2.08 5 5.69 29 9.68 42 1.73 2 8.29 25 12.2 30 5.23 121 17.8 59 24.0 53 5.10 60 10.6 119 26.6 124 3.83 139 8.83 49 37.5 47 2.45 16 14.1 63 21.9 62 2.16 3
MS-PFT [159]55.2 4.43 25 7.94 23 1.91 7 6.95 53 10.7 27 2.45 148 3.74 20 6.06 20 2.08 175 9.57 148 12.7 50 4.97 20 13.7 11 17.8 8 4.69 20 6.73 10 15.4 6 3.74 47 9.98 145 29.5 16 2.65 177 11.6 10 17.7 10 2.38 149
Layers++ [37]55.5 5.10 59 10.1 53 2.08 86 6.45 16 9.88 16 2.08 5 5.69 29 10.0 58 1.73 2 8.37 34 12.7 50 5.10 52 18.1 98 24.9 126 5.10 60 10.7 131 28.3 164 3.74 47 8.76 39 38.0 64 2.45 16 14.1 63 21.9 62 2.16 3
LME [70]55.7 5.07 38 10.1 53 2.00 14 7.05 61 12.0 70 2.16 80 5.69 29 10.7 113 1.73 2 8.35 27 12.8 54 5.10 52 18.0 84 24.4 81 5.29 176 10.2 87 25.3 84 3.74 47 8.70 37 36.4 30 2.45 16 14.0 48 21.7 50 2.16 3
ProbFlowFields [126]55.8 5.03 35 10.7 82 2.00 14 6.68 26 11.3 40 2.08 5 5.69 29 9.47 41 1.73 2 8.52 51 13.3 73 5.20 88 18.2 124 24.9 126 5.23 158 10.5 107 26.2 114 3.74 47 8.60 25 37.7 55 2.45 16 13.8 35 21.6 44 2.16 3
nLayers [57]56.0 5.16 67 10.5 74 2.00 14 6.66 25 10.9 30 2.08 5 5.69 29 9.00 27 1.73 2 8.49 50 13.0 57 5.10 52 18.3 135 25.2 145 5.20 101 10.4 102 25.6 93 3.74 47 8.66 29 38.5 78 2.45 16 14.2 80 22.4 82 2.16 3
CombBMOF [111]56.1 5.35 106 10.5 74 2.00 14 6.83 44 11.4 43 2.08 5 5.80 79 10.0 58 1.73 2 8.83 99 14.4 103 5.10 52 17.9 73 24.3 74 5.07 36 9.88 56 24.1 48 3.70 21 10.7 163 38.3 68 2.45 16 14.0 48 21.9 62 2.16 3
DeepFlow [85]56.8 5.07 38 9.63 37 2.08 86 7.44 91 13.0 93 2.16 80 5.74 75 10.0 58 1.73 2 8.96 112 13.0 57 5.20 88 17.6 34 23.8 42 5.20 101 9.15 29 23.2 33 3.87 149 8.81 46 35.6 28 2.45 16 13.7 31 21.1 33 2.16 3
HCFN [157]56.9 5.07 38 11.0 101 2.00 14 7.14 67 12.4 76 2.08 5 5.69 29 10.0 58 1.73 2 8.39 39 13.1 65 5.07 25 17.8 59 24.2 71 5.07 36 10.2 87 23.8 41 4.51 181 9.06 81 39.9 102 2.45 16 14.2 80 22.6 89 2.16 3
FMOF [92]57.6 5.42 128 11.0 101 2.00 14 6.76 36 11.0 34 2.08 5 6.00 84 10.3 89 1.73 2 8.83 99 14.1 95 5.10 52 17.8 59 24.1 63 5.07 36 10.0 76 25.6 93 3.74 47 8.58 24 37.7 55 2.45 16 14.3 90 22.4 82 2.16 3
Sparse-NonSparse [56]58.3 5.20 69 10.7 82 2.00 14 6.78 39 11.6 53 2.08 5 5.69 29 10.0 58 1.73 2 8.43 44 12.5 40 5.07 25 18.1 98 24.7 101 5.10 60 10.5 107 26.7 127 3.74 47 8.76 39 42.1 138 2.45 16 14.3 90 23.0 113 2.16 3
IROF-TV [53]58.4 5.20 69 10.7 82 2.08 86 7.05 61 11.9 67 2.08 5 6.00 84 10.3 89 1.73 2 8.37 34 12.6 45 5.16 76 17.8 59 24.1 63 5.23 158 10.1 78 25.0 75 3.70 21 9.04 76 39.1 90 2.45 16 13.7 31 21.0 31 2.16 3
PRAFlow_RVC [178]58.6 5.20 69 12.1 146 2.00 14 6.95 53 11.6 53 2.08 5 5.69 29 9.15 34 1.73 2 8.72 73 14.4 103 5.20 88 17.7 48 24.0 53 5.20 101 9.81 46 24.7 64 3.74 47 8.76 39 36.0 29 2.45 16 14.8 140 24.2 152 2.16 3
Aniso. Huber-L1 [22]59.1 5.26 92 10.0 49 2.08 86 8.81 141 14.5 144 2.16 80 6.00 84 9.75 49 1.73 2 8.72 73 13.0 57 5.16 76 17.6 34 23.8 42 5.10 60 9.87 55 23.2 33 3.70 21 9.26 99 37.8 57 2.45 16 13.8 35 21.0 31 2.16 3
FlowFields [108]59.3 5.10 59 11.1 112 2.00 14 6.88 47 11.5 50 2.08 5 5.69 29 10.0 58 1.73 2 8.76 79 14.9 119 5.20 88 18.0 84 24.4 81 5.16 91 10.3 95 25.8 99 3.74 47 8.76 39 37.8 57 2.45 16 14.1 63 22.5 87 2.16 3
TV-L1-MCT [64]59.5 5.48 145 11.4 126 2.00 14 7.35 77 13.1 99 2.08 5 5.48 27 10.3 89 1.73 2 8.35 27 12.4 35 5.07 25 18.3 135 25.3 150 5.10 60 9.49 34 23.5 37 3.79 118 8.81 46 39.2 94 2.45 16 13.7 31 21.1 33 2.16 3
Brox et al. [5]60.1 5.20 69 9.83 41 2.00 14 7.62 101 12.6 80 2.16 80 6.00 84 10.2 85 2.00 114 8.76 79 12.6 45 5.07 25 17.5 31 23.6 33 5.16 91 10.1 78 25.3 84 3.74 47 9.00 66 40.1 104 2.45 16 13.8 35 21.3 38 2.16 3
ComponentFusion [94]60.2 5.07 38 11.2 119 2.00 14 6.81 43 11.6 53 2.08 5 5.72 74 9.81 53 1.73 2 8.37 34 13.2 70 5.07 25 18.1 98 24.7 101 5.10 60 9.90 57 24.9 71 3.74 47 9.20 96 44.1 158 2.45 16 14.2 80 23.3 129 2.16 3
SegFlow [156]60.2 5.07 38 11.1 112 2.00 14 6.95 53 11.6 53 2.08 5 5.74 75 10.0 58 1.73 2 8.70 68 15.0 124 5.16 76 18.1 98 24.7 101 5.20 101 10.1 78 24.9 71 3.74 47 9.13 89 37.6 51 2.45 16 14.0 48 22.1 65 2.16 3
MDP-Flow [26]60.9 5.03 35 9.95 47 2.00 14 6.68 26 11.3 40 2.08 5 5.69 29 9.04 32 1.73 2 8.89 107 13.7 81 5.20 88 17.8 59 24.2 71 5.20 101 11.3 161 27.9 157 3.74 47 9.27 103 39.3 96 2.45 16 14.1 63 22.3 78 2.16 3
