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        
Average
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]2.9 2.06 1 3.06 1 1.14 6 2.80 1 3.91 2 1.24 1 1.99 1 2.73 1 1.21 3 3.84 1 4.64 1 2.69 1 8.10 12 10.0 12 2.96 1 4.10 3 7.53 3 1.98 2 5.49 3 12.1 3 1.39 3 5.40 2 8.33 2 1.50 3
FGME [158]9.7 2.08 2 3.34 3 0.98 1 3.32 16 4.43 8 1.63 101 2.46 3 3.28 4 1.41 13 4.08 2 4.85 2 3.05 13 7.36 1 9.08 1 3.03 5 4.17 5 7.62 5 2.06 15 4.95 2 10.7 2 1.44 11 5.45 3 8.41 3 1.57 12
EAFI [171]10.5 2.22 4 3.69 8 1.15 7 3.16 7 4.44 9 1.50 76 2.12 2 2.96 2 1.15 1 4.28 6 5.30 5 2.92 4 8.71 17 10.8 15 3.03 5 4.97 17 9.45 17 1.99 3 5.94 11 13.3 12 1.38 2 5.84 6 9.03 6 1.55 10
BMBC [172]10.5 2.30 10 3.40 5 1.20 18 3.07 4 4.25 5 1.41 50 3.17 15 4.19 24 1.66 34 4.24 4 5.28 4 2.85 3 7.79 4 9.62 4 3.14 17 4.08 2 7.47 2 2.02 6 5.63 5 12.4 5 1.40 5 5.55 4 8.58 4 1.61 18
STAR-Net [164]12.5 2.18 3 3.37 4 1.21 34 3.46 25 4.88 24 1.47 68 3.04 13 3.53 9 1.58 27 4.41 8 5.44 8 2.76 2 7.51 2 9.27 2 2.98 3 4.65 8 8.72 8 1.99 3 6.21 13 13.4 13 1.41 6 6.17 8 9.45 8 1.49 2
EDSC [174]13.5 2.32 14 3.90 13 1.16 8 3.10 5 4.38 7 1.51 77 2.98 11 3.54 10 1.36 11 4.49 9 5.74 10 3.16 25 8.05 11 9.96 11 3.08 10 4.89 16 9.28 16 2.02 6 5.55 4 12.3 4 1.41 6 6.42 15 9.99 16 1.55 10
AdaCoF [165]17.8 2.41 18 4.10 18 1.26 122 3.10 5 4.32 6 1.43 56 3.48 22 3.31 5 1.78 50 4.84 16 5.94 17 2.93 5 8.68 16 10.8 15 3.14 17 4.13 4 7.59 4 1.97 1 5.77 9 12.9 10 1.37 1 5.60 5 8.67 5 1.48 1
DSepConv [162]21.1 2.47 19 4.39 24 1.21 34 3.32 16 4.60 16 1.72 119 3.28 16 3.66 11 1.50 20 5.11 23 6.36 21 3.23 55 7.85 5 9.69 5 3.11 14 4.68 10 8.78 10 2.04 13 5.65 6 12.5 6 1.44 11 6.54 19 10.2 19 1.58 15
STSR [170]23.5 2.31 12 3.82 11 1.19 12 2.94 2 3.90 1 1.93 153 2.92 9 3.44 8 1.81 51 4.29 7 5.41 6 3.27 68 9.51 21 11.9 21 3.06 9 5.38 26 10.3 26 2.10 17 6.75 21 15.3 23 1.50 19 6.43 17 9.99 16 1.54 7
GDCN [173]23.5 2.31 12 3.98 16 1.10 4 3.80 75 5.17 40 1.54 82 2.92 9 3.78 16 1.43 15 5.59 75 6.01 19 3.24 59 9.02 18 11.3 18 3.10 12 4.66 9 8.75 9 2.08 16 5.75 8 12.7 7 1.42 9 6.40 14 9.98 15 1.53 6
