Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R10.0
interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
SoftSplat [169]6.7 0.60 2 1.65 1 0.00 1 1.31 2 3.46 4 0.15 48 0.28 1 0.82 2 0.07 2 1.42 1 2.96 1 0.38 11 9.15 11 15.1 11 0.63 4 2.47 5 10.2 4 0.03 3 3.25 10 18.1 11 0.05 5 4.83 2 12.2 2 0.14 17
BMBC [172]11.6 0.77 12 1.96 6 0.01 6 1.57 6 4.13 6 0.10 26 0.89 14 2.31 24 0.12 9 2.14 7 4.27 6 0.41 28 8.96 7 14.8 7 0.86 27 2.45 4 10.2 4 0.04 13 3.22 9 17.8 9 0.06 15 5.33 4 13.5 4 0.16 26
FGME [158]12.4 0.61 4 1.77 3 0.01 6 2.07 23 4.59 8 0.33 119 0.43 4 1.03 4 0.13 16 1.74 2 3.35 2 0.49 77 7.62 1 12.6 1 0.66 7 2.09 2 8.67 2 0.02 1 2.52 1 14.0 1 0.03 1 4.84 3 12.3 3 0.11 7
EAFI [171]16.3 0.68 6 2.23 10 0.01 6 1.84 10 4.62 10 0.32 113 0.45 5 1.04 5 0.07 2 2.25 9 4.31 7 0.49 77 10.7 18 17.7 19 0.66 7 3.00 11 12.4 10 0.03 3 3.25 10 18.1 11 0.05 5 6.60 10 16.7 11 0.14 17
EDSC [174]17.1 0.78 14 2.49 13 0.01 6 1.77 8 4.62 10 0.27 96 0.91 16 1.46 12 0.16 36 2.64 11 5.70 17 0.57 115 8.58 3 14.1 3 0.66 7 2.87 8 11.9 8 0.03 3 3.00 3 16.8 3 0.05 5 6.23 6 15.8 6 0.09 1
DCM [185]17.9 0.65 5 1.85 5 0.01 6 1.22 1 3.08 1 0.12 39 0.31 2 0.77 1 0.06 1 1.98 5 3.95 4 0.50 90 10.7 18 17.6 18 0.74 20 3.38 17 14.0 17 0.03 3 4.09 21 21.3 20 0.09 80 7.33 17 18.5 18 0.15 21
STAR-Net [164]18.6 0.60 2 1.73 2 0.00 1 2.34 44 5.83 29 0.21 75 1.04 20 1.08 7 0.18 58 2.40 10 4.54 9 0.49 77 8.24 2 13.6 2 0.67 13 3.13 15 13.0 15 0.04 13 3.79 13 17.8 9 0.06 15 6.45 8 16.2 7 0.09 1
AdaCoF [165]20.6 0.80 16 2.69 16 0.01 6 1.72 7 4.46 7 0.18 60 1.04 20 1.38 10 0.19 70 3.46 50 6.23 20 0.64 131 10.4 16 17.2 16 0.67 13 2.41 3 10.0 3 0.02 1 3.17 6 17.7 8 0.04 2 5.44 5 13.8 5 0.10 4
CyclicGen [149]23.0 0.55 1 1.82 4 0.01 6 1.48 5 3.28 2 0.45 152 0.94 17 2.65 26 0.17 46 3.61 61 6.73 22 1.04 169 9.11 10 14.9 8 0.60 2 1.58 1 6.55 1 0.03 3 2.59 2 14.4 2 0.04 2 3.82 1 9.70 1 0.11 7
FRUCnet [153]23.5 0.89 21 2.84 20 0.01 6 1.94 16 4.76 13 0.36 124 0.96 19 1.45 11 0.20 79 2.99 17 5.85 18 0.63 127 9.22 12 15.2 12 0.57 1 2.70 7 11.2 7 0.03 3 3.18 8 17.5 6 0.06 15 6.56 9 16.6 10 0.10 4
TC-GAN [166]25.6 0.76 11 2.64 14 0.01 6 1.94 16 4.83 14 0.45 152 0.83 12 1.60 17 0.17 46 2.81 12 5.56 15 0.83 158 9.05 8 14.9 8 0.66 7 3.09 13 12.8 13 0.04 13 3.86 15 21.2 17 0.05 5 7.16 16 18.1 16 0.12 11
DAIN [152]25.7 0.78 14 2.72 17 0.01 6 1.98 18 4.89 17 0.44 149 0.81 11 1.50 13 0.16 36 2.82 14 5.58 16 0.83 158 9.07 9 15.0 10 0.66 7 3.06 12 12.7 12 0.05 19 3.86 15 21.2 17 0.05 5 7.14 15 18.0 15 0.12 11
DSepConv [162]25.9 0.88 20 3.15 23 0.01 6 2.05 22 4.93 19 0.45 152 0.95 18 1.51 14 0.14 20 3.79 90 6.79 25 0.56 112 8.79 4 14.5 4 0.65 6 2.96 9 12.3 9 0.04 13 3.04 4 17.0 4 0.06 15 6.95 13 17.6 13 0.11 7
GDCN [173]27.6 0.77 12 2.80 19 0.01 6 2.99 96 6.52 51 0.24 86 0.80 9 1.35 9 0.13 16 3.99 115 5.28 12 0.67 136 8.91 6 14.7 5 0.64 5 3.10 14 12.9 14 0.05 19 3.17 6 17.5 6 0.05 5 6.43 7 16.3 8 0.09 1
STSR [170]29.5 0.87 19 2.75 18 0.01 6 1.35 3 3.28 2 0.30 108 0.80 9 1.55 15 0.22 94 2.03 6 4.43 8 0.72 145 12.6 22 20.8 22 0.72 19 3.93 24 16.2 23 0.06 25 4.13 22 22.9 25 0.07 35 7.92 25 20.0 25 0.11 7
MAF-net [163]29.6 0.69 8 2.29 12 0.01 6 2.57 63 5.86 30 0.47 158 0.85 13 1.64 18 0.16 36 2.81 12 5.13 11 0.65 132 12.0 21 19.7 21 0.77 23 3.68 21 15.3 21 0.05 19 3.46 12 19.3 14 0.05 5 7.40 19 18.7 20 0.13 16
PMMST [112]30.3 1.35 38 4.72 39 0.01 6 2.31 40 6.03 35 0.07 8 1.11 23 3.99 30 0.12 9 3.07 19 6.79 25 0.40 19 13.6 32 22.1 29 1.00 41 4.53 31 18.6 31 0.11 33 4.33 30 24.1 35 0.07 35 8.94 54 22.6 53 0.19 32
CtxSyn [134]30.8 0.83 17 2.64 14 0.01 6 1.46 4 3.91 5 0.12 39 0.89 14 1.58 16 0.21 88 1.91 4 4.91 10 0.47 67 13.3 27 21.6 27 0.88 28 4.13 26 16.8 26 0.05 19 5.12 153 24.8 59 0.06 15 7.83 24 19.5 24 0.17 28
FeFlow [167]30.8 0.75 10 2.27 11 0.01 6 2.35 45 5.57 26 0.49 166 0.78 8 1.22 8 0.11 5 2.92 15 5.53 14 0.84 160 8.90 5 14.7 5 0.70 16 3.32 16 13.7 16 0.03 3 3.96 17 19.2 13 0.14 134 6.92 12 17.4 12 0.14 17
MEMC-Net+ [160]32.1 0.71 9 2.21 9 0.01 6 2.01 21 4.85 15 0.48 160 1.07 22 1.64 18 0.22 94 2.96 16 5.29 13 0.82 157 10.5 17 17.3 17 0.71 17 3.40 18 14.1 18 0.05 19 4.01 18 21.0 15 0.07 35 7.41 20 18.7 20 0.14 17
SuperSlomo [130]33.4 0.91 23 2.94 21 0.01 6 2.72 72 6.28 41 0.48 160 0.71 7 1.99 22 0.12 9 3.19 24 6.15 19 0.81 155 12.7 23 20.8 22 0.74 20 3.92 23 16.2 23 0.04 13 4.20 23 22.7 24 0.05 5 7.68 23 19.4 23 0.15 21
ADC [161]34.0 0.92 24 3.15 23 0.02 93 1.92 14 4.61 9 0.32 113 1.31 54 1.92 20 0.18 58 4.07 122 7.05 33 0.69 139 9.99 15 16.4 15 0.61 3 2.99 10 12.4 10 0.03 3 3.11 5 17.4 5 0.06 15 7.06 14 17.9 14 0.10 4
MDP-Flow2 [68]34.2 1.29 30 4.46 32 0.01 6 2.18 27 6.04 36 0.06 3 1.11 23 4.13 35 0.14 20 3.08 20 6.86 28 0.36 6 13.5 28 22.1 29 1.01 52 4.96 63 20.4 64 0.18 65 4.31 27 24.0 32 0.07 35 8.94 54 22.6 53 0.20 52
DAI [168]35.5 0.85 18 2.04 8 0.20 184 2.39 54 5.22 22 0.75 179 0.39 3 1.05 6 0.11 5 1.85 3 3.73 3 1.39 178 11.6 20 19.1 20 0.71 17 3.61 19 14.9 19 0.03 3 3.83 14 21.2 17 0.04 2 7.36 18 18.6 19 0.15 21
UnDAF [184]36.0 1.31 31 4.58 34 0.01 6 2.19 29 6.06 38 0.06 3 1.16 30 4.52 41 0.17 46 3.13 23 7.00 31 0.36 6 13.6 32 22.2 34 1.01 52 4.97 69 20.4 64 0.18 65 4.32 28 24.0 32 0.06 15 8.96 61 22.7 62 0.19 32