JOF [136]61.0 5.35 106 10.8 91 2.08 86 6.68 26 10.9 30 2.08 5 5.69 29 9.68 42 1.73 2 8.39 39 12.5 40 5.20 88 18.1 98 24.7 101 5.20 101 10.6 119 27.1 138 3.74 47 8.66 29 37.6 51 2.45 16 14.3 90 22.5 87 2.16 3
2DHMM-SAS [90]63.9 5.42 128 11.2 119 2.00 14 7.90 115 13.7 120 2.08 5 5.60 28 9.85 54 1.73 2 8.35 27 12.2 30 5.10 52 18.0 84 24.6 99 5.10 60 9.93 61 25.7 96 3.74 47 8.96 58 39.8 101 2.45 16 14.4 102 23.0 113 2.16 3
PGM-C [118]64.0 5.07 38 10.9 98 2.00 14 6.93 51 11.6 53 2.08 5 6.00 84 10.3 89 1.73 2 8.76 79 15.2 129 5.16 76 18.0 84 24.7 101 5.20 101 9.97 69 24.8 69 3.74 47 9.00 66 40.1 104 2.45 16 14.1 63 22.7 96 2.16 3
FlowFields+ [128]64.2 5.10 59 11.1 112 2.00 14 6.78 39 11.3 40 2.08 5 5.69 29 10.0 58 1.73 2 8.70 68 14.9 119 5.16 76 18.2 124 24.9 126 5.20 101 10.4 102 26.3 117 3.74 47 8.79 44 38.6 82 2.45 16 14.1 63 22.7 96 2.16 3
CPM-Flow [114]65.7 5.07 38 10.9 98 2.00 14 6.95 53 11.6 53 2.08 5 5.80 79 10.0 58 1.73 2 9.00 119 15.9 146 5.20 88 18.1 98 24.7 101 5.20 101 9.81 46 24.3 54 3.79 118 9.26 99 38.3 68 2.45 16 14.0 48 22.2 72 2.16 3
CLG-TV [48]65.9 5.20 69 9.49 33 2.08 86 8.43 131 14.3 138 2.16 80 6.00 84 10.1 81 2.00 114 8.76 79 13.1 65 5.20 88 17.6 34 23.8 42 5.10 60 9.59 42 23.1 32 3.74 47 9.20 96 38.4 73 2.45 16 14.0 48 21.5 40 2.16 3
HAST [107]66.0 5.07 38 10.5 74 2.00 14 6.68 26 10.7 27 2.08 5 6.00 84 10.3 89 1.73 2 8.29 25 12.4 35 5.00 23 18.4 146 25.3 150 5.03 32 11.0 148 30.7 176 3.70 21 8.60 25 41.8 131 2.45 16 14.9 148 23.9 146 2.16 3
ALD-Flow [66]66.2 5.20 69 10.7 82 2.08 86 7.35 77 12.9 88 2.16 80 6.00 84 10.1 81 1.73 2 8.39 39 13.0 57 5.16 76 17.9 73 24.3 74 5.20 101 9.56 39 23.5 37 3.79 118 8.79 44 36.8 35 2.45 16 14.5 115 23.0 113 2.16 3
VCN_RVC [179]66.9 5.35 106 13.3 159 2.00 14 6.88 47 11.4 43 2.08 5 6.00 84 11.5 144 1.73 2 8.70 68 15.5 137 5.16 76 18.1 98 24.7 101 5.10 60 9.95 63 24.2 52 3.70 21 9.00 66 38.0 64 2.45 16 14.1 63 23.0 113 2.16 3
S2F-IF [121]67.0 5.10 59 11.6 137 2.00 14 6.78 39 11.4 43 2.08 5 5.69 29 10.3 89 1.73 2 8.74 75 15.2 129 5.07 25 18.3 135 25.1 140 5.20 101 10.5 107 26.1 109 3.74 47 9.02 74 38.5 78 2.45 16 14.1 63 22.6 89 2.16 3
Ramp [62]67.9 5.29 99 10.8 91 2.00 14 6.83 44 11.6 53 2.08 5 5.69 29 10.1 81 1.73 2 8.35 27 12.2 30 5.07 25 18.1 98 24.7 101 5.10 60 10.9 142 27.8 156 3.79 118 8.83 49 43.0 149 2.45 16 14.5 115 23.2 123 2.16 3
Second-order prior [8]68.2 5.20 69 9.83 41 2.08 86 8.43 131 14.5 144 2.08 5 6.35 139 11.0 131 2.00 114 8.83 99 13.8 88 5.07 25 17.7 48 23.8 42 5.07 36 9.70 44 24.1 48 3.74 47 9.33 107 38.4 73 2.45 16 14.0 48 21.8 54 2.16 3
RAFT-TF_RVC [180]68.5 5.10 59 13.0 155 2.00 14 6.76 36 11.4 43 2.08 5 5.69 29 9.68 42 1.73 2 8.68 63 14.6 111 5.10 52 17.9 73 24.3 74 5.10 60 10.7 131 26.8 130 4.55 183 8.66 29 36.8 35 2.45 16 14.7 134 25.3 165 2.16 3
EAI-Flow [147]69.6 5.20 69 11.2 119 2.08 86 7.39 81 12.4 76 2.16 80 6.00 84 10.8 126 1.73 2 8.81 93 14.6 111 5.07 25 18.1 98 24.8 115 5.16 91 9.83 48 24.0 44 3.74 47 9.43 117 38.3 68 2.45 16 13.7 31 21.5 40 2.16 3
CBF [12]70.3 5.00 29 9.40 31 2.08 86 7.77 108 13.0 93 2.16 80 6.00 84 9.68 42 1.73 2 8.68 63 12.5 40 5.35 158 17.6 34 23.4 29 5.20 101 9.85 53 24.3 54 3.74 47 9.11 87 39.3 96 2.52 140 14.0 48 21.1 33 2.38 149
SIOF [67]70.9 5.42 128 10.4 68 2.08 86 8.83 142 15.0 158 2.38 133 5.69 29 10.4 109 1.73 2 8.68 63 13.1 65 5.20 88 17.3 28 23.2 28 5.07 36 9.83 48 23.6 39 3.74 47 9.00 66 36.9 37 2.45 16 14.3 90 22.1 65 2.31 131
DPOF [18]71.0 5.35 106 11.7 139 2.08 86 6.56 22 10.4 24 2.08 5 6.00 84 9.71 48 1.91 109 8.76 79 14.4 103 5.20 88 17.7 48 24.1 63 5.07 36 10.3 95 26.7 127 3.70 21 9.33 107 39.1 90 2.45 16 14.4 102 22.8 102 2.16 3
p-harmonic [29]71.0 5.07 38 9.98 48 2.00 14 8.68 137 14.4 140 2.16 80 6.00 84 10.7 113 1.91 109 9.20 131 13.7 81 5.20 88 17.8 59 24.0 53 5.10 60 9.90 57 23.7 40 3.74 47 9.61 129 38.5 78 2.45 16 14.0 48 21.7 50 2.16 3
Local-TV-L1 [65]71.5 5.20 69 9.38 30 2.16 123 8.96 146 14.5 144 2.38 133 5.69 29 9.35 36 1.73 2 8.70 68 13.0 57 5.45 165 17.6 34 23.8 42 5.16 91 9.54 38 24.0 44 4.08 174 8.76 39 37.2 44 2.45 16 13.6 30 20.9 30 2.31 131
ProFlow_ROB [142]71.7 5.07 38 10.9 98 2.00 14 7.33 74 12.7 82 2.16 80 5.69 29 9.98 57 1.73 2 8.60 57 14.1 95 5.20 88 18.3 135 25.2 145 5.20 101 9.52 37 23.4 36 3.70 21 9.49 123 42.0 136 2.45 16 14.5 115 23.6 139 2.16 3