MAF-net [163]25.3 2.23 5 3.84 12 1.08 3 3.53 35 4.85 23 1.78 130 2.83 7 3.70 12 1.58 27 4.83 15 5.88 12 3.31 88 9.44 20 11.8 20 3.27 22 5.27 21 10.0 21 2.15 19 6.30 14 14.2 15 1.54 39 6.38 13 9.90 14 1.63 20
CtxSyn [134]25.7 2.24 6 3.72 9 1.04 2 2.96 3 4.16 4 1.35 34 4.32 91 3.42 7 3.18 133 4.21 3 5.46 9 3.00 7 9.59 24 11.9 21 3.46 27 5.22 18 9.76 18 2.22 22 7.02 26 15.4 24 1.58 58 6.66 22 10.2 19 1.69 29
ADC [161]26.4 2.54 24 4.31 19 1.29 140 3.27 10 4.46 10 1.62 99 3.76 46 3.76 14 1.70 41 5.27 30 6.37 22 3.19 36 8.66 15 10.8 15 3.11 14 4.78 14 9.04 15 2.01 5 5.72 7 12.8 9 1.41 6 6.56 20 10.2 19 1.51 4
FRUCnet [153]26.7 2.61 26 4.34 21 1.52 170 3.30 13 4.52 12 1.72 119 3.14 14 3.70 12 1.76 47 4.74 13 5.99 18 3.29 73 8.11 13 10.0 12 2.97 2 4.48 6 8.35 7 2.02 6 5.78 10 12.7 7 1.45 13 6.06 7 9.38 7 1.57 12
MPRN [151]27.4 2.53 22 4.43 25 1.21 34 3.78 72 4.97 27 1.57 88 3.39 20 5.49 30 1.28 4 5.03 19 6.58 25 3.19 36 9.53 22 11.9 21 3.31 24 5.25 20 9.92 19 2.22 22 6.87 23 15.5 25 1.49 16 6.72 23 10.4 23 1.60 17
FeFlow [167]27.7 2.28 8 3.73 10 1.18 11 3.50 33 4.78 22 2.09 164 2.82 6 3.13 3 1.66 34 4.75 14 5.78 11 3.72 146 7.62 3 9.40 3 3.04 7 4.74 13 8.88 12 2.03 10 6.07 12 13.1 11 1.59 61 6.78 25 10.5 25 1.65 21
CyclicGen [149]28.0 2.26 7 3.32 2 1.42 165 3.19 8 4.01 3 2.21 168 2.76 5 4.05 22 1.62 31 4.97 18 5.92 15 3.79 153 8.00 10 9.84 10 3.13 16 3.36 1 5.65 1 2.17 20 4.55 1 9.68 1 1.42 9 4.48 1 6.84 1 1.52 5
TC-GAN [166]28.5 2.34 15 3.96 15 1.25 108 3.26 9 4.51 11 1.81 134 3.49 23 3.80 18 2.20 80 4.65 11 5.90 14 3.44 115 7.87 6 9.73 6 3.00 4 4.78 14 9.00 14 2.03 10 6.34 15 14.2 15 1.50 19 6.28 10 9.73 11 1.54 7
DAIN [152]28.9 2.38 16 4.05 17 1.26 122 3.28 11 4.53 14 1.79 132 3.32 18 3.77 15 2.05 70 4.65 11 5.88 12 3.41 111 7.88 7 9.74 7 3.04 7 4.73 12 8.90 13 2.04 13 6.36 16 14.3 18 1.51 25 6.25 9 9.68 10 1.54 7
MS-PFT [159]29.0 2.53 22 4.35 22 1.16 8 3.61 48 5.03 29 1.69 114 3.30 17 4.25 25 1.77 49 5.13 24 6.55 24 3.19 36 7.94 9 9.81 9 3.21 20 4.49 7 8.24 6 2.22 22 6.55 18 13.9 14 1.79 117 6.42 15 9.89 13 1.69 29
DAI [168]32.0 2.30 10 3.42 6 1.47 169 3.46 25 4.66 18 1.92 147 2.55 4 3.78 16 1.33 6 4.27 5 5.10 3 4.24 166 9.07 19 11.3 18 3.08 10 5.28 22 10.1 23 2.02 6 6.56 19 14.7 20 1.39 3 6.48 18 10.0 18 1.59 16