OFRI [154]36.6 0.68 6 1.98 7 0.02 93 2.09 24 4.70 12 0.44 149 0.70 6 0.86 3 0.17 46 2.16 8 4.06 5 0.77 151 9.25 13 15.3 13 0.66 7 3.64 20 14.9 19 0.03 3 5.14 155 21.0 15 0.08 61 7.41 20 18.2 17 0.16 26
CoT-AMFlow [175]38.2 1.32 34 4.67 37 0.01 6 2.20 31 6.12 39 0.05 1 1.15 29 4.42 40 0.15 28 3.10 21 6.95 29 0.36 6 13.6 32 22.2 34 1.02 68 4.99 73 20.5 71 0.20 75 4.36 36 24.2 38 0.06 15 8.96 61 22.7 62 0.20 52
MPRN [151]41.8 1.02 26 3.42 26 0.01 6 2.81 77 5.90 32 0.24 86 1.40 78 5.46 113 0.14 20 3.69 72 7.51 50 0.61 124 12.7 23 20.8 22 0.78 24 3.89 22 16.1 22 0.07 26 4.37 38 23.6 27 0.07 35 7.54 22 19.1 22 0.12 11
NN-field [71]46.0 1.45 56 5.41 72 0.01 6 1.87 13 5.01 21 0.06 3 1.51 104 3.94 28 0.16 36 3.78 88 8.92 114 0.41 28 13.6 32 22.2 34 1.00 41 5.05 81 20.7 79 0.20 75 4.27 24 23.7 28 0.07 35 8.85 38 22.4 37 0.19 32
NNF-Local [75]46.9 1.41 45 5.16 57 0.01 6 1.85 11 5.00 20 0.07 8 1.12 25 4.05 31 0.14 20 3.68 71 8.61 98 0.42 35 13.6 32 22.3 38 1.00 41 5.21 103 21.4 105 0.24 99 4.35 32 24.1 35 0.11 107 8.85 38 22.4 37 0.19 32
TOF-M [150]48.1 1.06 27 3.25 25 0.02 93 2.86 83 6.62 57 0.50 167 1.17 32 2.25 23 0.21 88 3.42 46 6.74 23 0.59 121 13.0 26 21.2 26 0.84 26 4.19 27 17.3 27 0.08 27 4.61 95 22.9 25 0.06 15 8.43 28 21.0 27 0.15 21
DeepFlow [85]50.3 1.35 38 4.67 37 0.00 1 3.01 98 8.09 94 0.21 75 1.26 41 5.00 69 0.12 9 3.97 113 8.00 70 0.44 51 13.7 41 22.4 45 1.03 78 4.46 29 18.3 29 0.08 27 4.40 41 24.5 48 0.06 15 8.74 34 22.1 34 0.21 91
DeepFlow2 [106]52.5 1.40 44 4.87 43 0.01 6 3.01 98 8.13 96 0.20 71 1.25 40 5.01 73 0.11 5 3.83 99 8.21 81 0.43 44 13.7 41 22.4 45 1.03 78 4.49 30 18.5 30 0.08 27 4.49 59 24.8 59 0.06 15 8.87 41 22.5 44 0.21 91
MS-PFT [159]52.6 0.89 21 3.07 22 0.01 6 2.25 35 5.71 27 0.32 113 1.26 41 1.95 21 0.31 138 4.49 143 8.39 88 0.91 166 9.43 14 15.5 14 0.75 22 2.64 6 10.9 6 0.04 13 4.98 144 21.5 21 0.21 161 6.65 11 16.5 9 0.15 21
SepConv-v1 [125]53.4 0.93 25 3.75 27 0.02 93 2.74 74 6.52 51 0.46 156 1.13 26 2.38 25 0.42 151 3.64 69 7.10 36 0.94 167 13.6 32 22.1 29 0.82 25 4.01 25 16.5 25 0.05 19 4.02 19 22.3 22 0.12 123 8.05 26 20.3 26 0.12 11
DF-Auto [113]53.7 1.26 28 3.92 28 0.00 1 3.13 106 7.98 89 0.29 103 1.14 28 4.08 33 0.16 36 3.57 55 7.48 48 0.46 61 13.5 28 22.0 28 1.01 52 4.66 32 19.2 33 0.15 47 4.49 59 24.8 59 0.09 80 9.09 81 23.0 82 0.21 91
IROF++ [58]55.0 1.54 87 5.77 100 0.01 6 2.35 45 6.39 43 0.10 26 1.50 101 5.04 75 0.25 114 3.10 21 6.75 24 0.39 14 13.7 41 22.4 45 1.16 122 4.66 32 19.2 33 0.11 33 4.55 81 25.1 77 0.10 93 8.84 37 22.4 37 0.19 32
PH-Flow [99]55.4 1.54 87 5.76 98 0.01 6 1.93 15 5.29 23 0.08 14 1.17 32 4.41 39 0.17 46 3.05 18 6.71 21 0.39 14 13.6 32 22.3 38 1.01 52 5.35 123 21.9 124 0.34 146 4.36 36 24.3 41 0.10 93 8.92 52 22.6 53 0.22 127
NNF-EAC [101]56.5 1.48 61 4.99 49 0.03 155 2.49 59 6.76 64 0.08 14 1.56 111 4.39 38 0.24 107 3.28 28 7.08 34 0.39 14 13.7 41 22.3 38 1.01 52 4.66 32 19.1 32 0.12 37 4.41 45 24.5 48 0.11 107 9.02 69 22.8 70 0.20 52
Layers++ [37]58.9 1.44 54 5.17 58 0.01 6 1.83 9 4.87 16 0.05 1 1.32 56 4.86 58 0.22 94 3.34 35 7.36 42 0.43 44 13.8 56 22.6 72 1.13 115 5.37 130 22.0 128 0.24 99 4.39 40 24.3 41 0.05 5 9.00 66 22.7 62 0.22 127
nLayers [57]59.5 1.51 72 5.46 75 0.01 6 2.17 26 5.91 33 0.08 14 1.24 39 3.88 27 0.18 58 3.47 51 7.71 61 0.40 19 13.9 80 22.7 95 1.18 130 5.25 105 21.6 111 0.31 127 4.35 32 23.8 29 0.09 80 8.99 65 22.7 62 0.19 32
Local-TV-L1 [65]59.8 1.34 36 4.39 30 0.02 93 4.19 147 9.42 135 0.37 130 1.34 58 4.34 37 0.15 28 3.61 61 7.78 63 0.44 51 13.8 56 22.5 54 1.04 83 4.71 38 19.5 40 0.16 56 4.40 41 24.5 48 0.07 35 8.70 33 22.0 31 0.20 52
Brox et al. [5]60.5 1.43 51 4.82 41 0.01 6 2.95 88 7.80 84 0.18 60 1.40 78 5.17 88 0.16 36 3.73 80 7.70 60 0.45 55 13.7 41 22.4 45 1.00 41 5.04 79 20.6 76 0.27 112 4.52 64 25.1 77 0.09 80 8.87 41 22.4 37 0.19 32
ALD-Flow [66]61.7 1.53 84 5.62 85 0.01 6 2.86 83 7.94 86 0.16 49 1.29 46 5.15 85 0.12 9 3.34 35 7.68 58 0.38 11 14.0 117 22.8 115 1.15 120 4.71 38 19.2 33 0.11 33 4.41 45 24.4 45 0.06 15 9.30 115 23.5 116 0.20 52
LME [70]62.8 1.39 42 5.10 53 0.01 6 2.49 59 6.95 69 0.10 26 1.35 64 5.64 121 0.15 28 3.29 30 7.55 52 0.39 14 14.1 142 23.0 146 1.26 179 5.13 92 21.1 96 0.19 72 4.37 38 24.2 38 0.06 15 8.89 48 22.5 44 0.19 32
CBF [12]64.4 1.28 29 4.40 31 0.01 6 3.24 114 8.20 101 0.25 89 1.59 118 4.63 45 0.18 58 3.60 60 7.61 55 0.49 77 13.8 56 22.5 54 0.99 36 4.89 52 20.2 55 0.18 65 4.56 83 25.3 95 0.07 35 9.21 100 23.3 102 0.18 29
Aniso. Huber-L1 [22]64.8 1.43 51 5.00 50 0.01 6 4.12 143 9.46 138 0.36 124 1.60 120 4.77 49 0.17 46 3.69 72 7.99 68 0.43 44 13.7 41 22.3 38 1.00 41 4.90 55 20.1 50 0.12 37 4.62 98 25.2 85 0.07 35 8.95 59 22.6 53 0.20 52
WLIF-Flow [91]64.8 1.44 54 5.19 60 0.01 6 2.52 62 6.81 66 0.16 49 1.38 71 4.67 46 0.20 79 3.21 25 6.98 30 0.42 35 13.7 41 22.4 45 1.07 97 5.37 130 22.1 134 0.28 117 4.43 48 24.4 45 0.08 61 9.09 81 23.0 82 0.21 91
JOF [136]64.8 1.58 107 5.80 102 0.01 6 2.18 27 5.88 31 0.10 26 1.28 44 4.68 47 0.19 70 3.37 42 7.21 39 0.42 35 13.9 80 22.7 95 1.21 144 5.35 123 21.9 124 0.20 75 4.33 30 24.0 32 0.07 35 9.18 95 23.2 95 0.20 52
