Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
SD
interpolation
error
avg. Mequon
(Hidden texture)
im0   GT   im1
Schefflera
(Hidden texture)
im0   GT   im1
Urban
(Synthetic)
im0   GT   im1
Teddy
(Stereo)
im0   GT   im1
Backyard
(High-speed camera)
im0   GT   im1
Basketball
(High-speed camera)
im0   GT   im1
Dumptruck
(High-speed camera)
im0   GT   im1
Evergreen
(High-speed camera)
im0   GT   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
SoftSplat [169]6.1 4.71 1 5.71 2 1.42 3 5.82 2 7.42 4 2.98 19 9.56 4 9.45 4 6.82 12 6.69 1 8.59 1 5.07 2 18.5 10 21.0 10 7.63 2 10.9 3 15.4 3 5.18 26 16.7 3 25.6 3 6.69 20 15.1 5 19.0 5 6.17 2
BMBC [172]11.8 5.17 3 6.57 4 1.56 6 6.16 5 7.86 7 3.58 38 12.7 13 11.7 12 9.83 44 8.17 5 10.6 6 6.27 11 16.9 5 19.2 5 8.14 11 10.4 2 14.7 2 5.03 17 18.0 10 27.5 10 6.24 1 15.2 6 19.1 6 8.10 54
FGME [158]12.2 5.49 8 7.87 9 1.40 1 6.88 15 8.20 13 4.52 88 11.2 6 12.4 19 7.41 15 7.30 3 9.16 3 7.71 23 16.3 2 18.4 2 9.05 25 12.4 8 17.7 8 4.89 6 16.2 2 24.9 2 6.38 7 15.5 7 19.5 7 6.70 13
STAR-Net [164]15.0 5.30 5 7.45 7 1.40 1 7.21 17 9.10 26 3.88 53 12.8 15 13.2 24 8.32 26 8.94 9 10.8 10 5.65 4 16.6 4 18.9 4 7.90 5 13.9 16 19.7 16 5.02 16 21.2 27 32.5 27 6.59 18 16.7 15 21.0 15 5.33 1
EAFI [171]15.5 5.84 10 8.61 12 1.51 5 6.51 8 8.23 14 4.09 67 9.18 3 9.46 5 5.53 3 8.20 6 10.4 5 6.85 16 19.4 15 22.0 15 8.29 12 16.9 45 24.0 51 4.93 10 19.2 14 29.5 15 6.46 10 14.7 2 18.4 2 6.94 26
DCM [185]15.8 5.08 2 6.51 3 1.87 84 5.57 1 7.02 1 2.99 20 7.83 1 7.98 1 5.12 2 7.08 2 8.89 2 5.62 3 18.9 14 21.4 14 8.50 20 13.2 14 18.7 14 4.82 3 17.8 6 27.1 6 6.48 14 14.9 3 18.7 3 8.47 146
AdaCoF [165]18.0 6.28 13 9.48 18 2.43 140 6.15 4 7.83 6 3.49 35 13.8 34 9.26 2 10.4 52 9.55 12 11.3 12 6.22 8 19.4 15 22.0 15 8.11 9 10.9 3 15.4 3 4.92 8 18.5 11 28.4 11 6.36 3 15.0 4 18.9 4 6.59 9
CyclicGen [149]24.0 5.21 4 5.40 1 4.82 173 6.70 12 7.19 2 6.53 166 8.79 2 10.2 7 7.42 16 10.2 15 10.7 7 11.3 101 18.5 10 21.0 10 7.91 7 7.38 1 10.4 1 4.92 8 13.6 1 20.8 1 6.46 10 10.5 1 13.2 1 6.74 19
EDSC [174]24.1 6.50 17 9.34 16 4.62 171 6.34 6 8.04 8 4.17 74 11.9 8 12.1 14 6.77 10 8.83 8 11.1 11 8.90 52 20.1 17 22.8 18 8.41 18 15.6 25 22.2 27 4.95 11 17.1 4 26.2 4 6.37 5 18.2 26 22.9 26 6.45 3
FRUCnet [153]25.1 7.39 26 10.7 24 5.61 180 6.60 9 8.27 15 4.37 82 12.6 11 12.4 19 9.21 36 9.30 11 11.7 15 9.37 63 18.2 9 20.6 9 7.68 3 12.2 5 17.3 5 4.96 13 17.6 5 26.9 5 6.89 24 15.9 9 19.9 9 6.73 16
MS-PFT [159]25.2 6.84 21 10.3 22 2.20 128 7.23 19 9.20 28 4.24 77 12.5 10 13.7 27 7.81 21 8.95 10 11.5 13 6.31 12 18.5 10 21.0 10 9.24 27 12.9 12 18.3 12 4.98 15 19.4 16 29.7 18 7.28 31 17.8 23 22.4 24 6.74 19
DSepConv [162]26.0 6.88 22 10.3 22 4.01 163 6.65 10 8.37 16 4.68 95 13.0 17 11.9 13 7.98 23 10.7 16 12.5 21 9.29 61 17.3 8 19.6 8 8.34 14 12.6 9 17.9 10 4.95 11 17.8 6 27.3 7 6.37 5 17.7 21 22.2 21 6.82 25
GDCN [173]26.1 5.89 11 8.80 13 1.46 4 7.53 32 9.15 27 4.14 70 13.2 21 14.4 29 8.69 29 12.8 34 12.4 20 9.09 55 27.4 66 31.1 66 8.38 15 12.6 9 17.8 9 5.14 24 17.9 9 27.4 9 6.46 10 17.8 23 22.3 22 6.74 19
MPRN [151]26.2 6.90 23 10.7 24 1.78 61 7.67 41 8.95 21 4.37 82 10.2 5 12.1 14 4.23 1 11.0 23 14.1 26 7.77 25 20.8 22 23.5 22 8.13 10 14.1 18 19.9 18 5.38 29 20.8 23 31.7 23 7.28 31 18.1 25 22.7 25 7.62 37
CtxSyn [134]26.8 5.47 6 7.82 8 2.18 125 5.98 3 7.57 5 3.23 30 19.2 121 10.6 8 17.0 126 7.49 4 9.86 4 5.67 5 20.6 19 23.3 19 8.83 24 12.8 11 18.0 11 4.72 2 19.4 16 29.6 16 6.47 13 16.8 16 21.0 15 7.43 35
ADC [161]28.2 6.60 18 9.73 19 4.20 167 6.40 7 8.08 11 4.08 66 15.1 54 10.7 9 10.6 57 10.9 20 12.1 18 8.34 37 20.6 19 23.4 20 8.39 16 14.2 20 20.1 21 4.97 14 19.1 13 29.3 13 6.45 9 17.7 21 22.3 22 6.54 6
SuperSlomo [130]32.8 7.27 25 10.8 26 4.59 170 7.40 26 9.09 24 5.23 125 11.7 7 11.2 11 6.26 6 11.1 25 12.9 24 10.9 93 21.1 23 23.9 23 8.02 8 14.2 20 20.0 20 4.85 5 19.9 20 30.4 20 6.69 20 17.4 19 21.8 19 6.97 27
MAF-net [163]33.0 6.90 23 9.87 20 5.38 178 7.49 30 8.96 22 5.64 153 12.6 11 13.0 23 8.75 31 10.7 16 12.5 21 8.27 35 21.4 24 24.3 24 8.67 23 14.8 23 20.9 23 5.10 20 20.9 24 32.1 24 6.42 8 16.6 13 20.8 13 6.66 11
STSR [170]33.6 6.06 12 8.60 11 3.79 159 8.01 69 7.20 3 10.4 182 13.1 19 10.8 10 11.4 67 8.49 7 10.7 7 8.73 46 20.7 21 23.4 20 7.52 1 15.1 24 21.3 24 5.34 28 20.1 21 30.7 21 7.22 30 15.7 8 19.7 8 6.56 8
TOF-M [150]35.0 6.83 20 10.1 21 3.40 158 7.55 33 9.25 29 5.28 126 13.2 21 10.1 6 10.7 59 10.7 16 13.0 25 9.18 58 22.7 25 25.7 25 8.66 22 13.7 15 19.3 15 5.12 22 21.0 25 32.1 24 6.49 15 19.6 28 24.6 28 6.79 24
OFRI [154]36.8 5.75 9 6.90 5 5.06 175 8.11 79 8.48 17 9.61 177 13.4 24 13.5 25 9.12 34 11.0 23 12.3 19 13.7 155 16.5 3 18.7 3 7.90 5 16.3 36 23.2 37 4.90 7 18.9 12 28.9 12 6.34 2 15.9 9 19.9 9 6.50 5
FeFlow [167]37.3 6.81 19 8.52 10 6.23 182 8.28 95 8.62 19 9.28 174 12.3 9 9.39 3 9.93 45 10.9 20 11.7 15 12.8 150 15.8 1 17.8 1 8.46 19 12.3 6 17.4 6 4.56 1 17.8 6 27.3 7 6.72 22 18.6 27 23.4 27 7.07 32
DAIN [152]38.2 6.45 16 9.46 17 4.07 164 6.69 11 8.09 12 6.20 162 16.0 67 12.2 18 13.6 97 9.77 14 11.7 15 10.3 79 16.9 5 19.2 5 8.65 21 13.9 16 19.8 17 5.10 20 19.2 14 29.4 14 8.11 91 16.3 11 20.5 11 6.74 19