OFLAF [78]72.0 5.07 38 10.6 79 2.00 14 6.48 20 10.5 25 2.08 5 5.69 29 10.0 58 1.73 2 8.37 34 12.6 45 5.07 25 18.4 146 25.4 157 5.20 101 10.9 142 27.4 148 3.74 47 9.59 128 44.9 163 2.45 16 15.1 153 24.1 149 2.16 3
FC-2Layers-FF [74]72.3 5.26 92 11.0 101 2.00 14 6.40 10 9.88 16 2.08 5 5.69 29 10.3 89 1.73 2 8.39 39 12.8 54 5.10 52 18.2 124 25.0 134 5.20 101 11.0 148 28.1 160 3.79 118 8.91 56 42.8 144 2.45 16 14.5 115 23.0 113 2.16 3
LSM [39]72.4 5.35 106 11.5 131 2.00 14 6.98 57 11.9 67 2.08 5 5.80 79 10.7 113 1.73 2 8.58 54 13.4 74 5.07 25 18.1 98 24.9 126 5.10 60 10.6 119 27.1 138 3.74 47 8.83 49 42.2 140 2.45 16 14.4 102 23.0 113 2.16 3
AGIF+OF [84]72.4 5.42 128 11.1 112 2.00 14 6.98 57 11.8 64 2.08 5 5.69 29 10.0 58 1.73 2 8.43 44 12.8 54 5.07 25 18.5 154 25.2 145 5.20 101 10.8 139 27.6 151 3.74 47 8.98 63 37.9 60 2.45 16 14.7 134 23.4 133 2.16 3
ComplOF-FED-GPU [35]72.6 5.20 69 11.1 112 2.00 14 7.19 72 12.6 80 2.08 5 6.35 139 10.0 58 2.00 114 8.68 63 14.0 94 5.10 52 17.9 73 24.5 89 5.10 60 9.97 69 25.1 78 3.74 47 9.40 112 38.8 86 2.45 16 14.5 115 23.2 123 2.16 3
LDOF [28]73.2 5.35 106 9.83 41 2.16 123 7.94 116 12.1 71 2.52 156 6.00 84 10.3 89 2.00 114 8.91 110 13.6 79 5.23 121 17.6 34 23.6 33 5.20 101 9.49 34 24.5 59 3.74 47 8.96 58 37.9 60 2.45 16 14.0 48 21.8 54 2.16 3
Classic+NL [31]73.5 5.35 106 11.0 101 2.08 86 6.98 57 11.7 62 2.08 5 5.69 29 10.2 85 1.73 2 8.43 44 12.4 35 5.20 88 18.1 98 24.8 115 5.10 60 10.6 119 26.8 130 3.79 118 8.83 49 42.9 145 2.45 16 14.4 102 22.9 109 2.16 3
OAR-Flow [123]74.7 5.20 69 10.7 82 2.08 86 7.44 91 13.0 93 2.16 80 5.74 75 10.0 58 1.73 2 8.35 27 13.0 57 5.10 52 18.1 98 24.9 126 5.23 158 10.2 87 24.7 64 3.74 47 9.54 125 39.4 99 2.45 16 14.4 102 22.7 96 2.16 3
RNLOD-Flow [119]74.8 5.20 69 11.0 101 2.00 14 7.53 95 13.4 108 2.08 5 6.00 84 11.0 131 1.73 2 8.52 51 13.0 57 5.07 25 18.2 124 25.0 134 5.10 60 10.6 119 26.9 134 3.74 47 8.96 58 38.4 73 2.45 16 14.9 148 23.5 136 2.16 3
RFlow [88]75.1 5.07 38 10.2 59 2.08 86 8.58 135 14.7 150 2.08 5 6.00 84 10.3 89 1.73 2 8.91 110 14.4 103 5.20 88 17.7 48 23.9 50 5.10 60 9.95 63 25.4 87 3.70 21 9.13 89 40.4 109 2.45 16 14.3 90 22.6 89 2.31 131
TC/T-Flow [77]75.9 5.45 138 11.5 131 2.00 14 7.42 87 13.0 93 2.08 5 5.69 29 9.76 51 1.73 2 8.60 57 13.7 81 5.16 76 18.3 135 24.9 126 5.20 101 10.1 78 24.9 71 3.74 47 9.75 135 42.6 141 2.45 16 14.5 115 22.6 89 2.16 3
TF+OM [98]76.6 5.00 29 10.2 59 2.08 86 6.93 51 11.7 62 2.16 80 5.69 29 10.5 111 1.73 2 8.81 93 14.6 111 5.20 88 18.0 84 24.4 81 5.20 101 9.95 63 26.1 109 3.79 118 9.09 83 41.0 116 2.45 16 14.1 63 21.8 54 2.38 149
EpicFlow [100]77.2 5.07 38 11.0 101 2.00 14 7.39 81 12.9 88 2.08 5 5.80 79 10.3 89 1.73 2 8.85 105 15.5 137 5.20 88 18.1 98 24.8 115 5.20 101 10.2 87 25.1 78 3.74 47 9.33 107 40.4 109 2.45 16 14.5 115 24.1 149 2.16 3
DMF_ROB [135]78.0 5.20 69 10.8 91 2.08 86 7.85 111 13.4 108 2.08 5 6.35 139 11.6 146 2.00 114 9.02 120 14.5 109 5.16 76 17.8 59 24.4 81 5.20 101 9.83 48 24.3 54 3.74 47 9.04 76 38.3 68 2.45 16 14.1 63 22.4 82 2.16 3
S2D-Matching [83]78.3 5.35 106 11.2 119 2.00 14 7.75 106 13.5 112 2.08 5 5.69 29 10.0 58 1.73 2 8.37 34 12.6 45 5.20 88 18.3 135 25.2 145 5.07 36 11.0 148 27.7 155 3.79 118 9.09 83 40.3 107 2.45 16 14.4 102 23.0 113 2.16 3
TC-Flow [46]78.3 5.07 38 10.8 91 2.00 14 7.39 81 13.2 104 2.16 80 6.00 84 10.3 89 1.73 2 8.66 60 13.7 81 5.23 121 18.2 124 25.0 134 5.20 101 10.2 87 24.5 59 3.79 118 9.04 76 38.1 66 2.45 16 14.5 115 23.5 136 2.16 3
F-TV-L1 [15]79.2 5.35 106 10.3 65 2.16 123 8.83 142 14.6 149 2.16 80 6.00 84 10.3 89 2.00 114 8.76 79 13.2 70 5.26 139 17.6 34 23.8 42 5.03 32 9.57 41 23.2 33 3.79 118 9.18 93 37.6 51 2.45 16 13.8 35 21.2 36 2.31 131
Fusion [6]80.6 5.20 69 10.4 68 2.00 14 7.14 67 11.8 64 2.08 5 5.74 75 9.68 42 1.73 2 9.33 134 14.2 97 5.20 88 18.3 135 24.7 101 5.07 36 11.6 166 28.1 160 3.70 21 9.63 130 41.4 124 2.45 16 15.3 166 24.2 152 2.16 3
LFNet_ROB [145]82.3 5.35 106 13.4 160 2.00 14 7.72 103 12.9 88 2.16 80 6.00 84 11.3 138 1.73 2 8.98 118 15.9 146 5.07 25 18.1 98 24.8 115 5.10 60 11.0 148 28.1 160 3.74 47 9.09 83 37.6 51 2.45 16 14.0 48 22.4 82 2.16 3
Classic++ [32]83.6 5.20 69 10.3 65 2.08 86 7.94 116 13.8 122 2.08 5 6.00 84 10.1 81 1.73 2 8.89 107 13.7 81 5.23 121 18.0 84 24.5 89 5.10 60 10.3 95 25.8 99 3.87 149 9.13 89 40.1 104 2.45 16 14.2 80 22.2 72 2.31 131