ComponentFusion [94]65.3 1.54 87 6.05 119 0.01 6 2.33 43 6.57 55 0.07 8 1.31 54 4.82 53 0.16 36 3.35 39 7.66 57 0.37 10 13.9 80 22.6 72 1.13 115 4.93 57 20.3 59 0.20 75 4.61 95 25.7 116 0.13 130 9.06 75 22.9 75 0.20 52
TV-L1-MCT [64]67.2 1.70 137 6.35 135 0.02 93 2.90 85 7.98 89 0.17 54 1.39 75 5.19 92 0.20 79 3.32 34 7.10 36 0.45 55 13.9 80 22.6 72 1.17 128 4.67 35 19.3 37 0.15 47 4.44 50 24.4 45 0.08 61 8.67 31 22.0 31 0.19 32
HCFN [157]67.2 1.51 72 5.76 98 0.01 6 2.65 67 7.50 75 0.11 36 1.34 58 5.07 78 0.18 58 3.35 39 7.86 65 0.32 2 13.7 41 22.3 38 1.04 83 5.13 92 20.3 59 0.34 146 4.58 87 25.3 95 0.11 107 9.08 77 23.0 82 0.20 52
VCN_RVC [179]67.8 1.77 146 7.53 159 0.02 93 2.31 40 6.52 51 0.08 14 1.49 98 6.27 143 0.16 36 3.70 76 9.04 121 0.41 28 13.8 56 22.6 72 1.01 52 4.96 63 20.3 59 0.12 37 4.53 69 25.1 77 0.07 35 8.79 35 22.3 35 0.19 32
CLG-TV [48]68.8 1.35 38 4.56 33 0.02 93 3.84 131 9.35 130 0.29 103 1.38 71 5.11 80 0.18 58 3.71 78 7.93 66 0.50 90 13.8 56 22.4 45 1.00 41 4.74 41 19.5 40 0.13 42 4.59 92 25.2 85 0.07 35 9.08 77 22.9 75 0.20 52
COFM [59]69.1 1.49 67 5.57 80 0.01 6 2.37 47 6.48 49 0.11 36 1.30 49 4.84 56 0.23 101 3.29 30 7.33 41 0.40 19 13.8 56 22.5 54 1.02 68 5.52 145 22.7 150 0.39 162 4.04 20 22.5 23 0.11 107 9.33 119 23.6 121 0.20 52
CombBMOF [111]69.5 1.59 109 5.46 75 0.02 93 2.30 39 6.40 44 0.10 26 1.39 75 4.83 55 0.21 88 3.90 107 8.60 96 0.46 61 13.8 56 22.5 54 1.01 52 4.92 56 20.1 50 0.11 33 5.35 166 25.9 123 0.10 93 8.89 48 22.4 37 0.19 32
TF+OM [98]71.2 1.41 45 5.19 60 0.01 6 2.38 51 6.62 57 0.12 39 1.42 85 5.51 115 0.15 28 3.87 102 8.66 103 0.49 77 13.9 80 22.6 72 1.05 89 4.96 63 20.3 59 0.16 56 4.54 75 25.3 95 0.10 93 9.12 87 23.0 82 0.21 91
Sparse-NonSparse [56]71.4 1.54 87 5.67 91 0.02 93 2.38 51 6.47 48 0.12 39 1.42 85 5.13 82 0.17 46 3.42 46 7.36 42 0.42 35 13.8 56 22.5 54 1.18 130 5.29 112 21.7 117 0.23 91 4.43 48 24.5 48 0.10 93 9.11 85 23.0 82 0.20 52
SegFlow [156]71.6 1.52 80 5.83 105 0.01 6 2.37 47 6.71 62 0.10 26 1.34 58 5.00 69 0.12 9 3.69 72 8.87 112 0.49 77 13.9 80 22.6 72 1.22 157 5.08 85 20.9 86 0.33 142 4.58 87 25.3 95 0.08 61 8.87 41 22.4 37 0.20 52
ProbFlowFields [126]71.8 1.46 58 5.63 86 0.02 93 2.23 34 6.35 42 0.09 21 1.19 34 4.55 43 0.20 79 3.51 53 8.02 72 0.45 55 13.9 80 22.7 95 1.24 169 5.28 111 21.6 111 0.39 162 4.32 28 24.1 35 0.11 107 8.68 32 22.0 31 0.21 91
PGM-C [118]71.8 1.50 69 5.75 96 0.01 6 2.37 47 6.68 60 0.10 26 1.48 97 5.32 99 0.15 28 3.77 86 9.13 127 0.50 90 13.9 80 22.6 72 1.21 144 4.97 69 20.4 64 0.23 91 4.54 75 25.1 77 0.08 61 8.94 54 22.6 53 0.20 52
IROF-TV [53]72.0 1.51 72 5.64 87 0.02 93 2.60 64 6.84 67 0.16 49 1.34 58 5.38 106 0.18 58 3.29 30 7.49 49 0.42 35 14.0 117 22.8 115 1.21 144 5.05 81 20.8 83 0.20 75 4.52 64 25.2 85 0.07 35 8.82 36 22.3 35 0.21 91
FlowFields [108]72.1 1.52 80 5.99 114 0.02 93 2.31 40 6.55 54 0.09 21 1.30 49 4.97 66 0.20 79 3.76 84 9.03 119 0.40 19 13.9 80 22.7 95 1.16 122 5.16 95 21.3 101 0.28 117 4.40 41 24.5 48 0.07 35 8.88 44 22.5 44 0.21 91
CPM-Flow [114]72.5 1.50 69 5.73 95 0.01 6 2.37 47 6.69 61 0.10 26 1.38 71 5.06 77 0.12 9 4.02 121 9.68 141 0.51 97 13.9 80 22.6 72 1.21 144 4.83 45 19.9 44 0.15 47 4.63 101 25.6 110 0.08 61 8.88 44 22.5 44 0.22 127
SIOF [67]72.5 1.53 84 5.38 70 0.01 6 4.17 144 10.1 155 0.31 110 1.40 78 5.38 106 0.14 20 3.62 64 7.99 68 0.61 124 13.5 28 22.1 29 0.98 33 4.87 48 20.1 50 0.13 42 4.49 59 24.9 68 0.08 61 9.34 121 23.6 121 0.20 52
HAST [107]72.9 1.48 61 5.42 73 0.01 6 2.14 25 5.79 28 0.06 3 1.52 106 5.24 94 0.23 101 3.27 27 7.14 38 0.33 3 14.0 117 22.8 115 0.99 36 5.52 145 22.7 150 0.31 127 4.35 32 24.3 41 0.07 35 9.68 147 24.4 148 0.21 91
RAFT-TF_RVC [180]73.3 1.70 137 7.21 152 0.02 93 2.25 35 6.40 44 0.06 3 1.16 30 4.53 42 0.18 58 3.67 70 8.70 104 0.47 67 13.9 80 22.6 72 1.00 41 5.44 138 20.7 79 0.28 117 4.35 32 24.2 38 0.06 15 9.06 75 22.9 75 0.24 162
FMOF [92]74.0 1.67 133 5.98 112 0.03 155 2.22 32 6.04 36 0.08 14 1.56 111 5.22 93 0.28 130 3.81 96 8.34 85 0.49 77 13.8 56 22.5 54 1.01 52 5.01 76 20.5 71 0.15 47 4.30 26 23.9 31 0.07 35 9.21 100 23.3 102 0.20 52
ProFlow_ROB [142]74.6 1.48 61 5.67 91 0.01 6 2.74 74 7.77 83 0.14 45 1.36 66 4.82 53 0.15 28 3.58 57 8.56 93 0.35 4 14.0 117 22.8 115 1.22 157 4.69 37 19.3 37 0.09 30 4.75 120 25.9 123 0.08 61 9.34 121 23.6 121 0.21 91
Ramp [62]75.0 1.57 105 5.75 96 0.01 6 2.38 51 6.51 50 0.19 64 1.41 82 5.11 80 0.17 46 3.26 26 7.09 35 0.41 28 13.9 80 22.6 72 1.15 120 5.51 143 22.5 143 0.32 136 4.48 55 24.7 56 0.07 35 9.33 119 23.6 121 0.20 52
PRAFlow_RVC [178]75.4 1.67 133 6.70 146 0.02 93 2.39 54 6.57 55 0.11 36 1.13 26 4.12 34 0.15 28 3.70 76 8.75 105 0.48 71 13.8 56 22.5 54 1.03 78 4.85 47 19.9 44 0.15 47 4.40 41 24.5 48 0.11 107 9.52 138 23.9 139 0.23 153
FlowFields+ [128]76.9 1.52 80 5.97 111 0.02 93 2.26 37 6.42 47 0.09 21 1.29 46 5.05 76 0.19 70 3.69 72 8.96 116 0.44 51 14.0 117 22.8 115 1.21 144 5.26 106 21.6 111 0.33 142 4.41 45 24.5 48 0.08 61 8.86 40 22.5 44 0.20 52
2DHMM-SAS [90]77.4 1.65 127 6.25 131 0.02 93 3.41 118 8.58 109 0.22 79 1.36 66 4.84 56 0.19 70 3.28 28 7.02 32 0.43 44 13.8 56 22.5 54 1.19 136 4.94 60 20.1 50 0.09 30 4.52 64 24.8 59 0.12 123 9.25 110 23.4 110 0.20 52