DAI [168]38.5 5.47 6 7.37 6 3.86 161 7.29 22 8.64 20 5.37 137 13.4 24 16.0 47 9.34 40 10.8 19 10.7 7 14.9 169 20.1 17 22.7 17 8.32 13 17.0 50 24.1 53 5.06 19 20.1 21 30.8 22 6.36 3 16.9 17 21.1 17 6.73 16
TC-GAN [166]40.0 6.31 14 9.15 14 4.14 165 6.80 14 8.05 9 6.66 167 17.1 94 12.5 21 14.5 106 9.69 13 11.5 13 10.3 79 17.0 7 19.2 5 8.40 17 14.5 22 20.5 22 5.05 18 19.4 16 29.6 16 7.95 81 16.5 12 20.7 12 6.77 23
MEMC-Net+ [160]45.2 6.44 15 9.31 15 4.42 169 8.18 86 8.07 10 9.92 179 14.7 48 12.1 14 13.3 92 10.9 20 12.6 23 12.4 144 18.8 13 21.3 13 9.95 30 12.3 6 17.4 6 4.83 4 19.6 19 29.9 19 8.66 104 16.6 13 20.8 13 7.01 29
MDP-Flow2 [68]48.0 8.94 58 13.9 55 1.56 6 7.36 24 9.57 35 2.68 5 15.9 65 20.5 114 16.3 122 13.4 43 18.2 57 8.87 51 24.1 32 27.3 32 12.1 44 17.6 59 25.0 64 6.01 51 22.8 38 34.9 39 7.11 27 20.9 45 26.2 45 7.78 41
CBF [12]49.5 8.02 28 12.4 28 1.75 49 8.18 86 10.3 68 4.84 108 13.2 21 15.5 41 9.17 35 11.5 26 15.0 28 7.94 30 22.8 26 25.8 26 12.2 63 16.2 34 22.9 35 6.24 75 23.4 50 35.8 50 8.06 90 21.2 52 26.7 54 8.24 85
PMMST [112]50.0 8.93 54 14.0 62 1.57 8 7.21 17 9.34 30 2.66 3 14.1 40 16.2 53 11.0 62 15.6 112 21.2 123 14.7 165 24.1 32 27.3 32 12.1 44 16.3 36 23.0 36 5.91 41 22.6 35 34.5 35 7.52 47 19.9 31 25.0 31 8.18 70
CoT-AMFlow [175]53.7 8.90 52 14.0 62 1.64 14 7.56 35 9.84 43 2.60 1 16.3 75 20.2 111 14.8 110 13.3 39 18.0 52 8.86 50 24.1 32 27.3 32 12.1 44 17.9 71 25.4 73 6.03 53 22.9 39 35.1 42 7.09 26 20.7 40 26.0 41 8.55 152
SepConv-v1 [125]54.2 8.19 30 12.5 29 5.08 176 7.89 55 9.09 24 8.08 173 20.8 137 12.1 14 18.4 140 12.5 32 14.8 27 11.7 124 23.5 28 26.6 28 9.13 26 14.1 18 19.9 18 5.12 22 21.1 26 32.2 26 8.37 98 17.2 18 21.5 18 6.71 14
DeepFlow [85]55.4 8.76 43 13.7 45 1.59 9 8.08 77 10.4 79 4.72 97 13.8 34 18.1 79 7.83 22 12.1 27 15.2 29 8.41 39 28.8 98 32.7 98 12.1 44 17.0 50 24.1 53 5.99 48 21.6 29 33.0 30 7.45 40 23.0 108 28.9 109 7.80 43
UnDAF [184]57.8 8.73 41 13.7 45 1.64 14 7.56 35 9.88 45 2.62 2 16.1 69 23.1 140 17.0 126 13.7 50 18.6 63 12.0 130 24.5 38 27.8 39 12.1 44 17.5 58 24.8 58 6.05 54 22.7 36 34.8 38 7.08 25 20.6 36 25.8 36 9.44 165
DeepFlow2 [106]60.4 8.59 37 13.4 38 1.64 14 8.06 75 10.4 79 4.45 85 13.8 34 18.6 84 8.12 25 12.4 29 16.1 31 10.6 85 28.5 92 32.3 91 12.3 74 16.7 41 23.6 41 5.92 43 23.0 44 35.0 40 7.49 43 22.6 89 28.4 90 8.47 146
AdaConv-v1 [124]65.0 9.51 94 14.1 70 4.99 174 9.04 132 9.51 34 9.70 178 18.8 119 13.8 28 18.3 139 14.5 75 16.5 36 15.2 171 25.9 48 29.4 48 7.81 4 13.1 13 18.4 13 5.63 33 21.4 28 32.7 28 7.45 40 17.4 19 21.8 19 6.73 16
CLG-TV [48]65.0 8.34 34 12.9 33 1.98 104 8.74 117 10.8 107 4.75 104 14.0 38 16.0 47 9.23 37 12.4 29 16.1 31 9.95 72 29.7 126 33.7 126 12.0 41 16.8 42 23.9 45 5.46 30 22.2 31 32.9 29 8.02 85 21.8 69 27.4 70 8.33 114
SIOF [67]65.5 8.78 45 13.5 40 1.80 69 8.97 128 11.2 134 4.51 87 16.7 84 23.2 141 11.6 69 13.2 37 17.7 46 9.61 68 23.7 30 26.8 30 11.8 34 17.8 65 25.2 68 5.98 47 23.4 50 35.9 53 7.33 34 22.1 73 27.8 76 8.15 63
Aniso. Huber-L1 [22]66.7 8.22 31 12.7 31 1.84 80 9.12 143 11.1 129 5.11 118 13.6 30 16.3 55 7.58 19 12.2 28 16.1 31 9.16 57 29.8 132 33.8 131 12.7 86 16.9 45 23.9 45 5.57 32 23.2 47 35.5 47 7.30 33 21.8 69 27.4 70 8.32 112
NN-field [71]68.0 9.03 66 14.1 70 1.74 44 7.01 16 9.05 23 2.74 10 18.3 114 19.1 92 12.6 84 16.8 139 22.7 145 15.8 173 24.2 35 27.5 35 12.1 44 17.8 65 25.1 66 6.07 59 23.1 45 35.4 46 7.69 61 20.6 36 25.9 38 8.36 126
LME [70]68.4 8.97 60 14.0 62 1.62 11 8.07 76 10.5 87 3.69 43 16.9 87 17.7 71 9.29 39 14.5 75 19.6 88 9.68 69 29.2 117 33.1 117 15.3 138 18.1 76 25.7 78 6.15 66 22.7 36 34.7 36 7.37 36 21.0 48 26.4 49 8.20 76
CombBMOF [111]68.5 9.74 110 14.3 80 3.85 160 7.82 49 10.2 59 3.81 50 16.2 72 19.1 92 12.8 86 13.8 53 18.5 62 10.2 77 26.5 49 30.0 49 12.2 63 17.8 65 25.2 68 6.09 63 23.1 45 35.2 45 7.64 56 21.3 55 26.7 54 8.21 81
MDP-Flow [26]69.3 8.27 32 12.8 32 1.74 44 7.26 21 9.42 31 3.90 54 17.2 95 16.1 52 15.0 113 13.6 47 18.0 52 10.9 93 28.8 98 32.7 98 15.3 138 17.9 71 25.2 68 7.36 138 23.6 57 36.1 57 12.2 150 20.6 36 25.9 38 8.07 48
IROF-TV [53]69.8 8.93 54 13.9 55 1.82 76 8.15 83 10.6 92 4.01 61 13.9 37 17.6 69 8.70 30 13.3 39 18.0 52 9.04 54 28.5 92 32.3 91 15.3 138 18.5 91 26.2 93 6.57 105 24.7 82 37.8 84 6.81 23 22.2 78 28.0 81 6.71 14
NNF-Local [75]69.8 8.84 48 13.8 48 1.61 10 7.25 20 9.44 32 2.76 11 14.6 46 19.3 98 14.5 106 16.0 126 21.6 132 15.8 173 24.2 35 27.5 35 12.2 63 18.4 85 26.0 88 6.42 96 24.2 67 37.1 71 9.54 121 20.3 34 25.4 34 8.27 97
ALD-Flow [66]70.1 10.4 131 16.0 130 1.76 52 7.99 66 10.3 68 3.78 48 14.1 40 19.3 98 6.64 8 16.1 128 21.9 136 5.92 7 26.5 49 30.0 49 14.0 103 16.9 45 23.9 45 6.23 74 22.5 34 34.4 34 7.50 45 23.2 118 29.2 123 8.09 51
p-harmonic [29]70.3 8.89 51 13.9 55 1.68 21 8.86 122 10.9 114 5.20 124 13.4 24 17.5 68 6.45 7 13.7 50 17.9 51 10.0 74 28.9 103 32.8 104 12.8 87 17.6 59 24.9 61 6.53 104 22.9 39 35.0 40 8.88 105 22.5 84 28.3 86 8.10 54
WLIF-Flow [91]70.5 8.64 38 13.4 38 1.69 25 7.89 55 10.2 59 3.94 56 17.0 90 22.0 125 14.5 106 13.7 50 18.4 60 11.5 113 26.7 52 30.3 52 12.3 74 19.8 140 28.0 141 8.12 162 22.4 33 34.2 33 7.58 53 21.1 50 26.4 49 7.62 37
Second-order prior [8]71.0 8.06 29 12.5 29 1.93 94 8.80 118 11.0 119 4.80 107 12.8 15 16.2 53 7.51 18 12.6 33 16.7 37 6.25 10 28.9 103 32.8 104 12.2 63 18.1 76 25.7 78 6.10 64 23.3 48 35.5 47 9.35 118 22.7 95 28.6 101 8.45 144