AggregFlow [95]83.9 5.45 138 13.8 164 2.08 86 7.44 91 13.1 99 2.16 80 5.69 29 9.95 56 1.73 2 9.15 128 16.1 148 5.10 52 18.0 84 24.5 89 5.20 101 9.90 57 24.6 62 3.83 139 8.98 63 40.7 112 2.45 16 14.4 102 23.0 113 2.16 3
Sparse Occlusion [54]84.0 5.26 92 10.5 74 2.08 86 8.04 119 14.4 140 2.08 5 6.00 84 10.0 58 1.73 2 8.83 99 13.7 81 5.20 88 18.1 98 24.7 101 5.20 101 11.0 148 26.5 120 3.74 47 9.42 113 42.0 136 2.45 16 14.4 102 22.8 102 2.16 3
FESL [72]84.1 5.42 128 11.0 101 2.00 14 7.05 61 11.8 64 2.08 5 5.69 29 10.7 113 1.73 2 8.81 93 13.5 77 5.20 88 18.4 146 25.1 140 5.20 101 11.0 148 27.0 137 3.74 47 9.06 81 42.9 145 2.45 16 14.8 140 23.7 140 2.16 3
PMF [73]84.4 5.20 69 11.4 126 2.00 14 7.35 77 12.4 76 2.08 5 6.00 84 12.0 155 1.73 2 8.76 79 14.4 103 5.07 25 18.4 146 25.0 134 5.10 60 10.2 87 25.8 99 3.87 149 9.04 76 41.3 122 2.45 16 15.2 162 24.5 157 2.16 3
Classic+CPF [82]84.8 5.35 106 11.3 124 2.00 14 7.07 66 12.1 71 2.08 5 5.69 29 10.5 111 1.73 2 8.43 44 12.7 50 5.07 25 18.7 166 25.7 167 5.20 101 11.2 158 28.7 167 3.74 47 9.42 113 42.9 145 2.45 16 15.1 153 24.2 152 2.16 3
Modified CLG [34]84.9 5.07 38 9.49 33 2.16 123 9.42 160 14.2 136 2.65 162 6.00 84 11.5 144 2.00 114 9.15 128 14.3 99 5.10 52 17.7 48 23.9 50 5.10 60 10.1 78 24.7 64 3.74 47 9.31 106 37.5 47 2.45 16 14.1 63 21.8 54 2.31 131
FF++_ROB [141]86.0 5.07 38 11.5 131 2.00 14 7.16 71 12.2 73 2.08 5 6.00 84 10.3 89 1.73 2 8.96 112 16.4 152 5.20 88 18.6 160 25.7 167 5.20 101 10.6 119 26.8 130 3.92 164 9.00 66 39.1 90 2.45 16 14.2 80 22.9 109 2.16 3
TCOF [69]87.1 5.35 106 10.7 82 2.00 14 9.27 154 15.4 165 2.16 80 5.69 29 10.2 85 1.73 2 8.74 75 13.1 65 5.23 121 17.7 48 23.8 42 5.07 36 10.7 131 26.6 124 3.70 21 10.0 146 44.7 162 2.45 16 14.6 129 22.9 109 2.38 149
OFH [38]87.8 5.35 106 11.0 101 2.08 86 8.06 122 13.7 120 2.08 5 6.00 84 11.6 146 1.73 2 8.58 54 13.9 92 5.07 25 18.2 124 24.9 126 5.16 91 10.3 95 25.1 78 3.74 47 9.88 141 42.7 143 2.45 16 14.8 140 24.7 159 2.16 3
SVFilterOh [109]88.5 5.20 69 10.6 79 2.00 14 6.73 34 11.0 34 2.08 5 6.00 84 10.0 58 1.73 2 8.76 79 13.8 88 5.26 139 18.4 146 25.3 150 5.26 169 10.6 119 28.0 158 3.74 47 8.45 21 39.2 94 2.52 140 14.7 134 23.3 129 2.31 131
C-RAFT_RVC [182]88.7 5.94 166 15.4 171 2.16 123 7.53 95 12.7 82 2.16 80 6.00 84 11.3 138 1.73 2 9.09 123 15.6 139 5.20 88 17.8 59 24.0 53 5.07 36 10.5 107 26.4 118 3.74 47 9.18 93 37.5 47 2.45 16 14.5 115 23.8 143 2.16 3
SRR-TVOF-NL [89]88.8 5.45 138 12.1 146 2.08 86 7.77 108 13.5 112 2.16 80 6.00 84 10.3 89 1.73 2 9.26 132 14.7 115 5.07 25 18.1 98 24.6 99 5.10 60 10.4 102 26.6 124 3.70 21 9.42 113 38.5 78 2.45 16 15.1 153 23.9 146 2.16 3
FlowNetS+ft+v [110]88.8 5.26 92 10.1 53 2.16 123 9.11 150 14.5 144 2.45 148 6.00 84 10.3 89 2.00 114 8.96 112 13.5 77 5.26 139 17.8 59 24.1 63 5.23 158 9.76 45 23.9 43 3.74 47 9.38 111 41.6 127 2.45 16 14.1 63 22.2 72 2.16 3
Efficient-NL [60]89.5 5.35 106 10.7 82 2.00 14 7.42 87 13.0 93 2.08 5 6.35 139 10.7 113 2.00 114 8.81 93 13.4 74 5.10 52 18.1 98 24.7 101 5.10 60 11.2 158 27.6 151 3.70 21 9.47 118 43.6 155 2.45 16 15.1 153 23.8 143 2.16 3
BlockOverlap [61]89.7 5.20 69 9.29 29 2.16 123 8.74 139 14.1 131 2.65 162 6.00 84 9.35 36 2.00 114 8.52 51 11.9 23 5.60 172 17.8 59 24.0 53 5.32 178 9.83 48 25.0 75 4.04 169 8.83 49 37.1 41 2.52 140 13.5 29 20.6 29 2.38 149
EPPM w/o HM [86]89.8 5.23 90 12.6 151 2.00 14 7.39 81 13.0 93 2.08 5 6.35 139 14.0 175 1.91 109 8.83 99 15.3 133 5.10 52 18.0 84 24.5 89 5.10 60 10.5 107 27.6 151 3.74 47 9.11 87 41.9 132 2.45 16 14.5 115 23.2 123 2.16 3
CRTflow [81]90.5 5.29 99 10.5 74 2.16 123 8.43 131 14.5 144 2.16 80 6.35 139 11.1 137 2.00 114 8.64 59 13.0 57 5.29 149 18.0 84 24.5 89 5.20 101 9.68 43 23.8 41 3.74 47 9.00 66 40.9 114 2.45 16 14.1 63 22.2 72 2.31 131
PWC-Net_RVC [143]90.5 5.35 106 13.8 164 2.00 14 7.55 99 13.3 106 2.08 5 6.00 84 11.3 138 1.73 2 8.76 79 15.7 141 5.07 25 18.6 160 25.9 172 5.20 101 10.5 107 26.9 134 3.83 139 9.00 66 38.6 82 2.45 16 14.3 90 23.7 140 2.16 3
3DFlow [133]90.8 5.42 128 11.5 131 2.00 14 7.14 67 12.3 74 2.08 5 6.22 138 10.0 58 1.73 2 8.66 60 13.6 79 5.23 121 17.9 73 24.5 89 5.20 101 12.3 180 29.0 169 3.79 118 10.6 161 41.7 129 2.45 16 14.8 140 23.2 123 2.16 3