F-TV-L1 [15]77.7 1.54 87 5.24 64 0.02 93 4.11 142 9.73 149 0.32 113 1.50 101 5.44 110 0.23 101 3.76 84 8.03 73 0.47 67 13.5 28 22.1 29 0.94 29 4.71 38 19.4 39 0.17 60 4.61 95 25.3 95 0.13 130 8.92 52 22.6 53 0.19 32
BlockOverlap [61]77.8 1.34 36 4.33 29 0.02 93 4.04 140 9.04 123 0.48 160 1.36 66 4.31 36 0.32 139 3.43 49 6.81 27 0.71 143 14.0 117 22.8 115 1.04 83 4.89 52 20.0 48 0.22 86 4.44 50 24.7 56 0.11 107 8.64 30 21.8 29 0.20 52
MDP-Flow [26]78.3 1.35 38 4.97 48 0.02 93 2.22 32 6.25 40 0.09 21 1.20 35 4.07 32 0.14 20 3.89 105 8.34 85 0.48 71 13.8 56 22.5 54 1.24 169 5.74 160 23.6 165 0.50 180 4.63 101 25.6 110 0.11 107 8.97 63 22.7 62 0.19 32
Classic++ [32]78.3 1.46 58 5.27 65 0.01 6 3.38 117 8.81 118 0.25 89 1.47 96 5.14 84 0.17 46 3.93 112 8.15 78 0.46 61 13.8 56 22.6 72 1.00 41 5.16 95 21.2 100 0.25 107 4.59 92 25.2 85 0.08 61 9.17 93 23.2 95 0.20 52
Classic+NL [31]79.2 1.62 117 5.98 112 0.02 93 2.48 56 6.65 59 0.17 54 1.41 82 5.13 82 0.19 70 3.37 42 7.27 40 0.44 51 13.9 80 22.6 72 1.12 114 5.34 120 21.8 121 0.22 86 4.48 55 24.8 59 0.09 80 9.27 113 23.4 110 0.19 32
Second-order prior [8]79.4 1.39 42 4.88 44 0.02 93 3.85 133 9.45 137 0.27 96 1.83 137 5.99 135 0.26 119 3.83 99 8.56 93 0.49 77 13.6 32 22.3 38 1.01 52 4.82 44 19.9 44 0.18 65 4.67 108 25.6 110 0.06 15 9.03 71 22.8 70 0.20 52
OAR-Flow [123]80.7 1.56 101 5.61 84 0.01 6 2.99 96 8.09 94 0.22 79 1.29 46 4.89 60 0.10 4 3.29 30 7.60 54 0.38 11 14.0 117 22.8 115 1.23 162 5.11 90 21.0 89 0.29 121 4.78 125 26.1 130 0.09 80 9.19 96 23.2 95 0.20 52
LSM [39]81.2 1.64 123 6.31 134 0.01 6 2.48 56 6.79 65 0.12 39 1.51 104 5.55 117 0.17 46 3.59 59 7.98 67 0.41 28 13.9 80 22.6 72 1.19 136 5.36 126 21.9 124 0.25 107 4.47 53 24.7 56 0.10 93 9.23 105 23.3 102 0.20 52
AggregFlow [95]81.3 1.89 158 7.48 157 0.01 6 2.95 88 8.13 96 0.16 49 1.22 37 4.86 58 0.14 20 4.18 129 9.69 142 0.45 55 13.9 80 22.6 72 1.04 83 4.94 60 20.2 55 0.15 47 4.51 62 25.0 72 0.12 123 9.24 109 23.3 102 0.21 91
LDOF [28]81.6 1.45 56 4.81 40 0.02 93 3.10 103 7.33 72 0.56 175 1.58 116 5.39 109 0.22 94 3.92 111 8.47 90 0.63 127 13.8 56 22.5 54 1.02 68 4.68 36 19.2 33 0.13 42 4.48 55 25.0 72 0.10 93 9.01 67 22.8 70 0.22 127
DMF_ROB [135]82.7 1.54 87 5.65 88 0.01 6 3.31 116 8.76 116 0.28 101 2.11 153 6.42 148 0.44 153 4.01 119 8.89 113 0.46 61 13.7 41 22.4 45 1.20 139 4.87 48 20.1 50 0.22 86 4.54 75 24.8 59 0.07 35 8.90 50 22.5 44 0.20 52
ComplOF-FED-GPU [35]83.1 1.56 101 5.92 107 0.02 93 2.71 71 7.63 78 0.17 54 1.95 145 5.09 79 0.39 150 3.63 65 8.64 100 0.40 19 13.7 41 22.5 54 1.13 115 4.98 71 20.5 71 0.17 60 4.70 112 25.7 116 0.07 35 9.31 116 23.4 110 0.19 32
CRTflow [81]83.3 1.50 69 5.48 77 0.02 93 3.87 134 9.40 134 0.36 124 1.62 123 6.22 142 0.24 107 3.55 54 7.76 62 0.43 44 13.9 80 22.7 95 1.21 144 4.77 43 19.6 42 0.14 45 4.53 69 25.2 85 0.07 35 9.04 72 22.9 75 0.20 52
DPOF [18]84.1 1.64 123 6.52 143 0.04 174 1.98 18 5.37 24 0.07 8 1.83 137 4.75 48 0.34 142 3.75 83 8.80 110 0.48 71 13.7 41 22.3 38 1.01 52 5.16 95 21.0 89 0.14 45 4.67 108 25.3 95 0.06 15 9.31 116 23.5 116 0.22 127
S2F-IF [121]84.2 1.55 97 6.13 123 0.01 6 2.26 37 6.41 46 0.09 21 1.30 49 5.17 88 0.17 46 3.72 79 9.01 118 0.45 55 14.0 117 22.9 136 1.24 169 5.27 107 21.6 111 0.32 136 4.54 75 25.2 85 0.09 80 8.88 44 22.5 44 0.23 153
TC-Flow [46]84.9 1.51 72 5.70 94 0.01 6 2.97 91 8.31 104 0.21 75 1.46 93 5.35 101 0.11 5 3.63 65 8.10 75 0.58 119 14.0 117 22.8 115 1.21 144 5.10 87 21.0 89 0.29 121 4.53 69 25.0 72 0.07 35 9.19 96 23.3 102 0.21 91
OFLAF [78]86.1 1.48 61 5.49 79 0.01 6 2.00 20 5.50 25 0.07 8 1.30 49 4.97 66 0.15 28 3.34 35 7.40 45 0.40 19 14.0 117 22.8 115 1.21 144 5.56 151 22.8 154 0.41 165 4.83 132 26.3 139 0.17 152 9.73 152 24.5 153 0.20 52
p-harmonic [29]86.5 1.42 48 4.96 47 0.01 6 4.00 137 9.50 139 0.39 135 1.38 71 5.68 123 0.19 70 4.20 131 8.58 95 0.49 77 13.9 80 22.6 72 1.01 52 4.93 57 20.3 59 0.21 81 4.81 128 26.1 130 0.11 107 9.12 87 23.1 91 0.20 52
SVFilterOh [109]86.9 1.51 72 5.48 77 0.02 93 2.19 29 5.94 34 0.10 26 1.50 101 5.00 69 0.25 114 3.78 88 8.01 71 0.40 19 14.3 160 23.2 158 1.22 157 5.35 123 22.0 128 0.23 91 4.27 24 23.8 29 0.06 15 9.55 139 24.1 142 0.22 127
FC-2Layers-FF [74]88.1 1.56 101 5.94 109 0.02 93 1.86 12 4.90 18 0.08 14 1.39 75 5.29 98 0.20 79 3.34 35 7.46 47 0.40 19 13.9 80 22.8 115 1.20 139 5.56 151 22.9 155 0.37 158 4.53 69 24.9 68 0.11 107 9.35 124 23.6 121 0.22 127
EAI-Flow [147]88.3 1.65 127 5.96 110 0.03 155 2.84 80 7.64 80 0.25 89 1.56 111 5.73 127 0.19 70 3.82 97 8.93 115 0.35 4 13.9 80 22.6 72 1.18 130 4.87 48 20.0 48 0.22 86 4.75 120 26.0 126 0.14 134 8.63 29 21.8 29 0.20 52
Occlusion-TV-L1 [63]91.8 1.43 51 5.20 63 0.01 6 4.18 146 10.3 159 0.37 130 1.34 58 5.35 101 0.27 126 4.19 130 9.14 128 0.56 112 13.7 41 22.4 45 0.97 30 4.99 73 20.6 76 0.33 142 5.12 153 25.4 103 0.27 168 9.01 67 22.7 62 0.19 32
S2D-Matching [83]92.5 1.65 127 6.07 121 0.02 93 3.21 110 8.58 109 0.23 85 1.34 58 5.00 69 0.23 101 3.35 39 7.36 42 0.42 35 13.9 80 22.7 95 1.07 97 5.53 148 22.6 146 0.35 151 4.57 86 24.8 59 0.07 35 9.22 104 23.3 102 0.22 127