OAR-Flow [123]71.0 9.14 75 14.0 62 1.71 32 7.90 57 10.1 50 4.04 64 14.3 43 18.8 87 5.59 4 16.6 136 22.6 142 6.23 9 27.7 76 31.4 75 15.3 138 15.9 30 22.4 30 6.89 119 24.2 67 36.4 61 7.80 71 22.9 105 28.8 107 8.15 63
Ad-TV-NDC [36]73.0 9.09 71 13.8 48 2.24 133 9.50 162 11.1 129 6.94 169 14.2 42 15.4 40 6.85 13 14.5 75 18.6 63 9.51 65 27.4 66 31.1 66 12.3 74 18.2 81 25.8 84 6.40 94 22.9 39 34.7 36 7.43 37 20.6 36 25.8 36 8.26 94
DF-Auto [113]75.2 9.30 86 14.4 89 1.99 105 8.37 99 10.6 92 4.99 112 15.5 61 22.3 127 8.88 32 13.3 39 17.6 45 9.86 71 25.7 45 29.1 45 13.9 102 18.1 76 25.7 78 5.96 46 25.2 91 38.6 96 10.8 140 20.7 40 25.9 38 8.09 51
IROF++ [58]75.5 8.58 36 13.3 36 1.68 21 7.99 66 10.4 79 3.84 51 17.3 97 18.5 82 12.5 82 12.4 29 16.7 37 9.15 56 28.4 91 32.3 91 15.3 138 19.5 131 27.6 132 6.06 57 23.3 48 35.6 49 8.55 102 23.4 127 29.4 132 7.79 42
Brox et al. [5]75.8 9.33 88 14.7 94 1.62 11 7.86 53 10.1 50 4.14 70 15.9 65 16.0 47 10.4 52 13.5 46 17.7 46 8.77 48 26.8 53 30.4 53 11.9 36 19.1 116 27.0 117 9.52 177 28.6 153 43.6 151 23.0 183 19.9 31 25.0 31 8.05 47
SegFlow [156]77.3 10.1 122 15.9 127 1.67 19 7.58 37 9.88 45 3.06 25 14.8 49 15.0 35 6.71 9 17.3 148 23.6 156 13.1 152 27.7 76 31.4 75 15.3 138 15.8 28 22.3 29 6.18 69 22.9 39 35.1 42 8.62 103 23.1 111 29.0 113 8.31 108
Modified CLG [34]77.9 7.87 27 12.2 27 1.68 21 8.96 126 10.7 102 5.94 160 16.8 85 16.7 57 15.9 120 13.3 39 16.4 35 12.6 148 27.6 72 31.3 72 11.9 36 18.8 104 26.6 105 6.50 101 22.3 32 34.0 32 7.67 58 22.2 78 27.9 78 8.64 155
NNF-EAC [101]78.5 9.00 63 14.0 62 1.99 105 7.79 47 10.2 59 2.85 15 17.5 103 25.1 158 19.2 144 15.4 104 20.6 108 11.6 118 29.9 136 33.9 136 12.1 44 16.5 38 23.4 38 5.99 48 22.9 39 35.1 42 7.51 46 20.9 45 26.2 45 8.42 141
Local-TV-L1 [65]81.9 8.65 39 13.3 36 1.90 90 9.07 137 11.0 119 5.04 116 13.1 19 15.3 39 8.62 28 12.8 34 17.0 39 7.89 29 30.8 166 35.0 167 15.5 172 18.4 85 26.0 88 6.98 123 23.9 64 36.5 65 7.66 57 21.4 58 26.9 59 8.40 137
HCFN [157]82.0 9.82 115 15.4 117 1.74 44 7.71 43 10.1 50 3.24 31 14.8 49 17.1 62 9.77 43 15.2 96 20.6 108 10.8 89 28.1 87 31.9 88 12.1 44 18.0 74 25.4 73 6.40 94 26.0 112 39.7 116 7.69 61 23.1 111 29.0 113 8.48 148
F-TV-L1 [15]83.0 10.4 131 16.2 132 1.94 97 9.02 130 11.2 134 4.72 97 14.6 46 16.7 57 11.0 62 14.2 62 18.9 73 10.3 79 27.5 69 31.2 70 12.3 74 16.0 31 22.6 31 6.38 91 23.9 64 36.6 67 9.23 114 21.3 55 26.7 54 10.2 171
JOF [136]83.2 9.04 67 14.1 70 1.81 73 7.55 33 9.71 42 5.06 117 15.1 54 16.7 57 12.0 71 14.4 71 19.4 83 11.4 107 29.2 117 33.2 119 15.4 164 19.8 140 28.0 141 6.36 90 23.4 50 35.8 50 7.68 60 21.4 58 26.8 58 8.30 105
PH-Flow [99]83.8 9.30 86 14.3 80 1.70 29 7.70 42 10.1 50 2.82 14 14.9 53 20.6 117 14.8 110 14.3 66 19.4 83 11.5 113 25.0 42 28.3 41 12.2 63 21.6 177 30.7 178 9.38 176 25.0 89 38.3 91 7.76 68 22.6 89 28.4 90 8.15 63
FMOF [92]84.2 9.22 81 13.9 55 1.96 101 7.58 37 9.87 44 2.87 16 19.5 125 22.4 128 17.7 134 15.3 100 20.6 108 12.5 147 24.5 38 27.7 37 13.7 97 19.3 125 27.3 126 6.05 54 24.6 80 37.7 82 6.64 19 23.4 127 29.4 132 6.98 28
VCN_RVC [179]85.3 14.1 174 22.5 177 1.93 94 7.72 44 10.1 50 3.17 28 15.6 63 19.7 101 11.0 62 22.0 172 29.9 173 10.2 77 27.1 58 30.7 58 12.1 44 17.6 59 25.0 64 5.84 35 24.3 72 37.1 71 7.57 51 22.1 73 27.7 74 11.2 174
C-RAFT_RVC [182]86.3 13.0 168 20.5 168 2.43 140 7.97 65 10.3 68 3.53 36 16.1 69 19.7 101 12.3 78 15.5 108 21.0 119 12.2 137 24.9 41 28.3 41 11.8 34 18.3 84 25.9 86 6.05 54 24.8 83 37.9 86 9.19 113 21.1 50 26.5 52 8.25 90
PRAFlow_RVC [178]86.3 10.6 135 16.6 137 1.85 82 7.46 29 9.61 37 3.14 27 16.1 69 20.9 118 15.5 119 15.2 96 20.6 108 6.66 13 23.8 31 26.9 31 12.1 44 18.9 108 26.8 112 6.70 109 23.8 59 36.5 65 14.0 160 24.0 156 30.2 157 8.18 70
Filter Flow [19]86.5 9.35 90 14.5 90 1.79 65 9.19 145 11.1 129 5.50 145 17.6 107 16.8 61 12.2 75 14.0 58 18.0 52 11.3 101 24.6 40 27.9 40 12.2 63 18.4 85 26.0 88 7.54 144 24.8 83 37.9 86 7.77 69 21.5 61 27.0 62 8.40 137
DMF_ROB [135]86.8 9.66 102 15.1 106 1.75 49 8.12 81 10.3 68 4.86 109 17.2 95 22.7 134 11.7 70 14.5 75 19.3 79 9.60 66 27.3 63 31.0 63 15.3 138 17.9 71 25.4 73 8.26 165 23.5 54 35.9 53 6.49 15 23.2 118 29.2 123 8.32 112
Sparse Occlusion [54]88.4 9.75 111 15.2 109 2.05 112 8.71 115 11.2 134 4.19 75 13.5 27 15.9 46 7.80 20 14.6 81 19.7 94 7.51 21 30.4 148 34.5 149 15.3 138 16.1 32 22.7 32 6.27 81 26.9 127 41.1 129 7.45 40 23.2 118 29.2 123 8.12 60
TC/T-Flow [77]88.5 9.42 92 14.6 93 2.39 139 8.67 114 11.2 134 4.00 59 13.6 30 16.0 47 8.03 24 17.5 152 23.5 155 10.8 89 27.3 63 31.0 63 15.3 138 17.4 56 24.6 56 5.89 40 25.8 107 37.8 84 9.59 123 22.8 99 28.7 105 8.13 61
CRTflow [81]89.1 8.75 42 13.6 42 2.04 109 9.27 150 11.5 157 5.28 126 16.2 72 22.5 130 9.27 38 12.8 34 17.0 39 11.5 113 27.0 56 30.6 56 15.3 138 17.6 59 24.9 61 6.06 57 27.8 137 42.7 140 7.62 55 23.4 127 29.4 132 8.16 68
COFM [59]89.7 8.95 59 13.8 48 1.90 90 7.42 27 9.61 37 3.19 29 15.3 58 22.1 126 16.3 122 15.4 104 20.9 116 14.6 161 26.8 53 30.4 53 12.2 63 21.4 173 30.3 173 6.26 80 26.3 116 40.4 119 10.4 136 20.8 42 26.1 42 8.36 126