MLDP_OF [87]91.6 5.32 103 11.1 112 2.00 14 7.55 99 13.6 117 2.08 5 5.69 29 10.0 58 1.73 2 8.76 79 13.1 65 5.26 139 18.0 84 24.5 89 5.20 101 11.0 148 26.9 134 4.08 174 9.26 99 38.2 67 2.52 140 14.4 102 22.6 89 2.38 149
Steered-L1 [116]92.7 5.07 38 9.81 40 2.00 14 7.35 77 12.8 87 2.16 80 6.35 139 10.3 89 2.00 114 9.31 133 14.3 99 5.35 158 18.2 124 24.7 101 5.07 36 10.2 87 25.7 96 3.79 118 9.33 107 40.4 109 2.45 16 14.6 129 22.8 102 2.31 131
2D-CLG [1]92.9 5.16 67 10.0 49 2.16 123 9.90 166 14.2 136 2.83 172 6.35 139 10.7 113 2.00 114 10.0 157 15.2 129 5.10 52 17.7 48 24.1 63 5.20 101 10.1 78 24.1 48 3.74 47 9.81 136 43.6 155 2.45 16 14.1 63 21.8 54 2.16 3
IAOF [50]94.1 5.60 153 11.0 101 2.16 123 12.0 182 16.9 183 2.52 156 5.69 29 11.0 131 2.00 114 9.76 152 14.3 99 5.20 88 17.7 48 24.0 53 5.07 36 10.0 76 25.2 82 3.74 47 9.47 118 41.4 124 2.45 16 14.2 80 22.1 65 2.16 3
Occlusion-TV-L1 [63]94.5 5.20 69 10.2 59 2.08 86 8.89 144 15.3 163 2.16 80 6.00 84 10.3 89 2.00 114 9.15 128 15.4 134 5.26 139 17.6 34 23.7 39 5.10 60 9.98 72 25.5 89 3.87 149 10.3 155 39.3 96 2.52 140 14.1 63 22.3 78 2.16 3
Complementary OF [21]95.0 5.20 69 12.0 143 2.00 14 7.19 72 12.9 88 2.08 5 6.68 159 10.8 126 2.00 114 8.76 79 14.6 111 5.16 76 18.2 124 25.2 145 5.10 60 10.3 95 25.9 103 3.74 47 9.97 144 42.6 141 2.45 16 15.6 171 28.0 176 2.16 3
CostFilter [40]97.0 5.32 103 13.2 158 2.00 14 7.33 74 12.3 74 2.08 5 6.06 130 13.5 173 1.73 2 8.96 112 16.1 148 5.07 25 18.6 160 25.6 166 5.16 91 9.98 72 24.8 69 4.04 169 9.20 96 43.5 154 2.45 16 15.1 153 24.9 162 2.16 3
Adaptive [20]97.1 5.32 103 10.3 65 2.16 123 9.29 157 15.4 165 2.16 80 6.00 84 10.7 113 1.73 2 8.81 93 13.8 88 5.20 88 17.9 73 24.3 74 5.07 36 10.4 102 26.0 105 3.79 118 9.83 137 44.6 160 2.45 16 14.5 115 22.8 102 2.31 131
Ad-TV-NDC [36]98.0 5.66 156 9.88 45 2.52 176 10.1 170 15.1 159 2.71 165 6.00 84 10.7 113 1.73 2 9.49 145 14.2 97 5.35 158 17.7 48 24.0 53 5.20 101 9.56 39 24.0 44 3.87 149 9.56 126 38.6 82 2.45 16 13.9 39 21.2 36 2.38 149
HBM-GC [103]99.4 5.35 106 10.6 79 2.16 123 7.42 87 13.4 108 2.16 80 5.69 29 9.00 27 1.73 2 8.74 75 13.2 70 5.26 139 18.6 160 25.5 163 5.26 169 11.8 173 31.5 180 3.83 139 8.83 49 41.1 118 2.45 16 14.3 90 22.2 72 2.31 131
BriefMatch [122]99.4 5.29 99 11.4 126 2.08 86 7.44 91 12.7 82 2.16 80 6.38 157 9.93 55 2.00 114 9.83 154 14.9 119 5.83 179 18.0 84 24.4 81 5.20 101 10.5 107 27.3 145 4.32 179 9.04 76 37.9 60 2.45 16 14.3 90 22.8 102 2.16 3
Black & Anandan [4]99.7 5.45 138 10.1 53 2.16 123 10.2 173 15.3 163 2.45 148 6.68 159 11.3 138 2.00 114 10.2 159 15.6 139 5.20 88 17.8 59 24.0 53 5.16 91 9.83 48 24.7 64 3.74 47 10.2 151 41.9 132 2.45 16 14.2 80 21.8 54 2.16 3
LiteFlowNet [138]100.2 5.45 138 14.5 168 2.00 14 7.42 87 12.7 82 2.08 5 5.69 29 13.0 167 1.73 2 9.71 151 23.2 179 5.29 149 18.4 146 25.4 157 5.20 101 10.8 139 27.1 138 3.70 21 10.2 151 43.0 149 2.45 16 14.3 90 23.2 123 2.16 3
CNN-flow-warp+ref [115]100.4 5.00 29 9.59 36 2.16 123 8.35 129 13.6 117 2.16 80 6.35 139 11.8 154 2.00 114 10.6 165 15.4 134 5.48 169 17.8 59 24.3 74 5.23 158 9.95 63 24.3 54 3.83 139 9.83 137 44.6 160 2.45 16 14.2 80 22.3 78 2.16 3
LSM_FLOW_RVC [183]102.8 5.74 159 16.9 175 2.08 86 8.12 123 14.0 129 2.16 80 6.00 84 13.0 167 1.73 2 9.38 136 18.9 166 5.16 76 18.2 124 25.1 140 5.10 60 10.5 107 25.5 89 3.74 47 9.63 130 41.1 118 2.45 16 14.4 102 24.0 148 2.16 3
HBpMotionGpu [43]103.1 5.48 145 10.8 91 2.38 168 10.1 170 15.4 165 2.71 165 5.69 29 10.0 58 1.73 2 9.40 138 16.2 151 5.23 121 17.9 73 24.3 74 5.20 101 10.5 107 26.4 118 3.83 139 8.96 58 37.8 57 2.45 16 14.3 90 22.6 89 2.38 149
TriFlow [93]103.1 5.26 92 12.0 143 2.16 123 8.39 130 14.4 140 2.38 133 6.00 84 11.0 131 1.73 2 9.02 120 15.4 134 5.10 52 18.5 154 25.4 157 5.20 101 10.6 119 27.3 145 3.74 47 9.26 99 39.7 100 2.45 16 14.6 129 23.1 121 2.16 3
TVL1_RVC [176]103.8 5.42 128 9.88 45 2.38 168 10.9 176 15.8 178 2.71 165 6.00 84 10.7 113 2.00 114 9.83 154 14.9 119 5.20 88 17.8 59 24.1 63 5.20 101 10.1 78 25.9 103 3.83 139 9.85 139 44.0 157 2.45 16 14.0 48 21.8 54 2.16 3
CompactFlow_ROB [155]104.8 5.48 145 15.2 170 2.08 86 7.75 106 13.2 104 2.38 133 6.19 137 13.3 171 1.73 2 9.57 148 22.0 178 5.23 121 18.0 84 24.5 89 5.10 60 10.6 119 27.2 141 3.70 21 9.66 133 40.9 114 2.45 16 14.4 102 23.4 133 2.16 3