TC/T-Flow [77]92.8 1.69 136 6.24 129 0.02 93 2.98 93 8.17 99 0.19 64 1.27 43 4.78 50 0.13 16 3.58 57 8.26 82 0.36 6 14.1 142 23.0 146 1.23 162 5.03 78 20.6 76 0.12 37 4.85 135 26.3 139 0.16 149 9.40 130 23.8 134 0.19 32
HBM-GC [103]93.6 1.54 87 5.66 89 0.01 6 2.98 93 8.21 102 0.17 54 1.20 35 3.96 29 0.18 58 3.63 65 7.79 64 0.43 44 14.4 166 23.5 167 1.29 182 5.96 172 24.4 174 0.48 176 4.46 52 24.6 55 0.05 5 9.35 124 23.6 121 0.22 127
EpicFlow [100]94.0 1.51 72 5.82 104 0.01 6 2.90 85 8.08 92 0.18 60 1.43 88 5.25 95 0.16 36 3.88 104 9.42 135 0.54 106 13.9 80 22.7 95 1.21 144 5.13 92 21.1 96 0.31 127 4.71 114 25.8 120 0.14 134 9.13 89 23.1 91 0.21 91
RFlow [88]94.4 1.41 45 5.18 59 0.02 93 3.96 136 9.67 146 0.35 121 1.41 82 5.37 104 0.26 119 3.91 110 8.76 106 0.52 98 13.7 41 22.5 54 1.01 52 4.96 63 20.5 71 0.21 81 4.58 87 25.5 106 0.09 80 9.37 128 23.7 131 0.23 153
AGIF+OF [84]95.0 1.66 132 6.04 118 0.02 93 2.48 56 6.73 63 0.19 64 1.44 89 4.96 65 0.26 119 3.41 45 7.54 51 0.45 55 14.1 142 23.1 155 1.21 144 5.47 140 22.3 139 0.27 112 4.52 64 24.3 41 0.07 35 9.41 133 23.8 134 0.21 91
MLDP_OF [87]95.3 1.55 97 6.03 117 0.02 93 3.12 105 8.40 107 0.20 71 1.22 37 4.97 66 0.13 16 3.77 86 7.62 56 0.73 146 13.9 80 22.7 95 1.01 52 5.60 155 23.0 159 0.31 127 4.63 101 25.3 95 0.14 134 9.21 100 23.3 102 0.21 91
OFH [38]96.1 1.56 101 5.79 101 0.01 6 3.55 123 8.78 117 0.30 108 1.62 123 6.44 149 0.16 36 3.57 55 8.52 92 0.39 14 13.8 56 22.6 72 1.16 122 5.18 99 21.3 101 0.31 127 4.94 141 26.6 142 0.15 142 9.36 126 23.6 121 0.19 32
RNLOD-Flow [119]96.5 1.52 80 5.81 103 0.01 6 3.05 102 8.32 106 0.19 64 1.58 116 5.84 133 0.32 139 3.47 51 7.69 59 0.43 44 13.9 80 22.7 95 1.19 136 5.36 126 22.0 128 0.26 111 4.51 62 24.8 59 0.14 134 9.66 144 24.4 148 0.21 91
PMF [73]96.7 1.59 109 6.16 127 0.01 6 2.73 73 7.62 77 0.07 8 1.65 127 6.90 158 0.28 130 3.74 81 8.38 87 0.40 19 14.1 142 23.0 146 1.02 68 5.10 87 20.9 86 0.19 72 4.56 83 25.4 103 0.09 80 9.84 158 24.9 166 0.22 127
Ad-TV-NDC [36]97.3 1.63 120 4.88 44 0.03 155 5.06 170 10.3 159 0.36 124 1.45 91 5.55 117 0.20 79 4.53 146 9.15 129 0.57 115 14.1 142 22.9 136 0.99 36 4.74 41 19.6 42 0.16 56 4.80 127 25.8 120 0.06 15 9.02 69 22.8 70 0.19 32
Sparse Occlusion [54]99.0 1.51 72 5.58 81 0.02 93 3.51 122 9.43 136 0.19 64 1.37 70 4.95 64 0.18 58 3.80 93 8.33 83 0.49 77 13.9 80 22.7 95 1.20 139 5.58 153 22.9 155 0.37 158 4.73 117 25.8 120 0.07 35 9.38 129 23.7 131 0.20 52
C-RAFT_RVC [182]99.0 2.24 172 9.02 171 0.02 93 2.91 87 8.15 98 0.18 60 1.54 109 5.96 134 0.28 130 4.11 126 9.64 140 0.48 71 13.8 56 22.5 54 0.99 36 5.29 112 21.7 117 0.21 81 4.60 94 25.4 103 0.06 15 9.19 96 23.2 95 0.22 127
TCOF [69]99.3 1.54 87 5.59 82 0.01 6 4.46 155 10.4 162 0.43 146 1.28 44 5.15 85 0.14 20 3.63 65 8.04 74 0.42 35 13.9 80 22.7 95 0.98 33 5.41 134 22.3 139 0.24 99 5.00 146 26.7 144 0.09 80 9.76 153 24.6 157 0.24 162
CostFilter [40]100.8 1.77 146 7.36 155 0.01 6 2.66 68 7.51 76 0.08 14 1.82 136 7.88 173 0.29 135 4.00 117 9.50 138 0.31 1 14.2 156 23.1 155 1.07 97 4.98 71 20.4 64 0.17 60 4.62 98 25.6 110 0.08 61 9.65 142 24.4 148 0.21 91
HBpMotionGpu [43]101.3 1.64 123 5.67 91 0.02 93 5.07 171 11.0 174 0.48 160 1.33 57 4.89 60 0.22 94 4.40 136 9.95 149 0.52 98 13.8 56 22.6 72 1.17 128 5.30 115 21.4 105 0.29 121 4.48 55 24.9 68 0.06 15 9.23 105 23.2 95 0.21 91
Modified CLG [34]101.6 1.31 31 4.60 35 0.01 6 4.56 160 9.63 144 0.50 167 1.63 125 6.45 151 0.33 141 4.14 128 9.05 122 0.62 126 13.9 80 22.6 72 1.02 68 5.08 85 20.8 83 0.31 127 4.65 105 25.9 123 0.09 80 9.08 77 22.9 75 0.22 127
Adaptive [20]102.5 1.48 61 5.33 68 0.02 93 4.48 156 10.6 168 0.43 146 1.53 108 5.50 114 0.18 58 3.84 101 8.33 83 0.54 106 13.9 80 22.7 95 1.00 41 5.20 102 21.4 105 0.28 117 4.89 136 26.1 130 0.07 35 9.41 133 23.8 134 0.21 91
FF++_ROB [141]103.1 1.55 97 6.13 123 0.01 6 2.70 69 7.41 73 0.14 45 1.46 93 5.35 101 0.25 114 3.98 114 9.53 139 0.53 103 14.1 142 22.9 136 1.25 176 5.34 120 21.9 124 0.32 136 4.55 81 25.2 85 0.12 123 8.94 54 22.6 53 0.25 168
AdaConv-v1 [124]103.3 2.34 174 9.17 172 0.04 174 4.08 141 8.31 104 0.75 179 2.48 164 6.07 139 0.62 166 7.79 178 14.5 181 2.10 183 12.8 25 20.9 25 0.69 15 4.24 28 17.6 28 0.09 30 4.52 64 25.1 77 0.22 166 8.39 27 21.2 28 0.12 11
PWC-Net_RVC [143]103.5 1.82 151 7.81 162 0.02 93 3.01 98 8.61 112 0.12 39 1.46 93 6.05 137 0.19 70 3.79 90 9.29 134 0.41 28 14.1 142 23.1 155 1.24 169 5.30 115 21.3 101 0.20 75 4.54 75 25.0 72 0.10 93 8.98 64 22.7 62 0.23 153
TriFlow [93]104.7 1.65 127 6.58 144 0.01 6 3.78 130 9.53 141 0.29 103 1.45 91 5.99 135 0.18 58 4.07 122 9.25 132 0.49 77 14.0 117 22.9 136 1.18 130 5.34 120 21.4 105 0.15 47 4.64 104 25.2 85 0.08 61 9.40 130 23.6 121 0.21 91
FlowNetS+ft+v [110]105.1 1.48 61 5.14 56 0.02 93 4.36 151 9.68 148 0.78 181 1.57 114 5.37 104 0.26 119 3.90 107 8.47 90 0.81 155 13.9 80 22.7 95 1.23 162 4.83 45 19.9 44 0.24 99 4.70 112 26.1 130 0.12 123 9.09 81 23.0 82 0.21 91
Efficient-NL [60]105.9 1.53 84 5.60 83 0.01 6 2.98 93 7.94 86 0.16 49 2.05 147 5.45 112 0.56 162 3.82 97 8.12 77 0.42 35 13.8 56 22.5 54 1.18 130 5.69 158 23.2 161 0.32 136 4.75 120 26.1 130 0.11 107 9.94 168 24.8 163 0.22 127