CPM-Flow [114]89.9 9.82 115 15.4 117 1.69 25 7.60 39 9.90 47 3.04 23 15.6 63 15.7 44 7.43 17 16.9 141 23.0 150 12.0 130 27.6 72 31.3 72 15.3 138 18.5 91 26.2 93 7.13 131 23.4 50 35.8 50 9.99 129 23.8 145 29.9 147 8.37 129
ComplOF-FED-GPU [35]90.0 9.91 120 15.5 120 1.77 59 7.74 45 10.1 50 4.25 79 19.8 130 17.7 71 17.0 126 15.3 100 20.7 113 11.8 125 28.2 90 32.0 90 14.5 109 16.2 34 22.8 34 5.95 45 26.2 115 39.6 115 9.25 115 22.7 95 28.4 90 8.25 90
CNN-flow-warp+ref [115]90.0 8.33 33 13.0 34 2.06 114 8.26 94 10.3 68 5.85 157 18.3 114 22.7 134 11.1 65 13.6 47 16.0 30 11.1 97 29.1 115 33.0 114 15.3 138 15.7 27 22.1 26 6.96 122 28.2 143 43.1 144 7.67 58 21.8 69 27.3 68 8.49 149
PMF [73]91.0 9.35 90 14.5 90 1.77 59 7.80 48 10.1 50 2.68 5 24.0 158 28.7 171 22.5 166 15.3 100 20.6 108 11.6 118 25.7 45 29.2 46 12.1 44 19.1 116 27.0 117 5.92 43 27.6 134 42.4 137 9.09 110 23.1 111 29.0 113 6.47 4
RAFT-TF_RVC [180]91.2 12.3 161 19.5 161 2.22 129 7.37 25 9.58 36 2.80 13 13.5 27 17.7 71 10.6 57 15.7 118 21.2 123 8.56 40 24.4 37 27.7 37 12.1 44 20.0 144 28.2 144 7.59 149 26.4 117 40.6 124 9.12 111 22.5 84 28.3 86 8.55 152
2DHMM-SAS [90]91.4 8.83 47 13.6 42 1.76 52 8.88 124 11.3 142 4.29 80 17.5 103 20.9 118 12.5 82 14.5 75 19.6 88 11.3 101 30.1 141 34.1 140 15.1 125 17.6 59 24.9 61 5.84 35 25.2 91 38.7 98 8.23 95 23.1 111 29.1 116 8.16 68
TC-Flow [46]91.5 10.9 141 17.1 143 1.71 32 8.86 122 11.6 160 4.00 59 13.0 17 16.0 47 6.24 5 15.6 112 21.1 120 8.58 41 27.9 79 31.7 81 15.1 125 18.7 100 26.4 101 6.72 110 24.6 80 37.6 80 7.95 81 23.4 127 29.4 132 8.28 101
LDOF [28]92.5 8.85 49 13.8 48 2.04 109 10.2 179 9.70 41 10.8 184 17.0 90 20.4 113 12.0 71 13.4 43 17.4 43 12.3 141 22.9 27 26.0 27 11.9 36 18.9 108 26.7 108 6.27 81 30.1 168 46.3 170 16.0 164 19.7 29 24.7 29 8.89 161
Horn & Schunck [3]92.6 8.92 53 13.6 42 1.73 37 9.79 172 11.4 147 6.31 164 24.1 159 18.7 85 18.6 142 15.8 122 19.4 83 11.1 97 28.0 82 31.8 83 10.4 31 17.8 65 25.2 68 5.54 31 25.3 96 38.4 94 9.70 125 22.1 73 27.7 74 8.27 97
ProFlow_ROB [142]92.6 9.82 115 15.5 120 1.71 32 8.15 83 10.6 92 3.63 40 15.4 60 12.7 22 8.98 33 19.8 167 26.9 168 7.99 31 29.0 113 33.0 114 15.3 138 15.6 25 22.0 25 5.16 25 26.4 117 40.3 118 7.90 79 24.4 165 30.5 164 11.5 176
OFLAF [78]92.7 9.70 105 15.0 103 1.69 25 7.94 62 10.4 79 2.73 9 14.3 43 15.0 35 10.2 48 13.8 53 18.6 63 8.40 38 30.0 138 34.0 138 15.4 164 17.0 50 23.9 45 6.73 111 30.1 168 46.1 168 13.9 158 23.4 127 29.3 128 9.45 166
2D-CLG [1]93.0 8.51 35 13.2 35 1.76 52 8.84 121 10.4 79 5.71 155 19.4 124 15.6 43 15.0 113 14.2 62 16.3 34 14.0 157 31.1 173 35.3 173 20.9 184 16.1 32 22.7 32 6.34 86 27.7 136 42.3 135 8.19 94 21.4 58 26.9 59 8.13 61
Black & Anandan [4]93.2 9.24 83 14.1 70 1.95 99 9.65 169 11.4 147 5.28 126 28.3 168 24.2 148 20.2 154 14.8 85 18.7 68 10.5 83 27.7 76 31.5 78 9.57 29 19.0 113 27.0 117 6.35 88 24.2 67 36.7 68 8.42 99 21.0 48 26.3 48 6.55 7
FlowNetS+ft+v [110]93.3 9.02 65 14.1 70 2.07 118 10.0 177 11.0 119 9.60 176 16.3 75 14.4 29 13.5 96 13.8 53 17.7 46 13.3 153 29.7 126 33.8 131 15.3 138 16.8 42 23.8 43 6.25 78 27.8 137 42.6 138 7.83 75 20.4 35 25.5 35 8.24 85
PGM-C [118]93.4 9.70 105 15.2 109 1.69 25 7.84 52 10.2 59 3.70 44 21.2 140 17.2 64 12.3 78 17.4 149 23.6 156 8.69 43 28.0 82 31.8 83 15.3 138 16.6 39 23.4 38 6.17 67 26.4 117 40.5 123 8.04 87 24.3 162 30.5 164 8.34 117
EpicFlow [100]93.7 9.69 104 15.2 109 1.67 19 7.90 57 10.2 59 4.37 82 16.0 67 14.5 31 9.75 42 19.1 163 25.8 166 12.3 141 27.9 79 31.6 79 15.3 138 16.9 45 23.9 45 6.21 73 24.9 86 38.0 88 10.3 134 24.6 168 30.9 169 8.30 105
MLDP_OF [87]93.9 9.06 68 14.1 70 1.83 79 8.81 119 11.3 142 4.78 106 14.0 38 17.6 69 8.56 27 15.5 108 20.3 104 15.8 173 29.7 126 33.7 126 13.6 93 19.1 116 27.0 117 5.86 38 23.8 59 36.3 59 8.15 93 23.2 118 29.1 116 8.25 90
Fusion [6]94.9 8.82 46 13.8 48 2.62 146 7.96 63 10.1 50 4.47 86 16.5 79 13.6 26 17.3 133 14.0 58 18.1 56 9.97 73 29.8 132 33.8 131 12.8 87 19.4 127 27.4 127 10.1 180 26.4 117 40.4 119 8.14 92 21.7 65 27.2 66 10.1 170
LFNet_ROB [145]95.0 11.6 151 18.2 154 2.58 145 8.05 73 10.4 79 4.02 63 17.8 109 26.6 163 11.5 68 13.2 37 17.8 49 7.21 19 26.9 55 30.5 55 14.8 116 21.1 166 29.9 167 7.31 136 23.5 54 35.9 53 11.3 143 22.4 82 28.2 84 8.11 58
EAI-Flow [147]95.4 11.1 144 15.4 117 6.27 183 8.02 71 10.2 59 4.70 96 16.9 87 20.1 110 15.0 113 14.8 85 19.8 96 4.86 1 29.2 117 33.1 117 14.8 116 16.6 39 23.5 40 5.99 48 23.8 59 36.4 61 20.9 179 22.6 89 28.4 90 11.1 173
TV-L1-MCT [64]95.5 9.18 78 14.2 77 1.78 61 8.53 106 11.1 129 3.70 44 17.7 108 23.3 144 13.6 97 14.4 71 19.5 87 11.6 118 30.5 155 34.6 153 13.8 99 18.1 76 25.7 78 6.02 52 25.8 107 39.5 111 15.0 162 21.7 65 27.3 68 7.99 45
AGIF+OF [84]95.7 9.07 69 14.0 62 1.78 61 7.93 61 10.3 68 3.78 48 14.4 45 17.8 74 12.4 80 14.9 88 20.2 101 11.4 107 28.9 103 32.8 104 15.3 138 20.0 144 28.3 145 6.98 123 25.5 99 39.0 101 7.74 66 23.9 152 30.1 156 8.28 101
S2F-IF [121]96.5 10.3 128 16.3 134 1.79 65 7.83 51 10.2 59 2.90 18 17.0 90 20.0 108 13.9 102 16.1 128 21.6 132 6.69 14 29.2 117 33.2 119 15.3 138 16.8 42 23.7 42 6.34 86 24.9 86 38.2 89 10.7 138 23.9 152 30.0 154 8.35 123
Bartels [41]96.6 12.7 164 20.1 166 2.13 124 8.52 105 11.0 119 4.96 111 13.5 27 14.5 31 10.2 48 14.4 71 18.9 73 10.8 89 23.5 28 26.6 28 12.9 90 19.0 113 26.9 114 6.94 121 24.5 75 37.5 78 19.7 176 23.4 127 29.4 132 8.31 108