AdaConv-v1 [124]104.9 6.24 172 14.4 167 2.38 168 9.02 147 12.7 82 3.11 177 7.00 169 11.0 131 2.38 176 13.1 178 18.8 165 5.83 179 16.8 24 22.5 24 4.83 24 8.79 28 22.0 27 3.70 21 8.91 56 36.6 33 2.58 165 13.3 28 20.2 28 2.38 149
Nguyen [33]105.7 5.42 128 10.0 49 2.38 168 10.9 176 15.1 159 2.65 162 6.00 84 12.0 155 2.00 114 10.4 164 16.1 148 5.20 88 17.8 59 24.1 63 5.07 36 9.98 72 25.3 84 3.70 21 10.9 167 46.9 169 2.52 140 14.1 63 22.1 65 2.16 3
FlowNet2 [120]108.7 6.45 177 19.1 181 2.16 123 7.85 111 13.4 108 2.38 133 6.06 130 11.7 148 1.73 2 9.40 138 18.2 161 5.23 121 18.5 154 25.3 150 5.20 101 10.3 95 25.2 82 3.74 47 9.27 103 41.9 132 2.45 16 14.3 90 22.8 102 2.16 3
TV-L1-improved [17]109.5 5.10 59 10.2 59 2.08 86 9.20 153 15.4 165 2.16 80 6.35 139 10.3 89 2.00 114 8.85 105 13.8 88 5.23 121 18.0 84 24.4 81 5.10 60 10.6 119 26.5 120 3.79 118 9.93 143 46.9 169 2.52 140 14.3 90 22.7 96 2.38 149
ResPWCR_ROB [140]110.1 5.35 106 12.5 150 2.00 14 7.94 116 13.6 117 2.16 80 6.68 159 11.3 138 1.91 109 9.42 140 18.1 160 5.29 149 18.1 98 24.8 115 5.07 36 10.6 119 27.3 145 4.40 180 9.56 126 38.4 73 2.45 16 14.7 134 24.7 159 2.16 3
SimpleFlow [49]110.4 5.35 106 11.0 101 2.00 14 8.04 119 13.9 125 2.08 5 6.56 158 11.3 138 2.00 114 8.41 43 12.7 50 5.20 88 18.4 146 25.4 157 5.20 101 11.4 164 28.9 168 3.74 47 10.1 148 53.7 179 2.52 140 15.3 166 26.5 170 2.16 3
Bartels [41]111.5 5.35 106 11.4 126 2.16 123 7.72 103 14.0 129 2.38 133 6.00 84 10.3 89 2.00 114 9.11 124 15.0 124 5.69 174 17.6 34 23.6 33 5.45 182 10.7 131 27.2 141 4.55 183 8.96 58 36.4 30 2.65 177 14.1 63 22.1 65 2.38 149
GraphCuts [14]111.8 5.66 156 11.9 142 2.16 123 7.53 95 12.5 79 2.38 133 7.68 176 10.2 85 2.00 114 9.47 143 14.9 119 5.23 121 18.1 98 24.5 89 5.00 29 10.1 78 25.7 96 3.70 21 9.02 74 42.1 138 2.52 140 15.1 153 24.1 149 2.31 131
ContinualFlow_ROB [148]114.0 5.60 153 14.6 169 2.16 123 7.85 111 13.5 112 2.31 132 6.35 139 12.4 161 2.00 114 8.96 112 16.8 153 5.20 88 18.7 166 26.1 177 5.20 101 9.90 57 24.9 71 3.70 21 9.18 93 41.6 127 2.45 16 15.2 162 27.5 175 2.16 3
AugFNG_ROB [139]114.1 5.48 145 14.1 166 2.16 123 8.27 126 13.5 112 2.38 133 6.35 139 14.0 175 2.00 114 9.47 143 19.5 170 5.20 88 18.7 166 26.0 174 5.23 158 9.85 53 25.5 89 3.70 21 9.85 139 38.7 85 2.45 16 14.2 80 23.1 121 2.16 3
ROF-ND [105]114.5 5.74 159 10.4 68 2.00 14 8.04 119 14.1 131 2.16 80 6.06 130 10.7 113 1.73 2 10.6 165 19.9 173 5.26 139 18.1 98 24.8 115 5.20 101 11.7 169 28.6 165 3.74 47 11.1 169 41.0 116 2.52 140 15.3 166 25.3 165 2.16 3
Filter Flow [19]115.4 5.42 128 10.2 59 2.16 123 9.40 159 14.7 150 2.71 165 6.00 84 10.7 113 2.00 114 9.49 145 13.9 92 5.35 158 18.1 98 24.3 74 5.26 169 10.2 87 25.6 93 3.83 139 9.52 124 41.4 124 2.45 16 14.6 129 22.3 78 2.38 149
EPMNet [131]116.1 6.45 177 19.7 183 2.16 123 7.85 111 13.1 99 2.38 133 6.06 130 11.7 148 1.73 2 10.1 158 24.0 181 5.23 121 18.5 154 25.3 150 5.20 101 10.7 131 27.6 151 3.70 21 9.27 103 41.9 132 2.45 16 14.5 115 23.8 143 2.16 3
Shiralkar [42]116.2 5.48 145 12.7 152 2.08 86 9.06 149 14.7 150 2.08 5 6.00 84 12.8 165 2.00 114 10.7 167 19.7 171 5.20 88 18.1 98 24.8 115 5.00 29 10.8 139 26.1 109 3.87 149 10.8 166 47.5 173 2.45 16 14.9 148 25.8 168 2.16 3
IIOF-NLDP [129]116.3 5.45 138 12.0 143 2.00 14 8.12 123 14.7 150 2.08 5 6.06 130 10.0 58 1.73 2 9.13 126 14.8 118 5.32 155 18.1 98 24.8 115 5.10 60 12.2 177 29.1 170 3.87 149 12.0 177 59.6 183 2.65 177 15.2 162 24.6 158 2.16 3
Correlation Flow [76]117.3 5.42 128 11.7 139 2.00 14 8.58 135 15.4 165 2.08 5 5.69 29 9.80 52 1.73 2 8.89 107 14.7 115 5.32 155 18.1 98 24.8 115 5.32 178 12.3 180 30.3 175 3.83 139 10.5 159 48.8 175 2.52 140 14.8 140 23.7 140 2.31 131
TriangleFlow [30]117.6 5.60 153 11.6 137 2.16 123 8.50 134 14.4 140 2.08 5 6.35 139 10.7 113 2.00 114 9.42 140 15.8 143 5.23 121 18.0 84 24.5 89 5.00 29 11.1 157 27.2 141 3.74 47 10.4 156 47.2 172 2.52 140 15.6 171 26.7 171 2.16 3
Rannacher [23]118.3 5.26 92 10.8 91 2.16 123 9.27 154 15.5 172 2.16 80 6.35 139 10.9 129 2.00 114 8.76 79 14.4 103 5.23 121 17.9 73 24.4 81 5.20 101 10.5 107 26.7 127 3.79 118 9.90 142 45.9 166 2.52 140 14.4 102 23.5 136 2.38 149
IAOF2 [51]122.8 5.74 159 11.5 131 2.16 123 9.49 161 15.9 181 2.38 133 5.69 29 11.0 131 2.00 114 9.61 150 15.8 143 5.26 139 18.7 166 25.3 150 5.20 101 10.9 142 27.4 148 3.74 47 9.47 118 41.1 118 2.45 16 14.5 115 22.8 102 2.31 131