Bartels [41]106.2 1.59 109 6.24 129 0.03 155 3.20 109 8.92 121 0.31 110 1.40 78 5.17 88 0.25 114 4.09 124 9.05 122 0.86 163 14.1 142 22.9 136 0.97 30 5.43 137 22.2 137 0.25 107 4.47 53 24.8 59 0.10 93 9.15 91 23.1 91 0.20 52
EPPM w/o HM [86]107.0 1.68 135 7.02 150 0.02 93 2.84 80 8.08 92 0.10 26 2.13 156 7.82 172 0.36 144 3.87 102 9.12 125 0.49 77 13.9 80 22.7 95 1.04 83 5.27 107 21.6 111 0.17 60 4.56 83 25.2 85 0.15 142 9.34 121 23.6 121 0.22 127
Filter Flow [19]108.1 1.54 87 5.28 66 0.01 6 4.52 159 9.97 154 0.35 121 1.61 122 5.53 116 0.20 79 4.55 147 8.61 98 0.46 61 14.3 160 23.2 158 1.08 102 5.10 87 21.0 89 0.21 81 4.76 124 26.1 130 0.11 107 9.65 142 24.3 147 0.20 52
FESL [72]108.5 1.63 120 5.93 108 0.02 93 2.50 61 6.86 68 0.14 45 1.49 98 5.44 110 0.26 119 3.80 93 8.16 79 0.50 90 14.1 142 22.9 136 1.21 144 5.60 155 22.9 155 0.40 164 4.58 87 25.0 72 0.08 61 9.50 135 24.0 141 0.22 127
Nguyen [33]108.8 1.55 97 5.02 51 0.00 1 5.69 177 10.8 170 0.48 160 1.63 125 6.70 155 0.28 130 5.35 164 10.5 155 0.77 151 13.8 56 22.5 54 1.01 52 4.99 73 20.7 79 0.18 65 5.44 168 28.2 162 0.21 161 9.08 77 22.9 75 0.20 52
Classic+CPF [82]108.8 1.65 127 6.18 128 0.02 93 2.63 66 7.07 71 0.17 54 1.44 89 5.38 106 0.23 101 3.40 44 7.45 46 0.42 35 14.3 160 23.3 162 1.21 144 5.68 157 23.2 161 0.31 127 4.71 114 25.3 95 0.10 93 9.77 154 24.6 157 0.22 127
GraphCuts [14]109.5 1.90 159 6.51 142 0.02 93 2.96 90 7.63 78 0.22 79 3.79 180 5.16 87 0.64 168 4.49 143 9.24 131 0.55 109 13.9 80 22.7 95 0.99 36 5.04 79 20.8 83 0.21 81 4.53 69 25.2 85 0.15 142 9.88 163 24.9 166 0.21 91
Complementary OF [21]109.6 1.61 114 6.47 139 0.01 6 2.74 74 7.75 82 0.19 64 2.67 171 5.71 124 0.89 182 3.74 81 8.76 106 0.41 28 13.9 80 22.7 95 1.14 119 5.19 100 21.4 105 0.31 127 4.98 144 26.9 149 0.13 130 9.78 156 24.8 163 0.21 91
2D-CLG [1]110.0 1.42 48 5.09 52 0.01 6 4.91 166 9.82 153 0.48 160 2.21 158 5.62 119 0.57 163 5.05 157 9.90 148 0.80 154 13.8 56 22.5 54 1.09 106 5.07 84 21.0 89 0.42 167 4.89 136 26.7 144 0.13 130 9.11 85 22.6 53 0.20 52
TVL1_RVC [176]110.0 1.54 87 4.90 46 0.01 6 5.65 176 11.1 175 0.46 156 1.54 109 5.71 124 0.36 144 4.83 154 9.25 132 0.70 142 14.0 117 22.8 115 1.03 78 5.05 81 20.9 86 0.23 91 4.92 139 26.8 147 0.19 156 9.04 72 22.9 75 0.19 32
Black & Anandan [4]110.3 1.63 120 5.12 54 0.01 6 5.17 173 10.5 165 0.41 139 2.30 161 6.36 145 0.47 157 5.20 161 9.84 147 0.49 77 14.0 117 22.9 136 1.02 68 4.88 51 20.2 55 0.18 65 5.10 152 27.0 150 0.08 61 9.23 105 23.1 91 0.21 91
SRR-TVOF-NL [89]110.4 1.79 148 6.72 147 0.02 93 3.21 110 8.72 115 0.29 103 1.42 85 5.34 100 0.20 79 4.29 132 9.00 117 0.53 103 13.9 80 22.8 115 1.20 139 5.24 104 21.5 110 0.22 86 4.68 110 25.1 77 0.07 35 9.93 167 25.0 168 0.22 127
IAOF [50]110.6 1.79 148 5.85 106 0.02 93 6.44 182 12.4 183 0.55 173 1.84 140 5.77 130 0.36 144 4.78 152 9.12 125 0.75 150 13.7 41 22.4 45 1.01 52 5.01 76 20.7 79 0.15 47 4.73 117 25.7 116 0.09 80 9.29 114 23.4 110 0.20 52
TV-L1-improved [17]111.2 1.42 48 5.19 60 0.01 6 4.41 153 10.4 162 0.40 136 2.10 150 5.27 97 0.50 159 3.89 105 8.46 89 0.52 98 14.0 117 22.8 115 1.00 41 5.33 119 22.0 128 0.25 107 4.96 143 27.5 158 0.23 167 9.26 111 23.4 110 0.21 91
Steered-L1 [116]111.5 1.33 35 4.83 42 0.02 93 2.85 82 7.86 85 0.32 113 2.08 149 5.18 91 0.64 168 4.36 134 8.60 96 1.06 170 14.1 142 23.0 146 0.97 30 5.12 91 21.1 96 0.34 146 4.69 111 26.1 130 0.12 123 9.50 135 24.1 142 0.22 127
LFNet_ROB [145]112.0 1.82 151 7.57 160 0.03 155 3.04 101 8.27 103 0.22 79 1.49 98 6.12 141 0.21 88 3.99 115 9.80 145 0.57 115 13.8 56 22.6 72 1.26 179 5.51 143 22.5 143 0.34 146 4.54 75 25.1 77 0.09 80 8.94 54 22.5 44 0.25 168
Fusion [6]113.9 1.46 58 5.40 71 0.02 93 2.70 69 6.97 70 0.17 54 1.30 49 4.55 43 0.29 135 4.32 133 8.77 108 0.46 61 14.3 160 23.5 167 1.02 68 5.93 171 24.4 174 0.47 173 4.83 132 26.7 144 0.12 123 10.4 174 26.1 176 0.22 127
3DFlow [133]115.5 1.71 140 6.28 133 0.02 93 2.62 65 7.42 74 0.20 71 1.91 144 4.91 63 0.25 114 3.61 61 8.10 75 0.55 109 13.9 80 22.7 95 1.02 68 6.30 181 25.3 182 0.47 173 5.26 162 27.2 155 0.15 142 9.71 149 24.5 153 0.21 91
ResPWCR_ROB [140]115.5 1.70 137 6.74 148 0.02 93 3.24 114 8.87 119 0.27 96 2.22 159 6.11 140 0.23 101 4.42 137 10.6 156 0.69 139 13.6 32 22.2 34 1.23 162 5.36 126 21.7 117 0.16 56 4.79 126 25.7 116 0.15 142 9.31 116 23.5 116 0.21 91
BriefMatch [122]116.8 1.61 114 6.15 126 0.03 155 2.97 91 7.73 81 0.61 177 2.12 154 4.79 51 0.58 164 4.84 155 9.05 122 1.68 180 13.9 80 22.7 95 1.08 102 5.30 115 21.8 121 0.24 99 4.53 69 24.9 68 0.14 134 9.13 89 23.0 82 0.28 180
CNN-flow-warp+ref [115]117.0 1.31 31 4.62 36 0.02 93 3.65 129 9.05 124 0.47 158 2.07 148 6.56 154 0.43 152 5.51 166 9.78 144 1.12 173 13.9 80 22.7 95 1.23 162 4.96 63 20.5 71 0.35 151 4.90 138 27.1 153 0.18 155 9.04 72 22.8 70 0.21 91
Rannacher [23]117.4 1.49 67 5.66 89 0.01 6 4.49 157 10.6 168 0.40 136 2.19 157 5.77 130 0.52 161 3.79 90 8.65 102 0.53 103 14.0 117 22.8 115 1.02 68 5.29 112 21.8 121 0.27 112 4.95 142 27.4 156 0.21 161 9.26 111 23.4 110 0.22 127