OFH [38]98.8 9.54 96 15.0 103 1.74 44 8.49 104 10.6 92 5.13 119 18.1 112 24.9 156 10.4 52 17.4 149 23.7 159 5.72 6 28.7 96 32.5 94 14.6 112 17.6 59 24.8 58 5.85 37 26.0 112 39.2 106 10.2 132 22.7 95 28.5 98 14.1 181
nLayers [57]99.0 9.15 76 14.3 80 1.76 52 7.42 27 9.62 39 3.57 37 27.8 166 29.9 174 25.8 176 15.9 124 21.5 130 11.9 126 30.2 142 34.3 143 14.7 115 20.3 152 28.8 153 6.45 98 23.5 54 36.0 56 7.87 77 21.6 62 27.1 63 8.10 54
HAST [107]99.2 8.87 50 13.8 48 1.76 52 7.34 23 9.50 33 2.70 7 28.8 170 28.6 170 24.0 171 14.9 88 20.2 101 7.68 22 28.9 103 32.8 104 12.1 44 21.3 172 30.2 172 7.57 146 28.6 153 43.9 154 7.55 50 22.8 99 28.7 105 8.43 143
BlockOverlap [61]99.8 9.09 71 14.3 80 2.04 109 8.96 126 10.9 114 5.37 137 18.1 112 15.5 41 18.0 137 14.2 62 17.2 41 14.0 157 28.9 103 32.8 104 13.8 99 18.8 104 26.7 108 7.92 156 24.8 83 37.2 73 21.0 180 20.0 33 25.1 33 8.38 131
TCOF [69]100.1 9.34 89 14.3 80 1.89 86 9.50 162 11.7 167 5.42 139 16.2 72 21.7 123 10.3 50 13.8 53 18.6 63 9.45 64 30.4 148 34.6 153 13.6 93 18.2 81 25.7 78 6.20 72 28.5 150 43.5 150 7.54 48 22.9 105 28.8 107 8.18 70
Layers++ [37]100.3 8.93 54 14.0 62 1.76 52 6.74 13 8.61 18 2.71 8 18.3 114 25.8 161 19.3 145 15.3 100 20.8 114 11.3 101 33.1 181 37.6 181 19.8 181 21.6 177 30.6 177 8.73 171 24.4 73 37.4 76 7.81 73 21.6 62 27.1 63 8.09 51
FlowFields [108]101.5 9.98 121 15.7 123 2.08 120 7.96 63 10.4 79 3.62 39 23.1 151 23.2 141 20.3 156 16.0 126 21.5 130 7.08 18 27.0 56 30.6 56 14.2 105 19.2 122 27.1 122 6.08 62 24.4 73 37.4 76 10.2 132 23.2 118 29.2 123 8.35 123
DPOF [18]101.6 11.0 142 17.4 147 3.88 162 7.78 46 10.2 59 3.01 21 18.7 117 18.1 79 18.4 140 16.5 133 22.4 139 14.6 161 28.8 98 32.7 98 12.1 44 18.9 108 26.7 108 6.18 69 25.2 91 38.4 94 7.59 54 23.6 140 29.6 140 8.07 48
Classic++ [32]102.5 9.48 93 14.9 98 1.80 69 8.59 109 11.0 119 4.61 91 13.7 33 15.0 35 9.57 41 14.4 71 19.0 75 8.76 47 29.9 136 33.9 136 13.6 93 20.2 150 28.7 151 6.87 118 27.4 131 42.0 131 9.63 124 23.8 145 29.9 147 8.34 117
NL-TV-NCC [25]103.4 9.19 80 14.3 80 2.18 125 9.02 130 11.6 160 4.13 69 14.8 49 16.7 57 10.9 61 20.8 168 28.1 169 8.19 34 26.5 49 30.0 49 13.1 91 18.9 108 26.7 108 6.43 97 26.6 123 40.4 119 15.1 163 23.7 144 29.7 144 8.29 104
SRR-TVOF-NL [89]103.7 9.65 100 14.8 95 1.82 76 8.21 91 10.6 92 4.76 105 22.7 149 28.1 168 21.9 161 15.6 112 20.9 116 9.18 58 28.9 103 32.8 104 15.3 138 20.7 161 29.3 161 5.91 41 24.5 75 37.6 80 6.56 17 22.5 84 28.2 84 8.34 117
HBM-GC [103]103.7 9.25 84 14.5 90 1.81 73 9.08 139 11.9 176 3.75 47 17.3 97 18.7 85 17.9 135 14.3 66 19.2 77 8.85 49 30.0 138 34.0 138 15.5 172 21.5 174 30.4 174 8.27 166 27.4 131 42.1 134 7.15 28 20.8 42 26.1 42 7.05 31
H+S_RVC [177]104.6 9.25 84 14.2 77 1.72 35 8.58 108 10.1 50 5.62 150 17.8 109 18.4 81 12.9 88 14.3 66 17.5 44 9.60 66 30.2 142 34.3 143 15.6 174 19.7 137 27.8 136 7.04 127 25.9 111 39.5 111 10.3 134 22.9 105 28.6 101 8.39 132
Complementary OF [21]104.7 11.4 150 18.1 153 1.70 29 9.23 148 12.1 177 4.19 75 31.6 175 19.0 91 23.6 168 19.5 166 26.5 167 6.72 15 28.1 87 31.8 83 14.6 112 17.3 55 24.4 55 6.38 91 26.1 114 39.0 101 8.92 107 22.3 80 27.9 78 7.57 36
Nguyen [33]105.3 9.83 118 15.2 109 1.73 37 9.59 167 11.0 119 5.65 154 15.3 58 20.5 114 10.3 50 14.6 81 18.8 69 12.1 133 28.8 98 32.7 98 12.2 63 19.4 127 27.4 127 8.01 160 29.7 163 45.5 163 8.29 97 21.2 52 26.6 53 8.34 117
LSM_FLOW_RVC [183]105.3 13.7 172 21.2 172 4.18 166 8.57 107 11.0 119 3.98 58 19.5 125 25.2 160 13.3 92 24.7 176 33.6 178 8.11 33 27.6 72 31.4 75 15.1 125 17.0 50 24.0 51 6.52 103 25.5 99 39.1 104 7.44 38 22.5 84 28.3 86 8.23 83
CompactFlow_ROB [155]105.7 12.7 164 20.0 165 2.28 134 8.24 93 10.7 102 4.14 70 19.8 130 22.5 130 14.5 106 27.5 183 36.7 184 7.77 25 27.6 72 31.3 72 12.1 44 19.8 140 28.0 141 6.19 71 27.4 131 42.0 131 7.16 29 22.0 72 27.6 72 8.20 76
FESL [72]106.3 9.09 71 13.9 55 1.74 44 7.90 57 10.3 68 3.35 33 16.5 79 21.9 124 12.0 71 15.1 94 20.3 104 11.4 107 30.8 166 35.0 167 15.4 164 19.6 133 27.8 136 6.48 99 27.8 137 42.6 138 7.75 67 23.9 152 30.0 154 8.39 132
Efficient-NL [60]106.4 8.71 40 13.5 40 1.68 21 8.66 113 11.2 134 3.65 41 22.5 145 20.0 108 19.9 150 14.3 66 19.3 79 11.0 95 30.5 155 34.7 160 15.0 120 20.1 146 28.4 147 6.27 81 28.5 150 43.7 152 8.92 107 23.8 145 29.9 147 6.66 11
ProbFlowFields [126]106.4 10.1 122 16.0 130 1.78 61 8.04 72 10.5 87 3.08 26 25.8 165 28.8 172 24.3 172 14.5 75 19.6 88 11.4 107 27.2 61 30.9 62 15.3 138 17.4 56 24.6 56 8.78 172 27.3 130 42.0 131 18.8 174 22.4 82 28.1 82 8.39 132
PWC-Net_RVC [143]107.3 11.7 153 18.2 154 2.05 112 8.35 98 10.9 114 3.91 55 13.6 30 17.4 67 6.79 11 18.8 159 25.6 165 8.72 45 30.5 155 34.6 153 15.1 125 19.4 127 27.4 127 5.68 34 23.6 57 36.2 58 7.95 81 24.2 159 30.4 161 11.5 176
AggregFlow [95]107.8 12.9 167 20.3 167 1.75 49 8.34 97 10.8 107 4.14 70 20.0 132 24.4 151 19.5 149 16.5 133 22.3 138 12.2 137 25.2 43 28.6 43 12.2 63 16.9 45 23.9 45 6.60 106 29.0 160 43.9 154 16.7 167 23.0 108 28.9 109 8.03 46
FlowFields+ [128]108.0 9.67 103 15.2 109 3.33 157 7.86 53 10.3 68 3.02 22 23.3 153 24.6 153 20.8 157 17.0 143 23.0 150 6.91 17 27.3 63 31.0 63 15.4 164 19.0 113 26.9 114 6.24 75 25.3 96 38.8 99 13.1 153 23.2 118 29.1 116 8.39 132