MEMC-Net+ [160]35.7 2.39 17 3.92 14 1.28 132 3.36 19 4.52 12 2.07 163 3.37 19 3.86 19 2.20 80 4.84 16 5.93 16 3.72 146 8.55 14 10.6 14 3.14 17 4.70 11 8.81 11 2.03 10 6.40 17 14.2 15 1.58 58 6.37 12 9.87 12 1.57 12
MDP-Flow2 [68]36.2 2.89 30 5.38 31 1.19 12 3.47 27 5.07 35 1.26 3 3.66 35 6.10 64 2.48 100 5.20 26 7.48 36 3.14 22 10.2 28 12.8 29 3.61 49 6.13 50 11.8 46 2.31 51 7.36 31 16.8 29 1.49 16 7.75 46 12.1 45 1.69 29
PMMST [112]36.9 2.90 32 5.43 33 1.20 18 3.50 33 5.05 33 1.27 8 3.56 26 5.46 28 1.82 54 5.38 43 7.92 63 3.41 111 10.2 28 12.8 29 3.60 43 5.76 28 11.0 28 2.26 29 7.39 32 16.9 32 1.53 32 7.57 31 11.8 31 1.72 60
SuperSlomo [130]37.4 2.51 20 4.32 20 1.25 108 3.66 56 5.06 34 1.93 153 2.91 8 4.00 21 1.41 13 5.05 20 6.27 20 3.66 141 9.56 23 11.9 21 3.30 23 5.37 25 10.2 25 2.24 25 6.69 20 15.0 21 1.53 32 6.73 24 10.4 23 1.66 22
TOF-M [150]37.5 2.54 24 4.35 22 1.16 8 3.70 62 5.19 41 1.88 140 3.43 21 3.89 20 1.93 60 5.05 20 6.43 23 3.39 105 9.84 25 12.3 25 3.42 26 5.34 24 10.0 21 2.28 37 6.88 24 15.2 22 1.61 68 7.14 27 11.0 27 1.69 29
OFRI [154]40.6 2.28 8 3.45 7 1.35 158 3.44 22 4.57 15 2.13 166 3.02 12 3.34 6 1.73 44 4.51 10 5.42 7 3.88 154 7.89 8 9.76 8 3.10 12 5.24 19 9.92 19 2.10 17 6.78 22 14.3 18 1.82 121 6.32 11 9.62 9 1.75 101
CoT-AMFlow [175]40.8 2.89 30 5.43 33 1.19 12 3.48 28 5.11 38 1.25 2 3.86 54 6.56 85 2.48 100 5.19 25 7.47 35 3.10 17 10.3 33 12.8 29 3.61 49 6.15 54 11.9 54 2.31 51 7.41 36 17.0 36 1.48 14 7.76 50 12.1 45 1.73 69
SepConv-v1 [125]45.6 2.52 21 4.83 26 1.11 5 3.56 44 5.04 31 1.90 143 4.17 77 4.15 23 2.86 119 5.41 52 6.81 26 3.88 154 10.2 28 12.8 29 3.37 25 5.47 27 10.4 27 2.21 21 6.88 24 15.6 26 1.72 104 6.63 21 10.3 22 1.62 19
DeepFlow [85]46.4 2.98 43 5.67 48 1.22 64 3.88 86 5.78 85 1.52 78 3.62 28 5.93 56 1.34 7 5.39 48 7.20 30 3.17 27 11.0 61 13.9 68 3.63 61 5.91 34 11.3 33 2.29 42 7.14 27 16.3 27 1.49 16 7.80 55 12.2 53 1.70 37
CBF [12]51.6 2.83 27 5.20 27 1.23 84 3.97 99 5.79 87 1.56 84 3.62 28 5.47 29 1.60 30 5.21 27 7.12 27 3.29 73 10.1 26 12.6 26 3.62 55 5.97 37 11.5 37 2.31 51 7.76 66 17.8 67 1.61 68 7.60 34 11.9 34 1.76 115