ContinualFlow_ROB [148]117.9 1.99 162 8.31 168 0.03 155 3.22 113 8.92 121 0.25 89 1.78 133 6.97 160 0.26 119 4.00 117 9.83 146 0.48 71 14.0 117 22.9 136 1.24 169 4.93 57 20.4 64 0.18 65 4.62 98 25.1 77 0.08 61 9.40 130 23.8 134 0.25 168
AugFNG_ROB [139]118.1 1.87 156 7.84 164 0.02 93 3.57 125 9.08 125 0.35 121 1.85 141 8.05 176 0.22 94 4.52 145 11.3 160 0.55 109 14.2 156 23.2 158 1.25 176 4.89 52 20.2 55 0.12 37 4.92 139 26.0 126 0.10 93 8.88 44 22.4 37 0.23 153
FlowNet2 [120]118.4 2.65 178 10.2 177 0.02 93 3.21 110 8.40 107 0.22 79 1.75 130 6.40 146 0.27 126 4.43 140 11.4 162 0.67 136 14.1 142 23.0 146 1.11 111 5.17 98 21.0 89 0.19 72 4.65 105 25.5 106 0.08 61 9.10 84 23.0 82 0.24 162
CompactFlow_ROB [155]120.9 2.02 164 8.69 169 0.03 155 3.10 103 8.65 114 0.21 75 1.77 132 7.43 166 0.24 107 4.62 150 11.4 162 0.58 119 13.9 80 22.6 72 1.06 93 5.36 126 22.0 128 0.24 99 4.83 132 26.2 138 0.08 61 9.20 99 23.2 95 0.24 162
SimpleFlow [49]122.2 1.60 113 6.00 115 0.01 6 3.50 121 8.63 113 0.32 113 2.53 165 6.06 138 0.79 173 3.42 46 7.56 53 0.48 71 14.0 117 22.8 115 1.20 139 5.77 162 23.7 167 0.43 170 5.01 147 28.0 160 0.42 178 9.68 147 24.5 153 0.20 52
LSM_FLOW_RVC [183]122.8 2.21 171 9.43 173 0.05 180 3.45 120 9.33 129 0.22 79 1.70 129 7.32 165 0.24 107 4.38 135 11.1 159 0.52 98 13.8 56 22.6 72 1.18 130 5.27 107 21.6 111 0.32 136 4.82 129 26.0 126 0.10 93 9.17 93 23.0 82 0.25 168
LocallyOriented [52]123.5 1.61 114 6.13 123 0.01 6 4.64 162 10.9 171 0.40 136 1.83 137 6.44 149 0.26 119 4.45 142 10.2 153 0.47 67 14.0 117 22.8 115 1.01 52 5.58 153 22.6 146 0.27 112 5.18 158 26.8 147 0.15 142 9.66 144 24.4 148 0.20 52
Horn & Schunck [3]123.7 1.62 117 5.42 73 0.01 6 5.40 175 10.9 171 0.44 149 2.27 160 6.97 160 0.45 154 6.35 174 11.5 165 0.65 132 14.1 142 23.0 146 1.06 93 4.95 62 20.4 64 0.17 60 5.51 169 28.2 162 0.14 134 9.57 140 23.7 131 0.18 29
TriangleFlow [30]124.6 1.73 142 6.50 140 0.02 93 3.84 131 9.51 140 0.31 110 1.78 133 5.71 124 0.27 126 4.43 140 10.1 151 0.57 115 13.7 41 22.5 54 0.98 33 5.69 158 22.9 155 0.23 91 5.16 156 28.3 165 0.21 161 10.1 170 25.4 170 0.21 91
2bit-BM-tele [96]127.2 1.51 72 5.13 55 0.04 174 4.17 144 10.2 156 0.41 139 1.52 106 4.90 62 0.46 155 4.01 119 8.64 100 0.60 123 14.4 166 23.3 162 1.05 89 5.89 166 24.1 169 0.45 172 5.77 175 32.3 182 0.60 181 8.90 50 22.5 44 0.21 91
Shiralkar [42]127.8 1.85 154 7.19 151 0.01 6 4.31 150 9.75 150 0.37 130 2.10 150 7.58 167 0.36 144 5.54 167 11.4 162 0.63 127 13.8 56 22.5 54 1.07 97 5.46 139 22.4 141 0.34 146 5.32 164 27.8 159 0.20 160 9.36 126 23.5 116 0.20 52
LiteFlowNet [138]128.3 1.90 159 8.16 166 0.03 155 2.81 77 8.01 91 0.20 71 1.60 120 6.95 159 0.24 107 4.75 151 11.8 168 0.86 163 13.9 80 22.7 95 1.25 176 5.50 142 22.1 134 0.32 136 5.07 151 26.6 142 0.19 156 8.95 59 22.6 53 0.25 168
EPMNet [131]128.5 2.65 178 10.8 180 0.03 155 3.16 108 8.19 100 0.25 89 1.75 130 6.40 146 0.27 126 5.13 158 13.4 178 0.65 132 14.1 142 23.0 146 1.11 111 5.39 132 22.1 134 0.23 91 4.65 105 25.5 106 0.08 61 9.23 105 23.3 102 0.25 168
Correlation Flow [76]129.1 1.71 140 6.50 140 0.02 93 4.00 137 10.2 156 0.36 124 1.35 64 4.81 52 0.19 70 3.90 107 8.77 108 0.50 90 14.0 117 22.9 136 1.05 89 6.25 180 24.8 179 0.43 170 5.22 160 28.1 161 0.19 156 9.80 157 24.7 160 0.23 153
TI-DOFE [24]130.5 1.76 144 6.02 116 0.01 6 6.21 181 11.7 181 0.51 170 1.97 146 7.23 163 0.28 130 6.30 173 11.3 160 0.85 162 14.0 117 22.8 115 1.02 68 4.96 63 20.4 64 0.15 47 5.21 159 27.1 153 0.15 142 9.86 160 23.8 134 0.26 177
SPSA-learn [13]131.1 1.59 109 5.32 67 0.01 6 4.23 148 9.36 132 0.42 144 2.54 167 6.27 143 0.80 174 5.24 163 9.44 136 0.73 146 14.0 117 22.8 115 1.03 78 5.27 107 21.7 117 0.31 127 5.93 180 33.0 183 0.86 184 10.4 174 26.2 178 0.20 52
IIOF-NLDP [129]131.5 1.76 144 6.66 145 0.02 93 3.58 126 9.59 143 0.28 101 1.79 135 5.02 74 0.24 107 4.13 127 8.86 111 0.63 127 13.8 56 22.6 72 1.05 89 6.33 182 24.8 179 0.52 182 5.81 177 31.8 181 0.63 182 9.72 151 24.2 146 0.22 127
ROF-ND [105]131.6 1.73 142 5.36 69 0.01 6 3.43 119 9.15 126 0.27 96 1.59 118 5.63 120 0.21 88 5.50 165 12.2 174 0.77 151 14.0 117 22.8 115 1.21 144 5.96 172 24.2 172 0.42 167 5.51 169 28.7 168 0.11 107 9.90 166 24.7 160 0.22 127
IAOF2 [51]131.9 1.81 150 6.46 138 0.02 93 4.65 163 11.3 179 0.36 124 1.57 114 5.79 132 0.21 88 4.61 149 10.0 150 0.56 112 14.4 166 23.5 167 1.16 122 5.48 141 22.6 146 0.29 121 4.75 120 25.6 110 0.11 107 9.57 140 24.1 142 0.21 91
StereoFlow [44]133.5 4.05 184 12.8 184 0.02 93 5.34 174 12.0 182 0.29 103 1.36 66 5.65 122 0.22 94 3.80 93 8.17 80 0.50 90 16.7 183 27.3 183 1.13 115 7.27 184 29.7 184 0.42 167 4.58 87 25.5 106 0.10 93 10.3 171 26.1 176 0.21 91
SegOF [10]138.5 1.57 105 6.05 119 0.02 93 3.63 127 8.91 120 0.24 86 2.71 172 6.79 157 0.74 172 4.81 153 11.7 167 0.73 146 14.0 117 22.8 115 1.22 157 5.52 145 22.7 150 0.48 176 5.17 157 28.7 168 0.33 174 9.21 100 23.2 95 0.23 153
IRR-PWC_RVC [181]138.5 2.29 173 9.48 174 0.04 174 3.13 106 8.58 109 0.25 89 1.87 142 8.32 177 0.24 107 5.21 162 12.8 176 0.52 98 14.3 160 23.3 162 1.30 183 5.40 133 22.2 137 0.23 91 4.82 129 26.1 130 0.08 61 9.67 146 24.5 153 0.23 153