RNLOD-Flow [119]109.1 8.93 54 13.8 48 1.65 17 8.48 103 11.0 119 4.06 65 16.3 75 23.2 141 12.8 86 14.1 60 19.1 76 11.1 97 29.7 126 33.7 126 15.6 174 20.3 152 28.7 151 8.92 174 25.7 103 39.4 109 16.4 166 24.2 159 30.4 161 8.20 76
StereoOF-V1MT [117]109.1 11.1 144 17.3 145 1.73 37 8.61 110 10.6 92 5.28 126 23.4 155 17.3 65 17.1 131 16.6 136 19.9 98 12.3 141 27.4 66 31.1 66 15.0 120 17.0 50 23.8 43 6.80 116 30.2 170 46.2 169 12.3 151 21.6 62 26.9 59 9.58 167
FlowNet2 [120]109.8 15.6 180 23.6 180 1.96 101 9.34 153 12.1 177 4.72 97 17.3 97 19.2 96 13.0 90 17.1 146 23.1 152 10.1 75 28.0 82 31.8 83 12.3 74 18.6 94 26.3 97 6.35 88 26.7 124 40.8 127 8.04 87 21.7 65 27.2 66 8.30 105
TI-DOFE [24]109.9 9.80 113 15.2 109 2.80 150 9.94 175 11.4 147 5.62 150 15.5 61 15.7 44 10.5 56 17.0 143 21.7 134 10.6 85 27.1 58 30.8 60 12.1 44 20.9 164 29.6 165 6.99 125 24.0 66 36.3 59 8.92 107 24.3 162 28.1 82 12.5 179
ACK-Prior [27]110.2 9.81 114 15.1 106 2.07 118 8.01 69 10.4 79 3.86 52 25.1 162 19.1 92 22.0 163 15.1 94 20.1 100 10.1 75 30.4 148 34.4 147 15.4 164 19.1 116 26.9 114 7.57 146 25.8 107 39.3 107 19.5 175 22.3 80 27.9 78 7.73 39
Sparse-NonSparse [56]110.3 9.18 78 14.3 80 1.73 37 8.14 82 10.6 92 3.31 32 16.6 82 22.9 137 13.8 101 14.8 85 19.8 96 11.3 101 30.5 155 34.6 153 15.0 120 20.1 146 28.5 149 7.48 142 28.5 150 43.7 152 9.49 119 23.5 137 29.5 137 8.24 85
Occlusion-TV-L1 [63]110.4 10.1 122 15.9 127 2.43 140 9.36 154 11.8 173 5.01 115 12.7 13 14.7 33 7.22 14 17.0 143 22.7 145 11.4 107 28.6 94 32.5 94 12.0 41 18.7 100 26.5 104 7.48 142 25.2 91 37.7 82 10.0 130 24.3 162 30.3 160 9.33 163
LSM [39]111.0 9.10 74 14.2 77 1.73 37 8.33 96 10.9 114 3.40 34 16.6 82 22.7 134 12.2 75 15.0 93 20.3 104 11.0 95 30.5 155 34.7 160 15.1 125 20.7 161 29.4 162 6.17 67 28.1 142 43.0 143 11.5 145 23.8 145 29.9 147 8.27 97
ResPWCR_ROB [140]111.3 11.2 149 17.7 149 1.95 99 8.98 129 11.7 167 4.11 68 15.2 57 17.3 65 10.0 46 23.1 174 31.2 176 10.5 83 30.5 155 34.6 153 14.2 105 20.3 152 28.8 153 5.27 27 23.8 59 36.4 61 7.54 48 25.4 176 31.9 180 7.76 40
Classic+CPF [82]111.4 9.07 69 14.0 62 1.80 69 8.09 78 10.5 87 3.71 46 17.0 90 21.5 121 12.9 88 13.9 57 18.8 69 11.4 107 30.7 164 34.9 165 15.4 164 21.2 169 30.0 170 7.73 154 28.2 143 43.2 146 7.80 71 24.7 170 31.0 170 7.89 44
TriFlow [93]112.2 13.1 169 20.8 169 2.06 114 9.53 165 12.2 179 5.29 133 16.5 79 18.5 82 10.1 47 17.2 147 22.8 147 7.74 24 27.9 79 31.6 79 15.1 125 19.4 127 27.4 127 6.07 59 24.5 75 37.2 73 10.9 141 23.8 145 29.8 146 8.15 63
3DFlow [133]112.2 9.65 100 14.9 98 1.89 86 7.82 49 10.0 49 4.94 110 16.9 87 19.9 106 13.7 99 16.5 133 22.4 139 15.8 173 29.3 122 33.2 119 12.5 81 18.4 85 25.9 86 8.56 169 27.2 128 41.4 130 10.1 131 23.4 127 29.3 128 8.87 159
TVL1_RVC [176]112.5 10.6 135 16.6 137 1.87 84 9.87 173 11.6 160 5.57 146 21.5 142 19.8 105 15.9 120 15.2 96 19.6 88 11.6 118 27.1 58 30.7 58 12.1 44 19.2 122 27.2 124 7.16 132 28.2 143 42.8 141 13.2 155 20.9 45 26.2 45 8.37 129
CostFilter [40]112.8 10.8 140 17.0 142 1.80 69 7.90 57 10.3 68 2.66 3 24.6 161 27.7 167 21.9 161 18.7 158 25.4 163 13.7 155 27.5 69 31.1 66 12.6 83 18.2 81 25.8 84 5.87 39 28.9 158 44.2 159 9.34 117 24.4 165 30.7 167 8.20 76
TF+OM [98]112.9 11.8 155 18.7 157 3.19 154 8.23 92 10.8 107 4.54 89 15.1 54 19.7 101 10.4 52 16.3 131 21.9 136 7.87 28 28.9 103 32.8 104 19.1 180 18.6 94 26.3 97 6.68 108 26.5 122 40.7 125 11.5 145 23.8 145 29.9 147 8.23 83
FFV1MT [104]113.5 11.6 151 17.7 149 2.19 127 9.20 146 10.9 114 5.96 161 22.6 146 30.3 175 16.3 122 15.5 108 18.8 69 12.4 144 27.5 69 31.2 70 11.6 33 18.6 94 25.7 78 7.42 141 27.2 128 40.7 125 8.88 105 21.2 52 26.4 49 9.73 168
Ramp [62]114.4 9.22 81 14.3 80 1.73 37 8.19 88 10.7 102 4.24 77 21.9 144 28.8 172 21.1 160 14.2 62 19.2 77 11.6 118 30.6 162 34.8 163 14.8 116 20.4 156 29.0 159 7.40 139 28.0 141 42.9 142 7.57 51 23.0 108 28.9 109 8.28 101
AugFNG_ROB [139]114.5 12.1 159 19.0 159 1.94 97 8.44 102 10.6 92 5.42 139 17.3 97 23.9 147 10.8 60 26.2 180 34.7 179 11.5 113 31.6 176 35.9 176 15.3 138 18.7 100 26.4 101 6.38 91 24.9 86 38.2 89 7.91 80 19.8 30 24.8 30 8.36 126
IAOF2 [51]115.5 10.7 139 16.6 137 2.36 137 9.40 155 11.6 160 5.33 134 17.4 102 18.0 76 12.4 80 14.1 60 18.2 57 9.32 62 30.3 147 34.4 147 14.0 103 20.5 160 29.1 160 8.20 163 25.2 91 38.3 91 8.49 100 23.1 111 29.1 116 8.24 85
SVFilterOh [109]115.8 10.5 134 16.4 135 1.97 103 7.65 40 9.98 48 3.05 24 28.0 167 30.4 176 25.4 174 15.6 112 21.2 123 14.7 165 28.9 103 32.7 98 15.4 164 20.1 146 28.4 147 6.61 107 25.8 107 39.5 111 7.84 76 22.5 84 28.3 86 8.49 149
EPMNet [131]116.4 16.1 182 24.7 182 2.22 129 9.04 132 11.7 167 4.55 90 17.3 97 19.2 96 13.0 90 26.7 182 36.3 183 12.1 133 28.0 82 31.8 83 12.3 74 18.4 85 26.0 88 6.25 78 26.7 124 40.8 127 8.04 87 22.6 89 28.4 90 8.35 123
TV-L1-improved [17]116.8 9.53 95 14.9 98 1.99 105 9.46 159 11.7 167 5.17 121 22.6 146 14.8 34 20.1 153 13.4 43 17.8 49 8.05 32 30.2 142 34.3 143 11.9 36 19.6 133 27.7 133 8.09 161 29.9 166 45.8 166 9.73 126 23.4 127 29.3 128 8.42 141