Horn & Schunck [3]123.2 5.48 145 10.4 68 2.16 123 10.5 175 15.4 165 2.52 156 6.68 159 12.0 155 2.00 114 11.5 173 17.6 159 5.23 121 17.9 73 24.0 53 5.20 101 9.93 61 24.1 48 3.79 118 11.1 169 42.9 145 2.52 140 14.5 115 22.2 72 2.38 149
OFRF [132]125.5 5.80 162 13.7 162 2.16 123 9.15 152 15.1 159 2.45 148 6.00 84 11.7 148 1.73 2 9.13 126 15.1 128 5.10 52 18.7 166 25.9 172 5.16 91 11.3 161 29.1 170 3.87 149 10.1 148 44.5 159 2.45 16 15.4 169 24.9 162 2.16 3
IRR-PWC_RVC [181]125.5 5.83 165 17.8 178 2.16 123 7.77 108 13.3 106 2.38 133 6.35 139 14.3 178 1.73 2 10.2 159 25.2 182 5.20 88 18.7 166 26.0 174 5.23 158 10.7 131 28.0 158 3.74 47 9.63 130 41.3 122 2.45 16 15.5 170 28.0 176 2.16 3
LocallyOriented [52]126.5 5.45 138 11.2 119 2.16 123 9.49 161 15.7 176 2.16 80 6.06 130 11.7 148 1.91 109 9.42 140 17.0 154 5.23 121 18.2 124 24.8 115 5.07 36 11.0 148 26.5 120 4.04 169 10.4 156 43.0 149 2.45 16 14.8 140 23.4 133 2.31 131
TI-DOFE [24]126.5 5.80 162 11.0 101 2.52 176 11.5 180 15.8 178 3.11 177 6.35 139 12.3 159 2.00 114 11.4 172 17.4 156 5.29 149 17.9 73 24.2 71 5.07 36 9.95 63 24.4 58 3.79 118 10.5 159 39.9 102 2.52 140 14.8 140 22.1 65 2.38 149
SegOF [10]128.3 5.10 59 11.4 126 2.16 123 8.29 127 13.9 125 2.38 133 7.00 169 12.1 158 2.00 114 9.81 153 21.0 174 5.20 88 18.2 124 25.1 140 5.20 101 10.9 142 26.1 109 3.79 118 10.4 156 48.4 174 2.58 165 14.7 134 25.1 164 2.16 3
SPSA-learn [13]128.6 5.29 99 10.4 68 2.16 123 9.04 148 14.1 131 2.45 148 6.68 159 11.7 148 2.00 114 10.3 163 15.8 143 5.10 52 18.4 146 25.3 150 5.20 101 10.5 107 26.8 130 3.74 47 12.3 180 58.4 181 2.71 183 17.6 180 35.0 183 2.16 3
StereoOF-V1MT [117]130.8 5.69 158 13.0 155 2.08 86 8.68 137 14.1 131 2.08 5 6.73 168 12.4 161 2.00 114 11.6 174 19.1 169 5.45 165 18.5 154 25.4 157 5.20 101 11.3 161 26.1 109 3.92 164 11.2 171 44.9 163 2.58 165 14.2 80 22.6 89 2.16 3
2bit-BM-tele [96]132.1 5.35 106 10.1 53 2.16 123 8.91 145 15.4 165 2.45 148 6.00 84 10.0 58 2.00 114 9.04 122 14.3 99 5.60 172 18.3 135 24.9 126 5.35 181 11.7 169 31.3 178 4.24 178 12.0 177 58.7 182 2.83 184 13.9 39 21.7 50 2.45 182
ACK-Prior [27]132.4 5.35 106 11.7 139 2.00 14 7.39 81 12.9 88 2.08 5 6.68 159 10.8 126 2.00 114 9.54 147 15.7 141 5.32 155 18.7 166 25.5 163 5.29 176 11.9 175 29.5 172 3.87 149 10.1 148 41.7 129 2.52 140 16.1 175 24.8 161 2.38 149
StereoFlow [44]132.8 8.68 184 20.4 184 2.45 173 10.3 174 16.1 182 2.71 165 6.00 84 10.7 113 1.73 2 8.81 93 13.7 81 5.16 76 22.6 182 31.6 182 5.26 169 14.3 184 35.7 184 3.79 118 9.13 89 38.8 86 2.45 16 15.6 171 25.3 165 2.31 131
UnFlow [127]135.2 5.97 167 15.5 172 2.16 123 9.13 151 14.1 131 2.38 133 6.68 159 13.0 167 2.00 114 9.35 135 17.1 155 5.23 121 18.6 160 25.8 170 5.20 101 11.5 165 29.5 172 3.74 47 9.66 133 37.4 46 2.45 16 16.9 179 28.1 178 2.38 149
Dynamic MRF [7]135.2 5.26 92 11.5 131 2.00 14 8.12 123 14.3 138 2.16 80 6.68 159 12.8 165 2.00 114 10.9 170 18.3 163 5.51 171 18.3 135 25.0 134 5.20 101 11.6 166 28.6 165 3.87 149 10.7 163 45.7 165 2.52 140 14.9 148 23.3 129 2.31 131
WRT [146]136.8 5.57 151 12.1 146 2.00 14 8.74 139 13.9 125 2.16 80 7.35 174 10.3 89 2.00 114 9.38 136 15.0 124 5.29 149 18.7 166 26.0 174 5.16 91 12.7 183 31.4 179 3.83 139 13.6 184 62.2 184 2.65 177 17.8 181 33.8 182 2.16 3
NL-TV-NCC [25]138.2 6.03 169 12.8 154 2.00 14 8.29 127 14.7 150 2.16 80 6.35 139 11.7 148 2.00 114 10.7 167 18.6 164 5.45 165 18.1 98 24.1 63 5.45 182 12.0 176 28.2 163 3.79 118 13.0 182 43.4 153 2.58 165 15.1 153 23.2 123 2.38 149
SILK [80]140.8 5.80 162 12.7 152 2.38 168 11.1 178 15.6 174 2.83 172 7.35 174 13.0 167 2.00 114 10.8 169 17.5 157 5.48 169 18.3 135 24.8 115 5.20 101 10.5 107 26.0 105 4.20 177 10.0 146 37.1 41 2.52 140 14.6 129 22.7 96 2.31 131
Learning Flow [11]141.5 5.57 151 11.1 112 2.16 123 9.27 154 15.1 159 2.16 80 7.00 169 13.3 171 2.00 114 10.2 159 15.2 129 5.45 165 18.5 154 25.1 140 5.32 178 10.7 131 26.2 114 3.87 149 10.6 161 40.8 113 2.52 140 15.1 153 23.3 129 2.38 149
H+S_RVC [177]143.7 6.00 168 13.0 155 2.16 123 9.49 161 13.5 112 2.71 165 7.68 176 13.7 174 2.38 176 13.7 180 17.5 157 5.35 158 18.3 135 24.7 101 5.20 101 10.9 142 25.5 89 3.79 118 11.6 174 41.2 121 2.58 165 14.8 140 22.9 109 2.38 149