OFRF [132]138.8 2.03 166 7.52 158 0.03 155 4.40 152 10.2 156 0.41 139 1.67 128 6.55 152 0.17 46 4.10 125 9.44 136 0.50 90 14.2 156 23.2 158 1.16 122 5.75 161 23.2 161 0.24 99 5.02 148 27.0 150 0.11 107 10.0 169 25.4 170 0.22 127
ACK-Prior [27]142.0 1.64 123 6.39 137 0.02 93 2.81 77 7.97 88 0.19 64 2.53 165 5.74 128 0.63 167 4.56 148 10.1 151 1.09 172 14.7 176 24.0 177 1.27 181 6.04 175 24.5 177 0.29 121 5.04 150 27.4 156 0.10 93 11.0 180 27.7 181 0.22 127
SILK [80]142.2 1.86 155 7.35 154 0.01 6 5.84 178 11.2 176 0.60 176 3.00 175 7.69 168 0.83 177 5.68 169 10.6 156 0.69 139 14.1 142 23.0 146 1.00 41 5.31 118 21.3 101 0.36 155 5.02 148 27.0 150 0.28 169 9.50 135 23.5 116 0.24 162
Dynamic MRF [7]145.4 1.58 107 6.37 136 0.02 93 3.55 123 9.67 146 0.27 96 2.35 162 7.75 171 0.50 159 5.74 170 10.9 158 1.06 170 14.0 117 22.8 115 1.23 162 5.90 169 24.1 169 0.51 181 5.28 163 28.7 168 0.34 175 9.71 149 23.9 139 0.21 91
Adaptive flow [45]146.0 2.02 164 6.27 132 0.03 155 5.93 179 11.2 176 0.55 173 1.87 142 5.74 128 0.37 149 5.16 159 9.21 130 0.73 146 14.7 176 24.0 177 1.04 83 5.89 166 24.3 173 0.37 158 4.72 116 26.3 139 0.14 134 9.84 158 24.8 163 0.18 29
Learning Flow [11]147.1 1.62 117 6.12 122 0.02 93 4.43 154 10.4 162 0.33 119 2.86 173 7.92 174 0.82 176 5.19 160 9.72 143 0.59 121 14.6 173 23.8 175 1.10 109 5.42 135 22.4 141 0.27 112 5.24 161 28.3 165 0.17 152 10.3 171 25.4 170 0.23 153
H+S_RVC [177]148.7 2.01 163 7.81 162 0.01 6 4.57 161 9.19 128 0.41 139 2.93 174 9.46 179 0.48 158 8.52 182 12.1 172 0.86 163 14.5 170 23.4 165 1.09 106 5.54 150 22.6 146 0.35 151 5.77 175 28.8 172 0.31 171 9.88 163 23.6 121 0.21 91
StereoOF-V1MT [117]148.8 1.94 161 7.40 156 0.02 93 3.93 135 9.53 141 0.41 139 2.57 168 7.29 164 0.60 165 6.23 172 11.5 165 0.94 167 14.2 156 23.0 146 1.24 169 5.81 164 22.7 150 0.48 176 5.53 172 28.2 162 0.29 170 9.16 92 22.7 62 0.22 127
FOLKI [16]150.5 1.88 157 7.22 153 0.02 93 6.20 180 11.2 176 0.86 182 2.60 169 9.02 178 0.64 168 7.81 179 12.1 172 1.70 181 14.6 173 23.7 172 1.06 93 5.19 100 21.0 89 0.24 99 5.43 167 28.9 173 0.32 172 9.77 154 24.1 142 0.21 91
NL-TV-NCC [25]151.2 2.10 168 7.63 161 0.03 155 3.63 127 9.77 151 0.25 89 2.10 150 6.55 152 0.29 135 5.56 168 12.2 174 0.54 106 14.5 170 23.5 167 1.08 102 6.15 176 24.4 174 0.36 155 6.66 184 29.8 178 0.16 149 10.3 171 25.8 175 0.21 91
UnFlow [127]151.4 2.13 169 8.96 170 0.03 155 4.27 149 9.79 152 0.42 144 2.12 154 7.71 169 0.35 143 4.42 137 10.4 154 0.67 136 14.0 117 22.9 136 1.16 122 5.85 165 23.3 164 0.47 173 4.82 129 25.6 110 0.16 149 11.0 180 25.7 174 0.33 182
SLK [47]155.8 2.08 167 8.23 167 0.01 6 5.10 172 9.38 133 0.50 167 3.21 176 7.73 170 0.83 177 8.10 181 14.2 180 1.61 179 14.5 170 23.7 172 1.06 93 5.77 162 22.5 143 0.36 155 5.84 178 30.6 179 0.36 177 9.87 161 24.4 148 0.22 127
HCIC-L [97]156.7 3.37 183 10.9 181 0.07 182 4.98 167 10.3 159 0.38 134 2.44 163 8.00 175 0.36 144 7.09 175 13.0 177 0.71 143 14.9 179 24.2 179 1.07 97 5.99 174 24.1 169 0.23 91 4.74 119 26.0 126 0.11 107 12.3 184 30.4 184 0.25 168
WRT [146]157.6 1.84 153 6.75 149 0.03 155 4.02 139 9.17 127 0.37 130 3.21 176 5.25 95 0.84 179 4.42 137 9.03 119 0.84 160 14.3 160 23.4 165 1.08 102 6.54 183 26.5 183 0.54 183 6.27 182 34.8 184 0.84 183 10.9 179 27.5 180 0.27 179
WOLF_ROB [144]163.1 2.64 176 9.90 176 0.03 155 5.04 168 10.9 171 0.45 152 2.66 170 6.77 156 0.46 155 4.88 156 12.0 171 0.65 132 14.4 166 23.5 167 1.22 157 5.89 166 23.6 165 0.37 158 5.89 179 29.3 174 0.19 156 9.87 161 24.7 160 0.25 168
FFV1MT [104]163.8 2.64 176 10.4 179 0.03 155 4.88 165 9.35 130 0.52 172 4.45 181 13.1 183 0.71 171 7.42 176 11.9 169 1.22 175 14.6 173 23.7 172 1.09 106 5.53 148 21.1 96 0.33 142 6.16 181 29.7 177 0.35 176 10.5 177 25.6 173 0.26 177
PGAM+LK [55]168.8 2.35 175 9.74 175 0.05 180 5.04 168 10.5 165 0.66 178 3.38 178 9.68 180 0.84 179 7.99 180 14.6 182 1.24 177 14.7 176 23.8 175 1.10 109 5.92 170 23.9 168 0.35 151 5.33 165 28.5 167 0.17 152 9.88 163 24.6 157 0.32 181
Pyramid LK [2]169.8 2.13 169 8.10 165 0.04 174 7.17 183 11.5 180 0.99 184 6.22 183 6.97 160 1.21 183 13.9 184 24.7 184 2.97 184 15.7 182 25.7 182 1.11 111 5.42 135 22.0 128 0.30 126 5.55 173 29.5 176 0.52 179 11.9 182 29.7 183 0.54 184
Heeger++ [102]172.5 3.11 182 11.9 183 0.03 155 4.77 164 9.65 145 0.51 170 4.48 182 12.0 182 0.80 174 7.42 176 11.9 169 1.22 175 15.0 180 24.5 180 1.23 162 6.24 178 23.0 159 0.60 184 6.37 183 29.4 175 0.32 172 10.4 174 25.1 169 0.25 168
GroupFlow [9]173.2 2.80 181 11.2 182 0.04 174 4.49 157 10.5 165 0.43 146 3.45 179 9.80 181 0.88 181 5.90 171 13.7 179 1.21 174 15.1 181 24.6 181 1.24 169 6.24 178 25.2 181 0.49 179 5.51 169 28.7 168 0.21 161 10.6 178 26.4 179 0.24 162
Periodicity [79]181.0 2.65 178 10.3 178 0.09 183 9.86 184 13.0 184 0.95 183 7.07 184 15.7 184 2.07 184 9.47 183 22.6 183 1.94 182 16.9 184 27.6 184 1.35 184 6.22 177 24.5 177 0.41 165 5.73 174 30.9 180 0.58 180 12.2 183 29.3 182 0.40 183
AVG_FLOW_ROB [137]185.0 18.5 185 43.1 185 1.46 185 22.0 185 25.4 185 2.17 185 18.9 185 25.1 185 4.07 185 34.3 185 52.0 185 7.35 185 26.2 185 39.9 185 2.35 185 16.3 185 52.5 185 2.03 185 21.5 185 44.4 185 1.54 185 26.6 185 42.2 185 2.44 185
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.