Adaptive [20]116.8 11.0 142 17.3 145 1.89 86 9.41 157 11.6 160 5.19 123 14.8 49 17.1 62 11.1 65 15.7 118 21.1 120 12.1 133 31.1 173 35.3 173 12.0 41 18.8 104 26.6 105 8.00 159 27.8 137 42.3 135 8.01 84 22.6 89 28.4 90 8.63 154
Classic+NL [31]117.2 8.97 60 13.9 55 1.79 65 8.11 79 10.5 87 4.01 61 20.8 137 28.3 169 19.9 150 14.3 66 19.3 79 11.5 113 30.7 164 34.8 163 14.6 112 20.3 152 28.8 153 7.40 139 28.3 146 43.4 148 11.9 149 23.5 137 29.6 140 8.25 90
Heeger++ [102]117.2 14.5 176 21.7 174 4.63 172 9.50 162 11.0 119 5.73 156 25.4 164 23.5 146 14.4 105 15.5 108 18.8 69 12.4 144 28.7 96 32.5 94 15.2 134 15.8 28 22.2 27 6.73 111 27.6 134 39.8 117 9.28 116 22.1 73 27.6 72 8.34 117
Dynamic MRF [7]117.3 10.1 122 15.9 127 1.81 73 8.42 101 10.8 107 4.73 101 19.5 125 19.1 92 12.2 75 15.6 112 19.3 79 12.8 150 27.2 61 30.8 60 15.2 134 18.6 94 26.3 97 7.28 135 28.8 157 44.1 158 12.4 152 24.6 168 30.7 167 9.73 168
TriangleFlow [30]117.8 9.59 98 14.8 95 2.06 114 9.07 137 11.4 147 5.47 143 19.2 121 20.2 111 13.9 102 13.6 47 18.2 57 8.31 36 30.0 138 34.1 140 9.31 28 17.8 65 25.2 68 7.56 145 30.8 172 47.2 172 13.9 158 25.5 179 31.9 180 11.3 175
IAOF [50]118.0 11.1 144 16.6 137 5.32 177 10.6 181 12.3 181 5.87 158 23.3 153 24.2 148 19.4 146 15.4 104 19.7 94 12.0 130 28.9 103 32.8 104 12.1 44 18.8 104 26.6 105 7.26 134 25.6 102 39.1 104 7.35 35 22.1 73 27.8 76 8.26 94
Steered-L1 [116]118.2 8.76 43 13.7 45 1.82 76 8.00 68 10.3 68 4.72 97 31.9 176 33.2 182 29.2 181 17.4 149 22.8 147 14.1 159 29.5 125 33.5 125 14.2 105 19.7 137 27.9 139 6.28 85 26.4 117 40.4 119 18.7 173 23.8 145 29.9 147 7.04 30
ROF-ND [105]118.4 9.00 63 13.9 55 1.62 11 9.53 165 10.8 107 10.7 183 16.4 78 22.9 137 12.7 85 18.3 156 24.1 160 11.9 126 29.4 124 33.3 124 15.2 134 18.6 94 26.2 93 7.60 150 24.5 75 37.3 75 13.2 155 24.4 165 30.5 164 9.33 163
FOLKI [16]118.8 10.6 135 16.5 136 2.43 140 9.94 175 11.2 134 6.70 168 19.6 128 21.6 122 19.9 150 18.3 156 19.4 83 17.3 178 28.0 82 31.7 81 13.6 93 19.1 116 27.1 122 10.9 182 24.2 67 36.9 69 17.3 170 21.3 55 26.7 54 8.10 54
FF++_ROB [141]118.9 10.6 135 16.7 141 1.70 29 8.19 88 10.6 92 3.67 42 21.6 143 22.6 132 17.0 126 19.0 161 25.5 164 14.9 169 28.9 103 32.8 104 15.4 164 19.3 125 27.4 127 6.24 75 25.7 103 39.5 111 11.8 148 23.5 137 29.5 137 8.27 97
LocallyOriented [52]119.5 10.1 122 15.7 123 1.79 65 9.46 159 11.6 160 5.28 126 23.1 151 24.2 148 20.9 159 19.3 165 23.2 153 7.35 20 30.4 148 34.6 153 12.6 83 18.9 108 26.8 112 6.27 81 25.7 103 38.6 96 7.89 78 23.6 140 29.6 140 8.19 74
SILK [80]121.0 9.72 109 15.1 106 2.69 147 10.2 179 11.4 147 7.82 172 39.2 184 32.9 181 28.5 180 14.6 81 18.4 60 9.73 70 29.0 113 32.9 113 10.4 31 21.2 169 30.0 170 7.00 126 24.5 75 37.5 78 8.03 86 23.1 111 28.9 109 8.31 108
S2D-Matching [83]123.2 9.57 97 14.9 98 1.76 52 8.37 99 10.8 107 4.36 81 20.1 134 24.9 156 18.2 138 15.7 118 21.3 128 15.7 172 28.8 98 32.7 98 14.5 109 21.5 174 30.4 174 11.0 183 25.7 103 39.3 107 11.5 145 23.1 111 29.1 116 8.75 158
GraphCuts [14]123.3 11.7 153 17.8 151 2.02 108 8.15 83 10.5 87 4.65 93 25.3 163 15.2 38 19.4 146 14.9 88 19.6 88 11.9 126 29.8 132 33.8 131 17.8 178 19.6 133 27.8 136 6.50 101 28.6 153 43.9 154 11.1 142 24.0 156 30.2 157 8.15 63
BriefMatch [122]123.7 9.89 119 15.5 120 2.11 122 8.05 73 10.2 59 5.90 159 23.5 156 18.0 76 22.7 167 18.2 155 18.6 63 18.7 181 28.1 87 31.9 88 13.8 99 19.5 131 27.7 133 7.05 129 26.7 124 39.4 109 21.6 181 23.4 127 29.3 128 14.3 183
ContinualFlow_ROB [148]123.8 12.2 160 19.3 160 2.23 131 8.71 115 11.3 142 4.73 101 17.5 103 19.9 106 13.3 92 22.6 173 30.7 175 8.65 42 32.4 179 36.8 180 15.3 138 18.5 91 26.2 93 6.12 65 28.6 153 43.9 154 8.50 101 22.7 95 28.4 90 8.39 132
ComponentFusion [94]124.2 12.3 161 19.5 161 1.66 18 8.65 112 11.4 147 2.88 17 19.7 129 21.0 120 15.1 116 15.4 104 20.9 116 14.4 160 29.7 126 33.7 126 14.5 109 18.6 94 26.3 97 7.67 152 31.9 174 49.0 176 20.5 177 24.2 159 30.4 161 8.18 70
RFlow [88]124.5 9.71 107 15.2 109 1.91 93 9.06 135 11.2 134 5.42 139 22.8 150 22.6 132 17.9 135 15.8 122 21.2 123 12.7 149 29.2 117 33.2 119 11.9 36 19.2 122 27.2 124 7.63 151 28.9 158 44.4 160 7.73 64 23.4 127 29.5 137 8.46 145
Learning Flow [11]125.1 8.99 62 14.1 70 1.85 82 9.10 141 11.3 142 4.99 112 40.2 185 42.5 185 31.6 185 14.9 88 17.2 41 12.2 137 30.8 166 35.0 167 15.1 125 18.7 100 26.4 101 7.58 148 25.1 90 38.3 91 11.4 144 25.5 179 31.7 176 8.24 85
Adaptive flow [45]125.7 10.3 128 14.8 95 2.37 138 9.87 173 11.5 157 5.57 146 18.0 111 17.9 75 17.1 131 16.4 132 20.0 99 14.8 167 32.3 178 36.7 178 16.6 176 21.1 166 29.8 166 8.41 167 23.8 59 36.4 61 13.1 153 21.7 65 27.1 63 7.17 33
FC-2Layers-FF [74]126.0 9.71 107 14.9 98 2.11 122 7.51 31 9.66 40 4.67 94 20.5 135 25.1 158 20.2 154 15.6 112 21.1 120 11.9 126 30.5 155 34.6 153 15.3 138 20.8 163 29.4 162 7.31 136 29.7 163 45.6 165 9.76 127 23.6 140 29.7 144 8.22 82
Shiralkar [42]126.5 12.0 158 18.8 158 1.72 35 9.11 142 11.1 129 5.14 120 21.2 140 16.6 56 13.7 99 19.2 164 24.3 162 10.6 85 29.7 126 33.7 126 12.8 87 18.0 74 25.4 73 7.19 133 29.4 161 44.9 161 10.4 136 25.1 175 31.5 175 9.03 162
SLK [47]126.7 9.63 99 15.0 103 1.90 90 9.14 144 10.3 68 5.63 152 34.7 178 19.7 101 22.4 165 18.9 160 24.2 161 20.4 183 29.8 132 33.8 131 12.2 63 18.1 76 25.5 77 6.93 120 31.9 174 48.8 174 9.12 111 22.8 99 28.5 98 14.2 182