Adaptive flow [45]151.4 6.24 172 11.3 124 2.71 179 11.2 179 15.7 176 3.42 181 6.35 139 10.9 129 2.00 114 10.2 159 14.7 115 5.72 175 18.7 166 25.4 157 5.23 158 11.7 169 30.8 177 3.87 149 9.42 113 38.8 86 2.58 165 14.9 148 24.3 155 2.38 149
WOLF_ROB [144]151.4 6.35 175 18.1 179 2.16 123 10.0 168 15.6 174 2.16 80 6.68 159 12.5 164 2.00 114 9.88 156 19.7 171 5.35 158 18.9 177 26.1 177 5.20 101 11.7 169 29.9 174 4.04 169 12.1 179 51.4 178 2.52 140 15.7 174 27.0 172 2.16 3
FOLKI [16]151.6 6.14 171 12.4 149 3.11 181 11.5 180 15.5 172 3.32 180 7.00 169 14.7 179 2.38 176 13.5 179 18.2 161 6.27 182 18.6 160 25.0 134 5.23 158 10.3 95 25.1 78 4.04 169 11.0 168 38.3 68 2.58 165 14.7 134 22.4 82 2.38 149
GroupFlow [9]153.4 6.56 179 19.6 182 2.16 123 9.38 158 14.7 150 2.52 156 7.68 176 16.8 182 2.00 114 11.1 171 23.5 180 5.29 149 20.7 181 29.3 181 5.23 158 12.4 182 32.8 182 3.87 149 11.3 173 49.6 177 2.45 16 16.8 178 30.4 181 2.16 3
Heeger++ [102]157.5 7.16 182 18.5 180 2.16 123 9.75 164 13.8 122 2.45 148 9.35 181 16.1 181 2.38 176 13.0 176 18.9 166 5.74 176 19.8 180 27.4 180 5.23 158 12.2 177 26.0 105 3.92 164 13.5 183 46.5 167 2.52 140 16.1 175 27.4 173 2.16 3
SLK [47]161.9 6.03 169 13.6 161 2.45 173 10.1 170 13.8 122 2.89 174 7.68 176 12.4 161 2.38 176 13.8 182 21.0 174 5.77 178 19.1 179 26.4 179 5.20 101 11.2 158 26.2 114 3.87 149 11.8 175 46.9 169 2.58 165 15.2 162 26.1 169 2.38 149
FFV1MT [104]164.3 6.40 176 16.8 174 2.16 123 9.87 165 13.9 125 2.89 174 9.35 181 18.7 183 2.52 182 13.0 176 18.9 166 5.74 176 18.8 175 25.7 167 5.26 169 10.9 142 26.0 105 3.92 164 12.8 181 46.5 167 2.52 140 16.2 177 27.4 173 2.45 182
HCIC-L [97]165.7 7.62 183 17.7 177 3.16 182 9.98 167 14.8 157 3.16 179 7.14 173 14.0 175 2.00 114 12.4 175 21.5 177 5.35 158 18.9 177 25.5 163 5.26 169 11.8 173 31.9 181 3.87 149 9.47 118 43.2 152 2.58 165 18.7 183 30.1 180 2.38 149
PGAM+LK [55]166.1 6.56 179 16.0 173 2.71 179 10.0 168 14.7 150 3.00 176 7.75 180 15.7 180 2.38 176 13.7 180 21.1 176 6.27 182 18.8 175 25.8 170 5.26 169 11.6 166 27.2 141 4.08 174 10.7 163 40.3 107 2.58 165 15.1 153 24.4 156 2.38 149
Pyramid LK [2]167.8 6.24 172 13.7 162 3.16 182 12.7 183 15.8 178 3.79 183 11.8 183 12.3 159 3.00 183 25.5 184 41.4 183 7.14 184 22.9 183 33.6 183 5.20 101 10.7 131 25.4 87 3.92 164 11.2 171 49.2 176 2.65 177 19.6 184 37.8 184 2.38 149
Periodicity [79]181.7 6.81 181 17.5 176 3.27 184 15.3 184 16.9 183 4.24 184 13.7 184 22.7 184 4.36 184 18.0 183 41.4 183 6.16 181 23.9 184 34.4 184 5.60 184 12.2 177 34.5 183 4.51 181 11.8 175 55.6 180 2.65 177 17.9 182 29.7 179 2.71 184
AVG_FLOW_ROB [137]185.0 31.4 185 43.5 185 5.60 185 24.2 185 24.5 185 6.45 185 24.3 185 27.7 185 8.43 185 44.7 185 55.2 185 16.9 185 38.9 185 51.5 185 6.24 185 31.3 185 72.3 185 4.83 185 34.9 185 63.2 185 3.65 185 35.1 185 43.8 185 6.73 185
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 T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[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 Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[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 Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
[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] EAFI 0.13 2 color Anonymous. (Interpolation results only.) Fast & small: Error-aware frame interpolation. ECCV 2020 submission 5256.
[172] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[173] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[174] 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.
[175] 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.
[176] 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.
[177] 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.
[178] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[179] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[180] 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.
[181] 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.
[182] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[183] 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.
[184] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. AAAI 2021 submission 6648.
[185] DCM 0.13 2 color Anonymous. (Interpolation results only.) Distill from a cheating model for flow-based video frame interpolation. AAAI 2021 submission 4425.
* 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.