EPPM w/o HM [86]127.4 10.4 131 16.2 132 2.97 152 8.62 111 11.3 142 2.76 11 29.0 171 27.4 165 22.2 164 16.8 139 22.6 142 10.8 89 25.8 47 29.2 46 12.1 44 20.2 150 28.6 150 6.49 100 29.8 165 45.8 166 18.0 171 24.0 156 30.2 157 8.72 157
UnFlow [127]129.2 13.4 170 21.2 172 2.71 149 8.81 119 10.7 102 6.35 165 18.7 117 18.9 88 14.8 110 14.6 81 19.6 88 7.77 25 31.8 177 36.1 177 15.0 120 22.2 180 31.4 180 7.79 155 24.2 67 37.0 70 7.49 43 28.1 184 33.7 185 11.6 178
Correlation Flow [76]129.5 9.75 111 15.3 116 1.84 80 9.28 151 11.6 160 5.17 121 17.5 103 18.9 88 15.2 117 16.1 128 21.7 134 11.3 101 30.2 142 34.3 143 12.5 81 21.2 169 29.9 167 8.24 164 31.3 173 47.8 173 9.82 128 24.9 173 31.3 174 6.61 10
LiteFlowNet [138]133.2 12.6 163 19.7 164 2.06 114 8.19 88 10.7 102 3.96 57 20.8 137 26.3 162 15.4 118 26.2 180 35.0 181 12.2 137 30.9 172 35.0 167 14.9 119 20.4 156 28.8 153 6.74 114 28.3 146 43.1 144 7.70 63 22.8 99 28.6 101 8.87 159
HBpMotionGpu [43]133.5 12.7 164 19.5 161 2.69 147 9.65 169 11.7 167 5.48 144 20.0 132 23.3 144 17.0 126 17.6 153 23.4 154 10.6 85 30.8 166 35.0 167 25.1 185 20.4 156 28.9 158 7.95 157 22.0 30 33.7 31 7.44 38 23.2 118 29.1 116 8.40 137
2bit-BM-tele [96]135.3 11.1 144 17.2 144 2.34 135 9.40 155 11.7 167 5.36 136 28.5 169 37.1 183 31.0 183 15.7 118 20.8 114 9.18 58 28.6 94 32.5 94 15.0 120 22.0 179 31.1 179 9.53 178 39.1 185 59.9 185 26.9 185 20.8 42 26.1 42 8.11 58
PGAM+LK [55]135.3 11.9 157 18.0 152 7.26 184 9.48 161 10.8 107 7.62 170 31.5 174 39.9 184 31.4 184 19.0 161 23.6 156 16.3 177 29.1 115 33.0 114 12.6 83 18.4 85 26.0 88 6.80 116 25.5 99 39.0 101 14.8 161 22.6 89 28.4 90 8.41 140
Rannacher [23]136.1 11.1 144 17.5 148 1.89 86 9.59 167 11.8 173 5.28 126 24.3 160 18.0 76 20.8 157 15.9 124 21.2 123 11.6 118 30.4 148 34.5 149 12.3 74 19.7 137 27.9 139 7.98 158 29.6 162 45.3 162 9.57 122 24.7 170 31.0 170 8.19 74
OFRF [132]136.6 13.6 171 21.1 171 2.23 131 9.25 149 11.4 147 5.60 148 19.2 121 19.5 100 14.1 104 16.9 141 22.8 147 14.6 161 30.8 166 34.9 165 14.4 108 19.6 133 27.7 133 6.07 59 28.3 146 43.4 148 7.78 70 24.7 170 31.1 172 8.34 117
StereoFlow [44]137.2 14.9 177 22.2 176 3.28 155 10.0 177 12.7 183 4.99 112 16.8 85 18.9 88 12.1 74 15.2 96 20.4 107 10.4 82 33.4 182 37.9 182 20.8 182 23.8 182 33.5 182 8.41 167 25.3 96 38.8 99 7.81 73 23.6 140 29.6 140 8.67 156
IRR-PWC_RVC [181]137.5 15.4 179 24.1 181 2.44 144 9.31 152 12.2 179 4.74 103 19.0 120 22.9 137 13.4 95 29.5 184 39.3 185 8.93 53 30.4 148 34.5 149 15.3 138 21.1 166 29.9 167 6.75 115 28.3 146 43.2 146 7.73 64 22.8 99 28.5 98 8.50 151
SimpleFlow [49]139.8 9.15 76 14.3 80 1.73 37 9.05 134 11.4 147 5.35 135 36.0 182 32.6 180 29.4 182 14.9 88 20.2 101 11.2 100 30.6 162 34.7 160 15.1 125 22.6 181 32.0 181 9.11 175 34.7 179 53.2 180 13.8 157 23.9 152 29.9 147 8.33 114
SPSA-learn [13]141.5 15.1 178 22.9 178 1.93 94 9.08 139 11.0 119 5.42 139 33.0 177 24.8 154 23.8 170 17.6 153 22.4 139 12.1 133 29.3 122 33.2 119 15.1 125 17.8 65 25.1 66 6.73 111 37.7 181 57.7 182 25.5 184 25.4 176 31.8 177 8.33 114
SegOF [10]141.8 11.8 155 18.2 154 5.53 179 8.88 124 11.4 147 4.62 92 31.1 173 20.5 114 23.7 169 25.8 178 34.8 180 18.2 180 30.2 142 34.2 142 15.3 138 19.1 116 27.0 117 7.08 130 32.5 177 49.7 177 16.8 168 22.8 99 28.6 101 8.08 50
HCIC-L [97]147.6 14.3 175 20.9 170 2.86 151 11.2 182 13.3 184 7.62 170 23.9 157 31.6 178 25.6 175 21.0 169 28.2 170 14.8 167 25.6 44 29.0 44 12.2 63 24.0 183 33.9 183 10.5 181 30.5 171 46.8 171 18.5 172 23.3 125 29.2 123 7.37 34
IIOF-NLDP [129]149.0 10.2 127 15.8 125 2.10 121 9.06 135 11.2 134 5.60 148 20.6 136 24.8 154 16.9 125 16.7 138 22.6 142 14.6 161 30.4 148 34.5 149 20.8 182 20.4 156 28.8 153 8.81 173 37.7 181 57.6 181 16.8 168 24.9 173 31.2 173 8.26 94
WOLF_ROB [144]149.1 16.7 183 24.7 182 3.17 153 9.76 171 11.8 173 5.28 126 22.6 146 24.5 152 19.4 146 21.5 171 28.4 171 8.71 44 30.8 166 35.0 167 15.2 134 20.1 146 28.3 145 7.04 127 32.0 176 48.8 174 8.28 96 25.4 176 31.8 177 8.20 76
WRT [146]156.6 10.3 128 15.8 125 2.35 136 9.41 157 10.6 92 9.35 175 35.2 180 27.6 166 26.8 177 21.2 170 21.4 129 13.6 154 31.3 175 35.6 175 13.7 97 21.5 174 30.4 174 8.56 169 39.0 184 59.6 184 16.0 164 26.1 182 32.6 183 8.31 108
GroupFlow [9]157.7 15.6 180 23.3 179 3.31 156 9.20 146 11.4 147 6.26 163 30.9 172 22.4 128 18.9 143 25.4 177 30.0 174 21.2 184 32.4 179 36.7 178 15.3 138 20.9 164 29.4 162 7.71 153 29.9 166 45.5 163 9.50 120 23.3 125 29.1 116 10.6 172
Pyramid LK [2]165.1 14.0 173 21.7 174 4.34 168 13.7 183 11.5 157 9.94 180 37.6 183 26.8 164 24.6 173 25.9 179 29.3 172 18.7 181 35.0 183 39.7 183 13.3 92 19.9 143 24.8 58 9.57 179 33.3 178 51.1 178 10.7 138 26.0 181 32.4 182 13.0 180
Periodicity [79]181.7 18.1 184 27.0 184 6.22 181 17.4 184 12.4 182 10.2 181 35.2 180 30.7 177 27.8 178 24.1 175 31.6 177 17.5 179 37.6 185 42.6 185 18.8 179 27.7 184 39.3 184 11.2 184 38.6 183 58.9 183 22.9 182 27.3 183 33.2 184 14.3 183
AVG_FLOW_ROB [137]182.6 31.2 185 31.0 185 11.6 185 19.8 185 21.4 185 12.0 185 34.9 179 32.0 179 28.1 179 31.2 185 36.2 182 23.9 185 36.4 184 41.0 184 16.9 177 39.5 185 55.0 185 16.9 185 36.8 180 52.3 179 20.8 178 30.2 185 31.8 177 15.5 185
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.