DeepFlow2 [106]51.8 2.99 46 5.65 45 1.22 64 3.88 86 5.79 87 1.48 70 3.62 28 6.03 58 1.34 7 5.38 43 7.44 34 3.22 48 11.0 61 13.8 61 3.67 69 5.83 29 11.2 29 2.25 28 7.60 48 17.4 49 1.50 19 7.82 56 12.2 53 1.77 125
NN-field [71]53.6 2.98 43 5.70 49 1.20 18 3.31 15 4.73 20 1.26 3 4.69 114 5.91 54 2.03 69 5.99 115 9.13 132 3.57 133 10.3 33 12.8 29 3.60 43 6.24 61 12.0 60 2.31 51 7.39 32 16.9 32 1.54 39 7.69 42 12.0 40 1.72 60
NNF-Local [75]54.3 2.92 35 5.51 40 1.19 12 3.30 13 4.71 19 1.26 3 3.65 33 5.91 54 2.29 90 5.76 93 8.70 114 3.55 131 10.3 33 12.9 36 3.60 43 6.42 81 12.4 80 2.34 65 7.57 44 17.4 49 1.74 106 7.61 35 11.9 34 1.72 60
Aniso. Huber-L1 [22]55.5 2.95 38 5.44 36 1.24 98 4.42 135 6.27 135 1.67 110 3.79 47 5.70 38 1.50 20 5.31 33 7.42 33 3.24 59 11.1 72 14.0 80 3.61 49 5.91 34 11.4 35 2.24 25 7.60 48 17.3 43 1.51 25 7.62 37 11.9 34 1.73 69
IROF-TV [53]56.0 3.07 61 5.91 71 1.23 84 3.71 64 5.47 62 1.40 46 3.70 41 6.27 70 1.58 27 5.25 29 7.60 43 3.17 27 11.0 61 13.9 68 4.47 131 6.37 77 12.4 80 2.30 48 7.79 70 17.9 71 1.50 19 7.63 38 11.9 34 1.66 22
LME [70]56.8 2.95 38 5.59 43 1.19 12 3.68 59 5.50 65 1.38 39 4.06 67 7.00 108 1.71 43 5.38 43 7.92 63 3.18 31 11.2 86 14.1 89 4.51 160 6.29 66 12.2 67 2.31 51 7.33 29 16.8 29 1.51 25 7.83 57 12.3 57 1.70 37
CLG-TV [48]57.1 2.94 36 5.45 37 1.25 108 4.26 122 6.17 122 1.60 93 3.68 39 5.73 40 1.73 44 5.36 39 7.41 32 3.32 92 11.1 72 14.0 80 3.57 32 5.88 33 11.3 33 2.26 29 7.58 45 17.0 36 1.57 55 7.75 46 12.1 45 1.72 60
IROF++ [58]57.8 3.03 52 5.77 57 1.20 18 3.59 47 5.31 50 1.33 28 4.32 91 6.61 87 2.25 85 5.06 22 7.14 28 3.16 25 11.0 61 13.9 68 4.44 127 6.34 72 12.3 74 2.27 34 7.54 43 17.3 43 1.64 83 8.09 81 12.7 82 1.69 29
CombBMOF [111]59.2 3.16 90 5.88 66 1.24 98 3.54 39 5.24 44 1.34 32 4.01 62 6.45 80 2.20 80 5.62 83 8.22 81 3.29 73 10.7 44 13.5 45 3.62 55 6.20 58 11.9 54 2.27 34 7.78 69 17.3 43 1.56 51 7.75 46 12.1 45 1.71 49
NNF-EAC [101]59.4 3.01 49 5.60 44 1.25 108 3.63 51 5.36 55 1.29 15 4.17 77 7.03 110 2.99 123 5.50 62 7.96 65 3.28 70 11.2 86 14.1 89 3.60 43 5.86 32 11.2 29 2.26 29 7.43 37 17.0 36 1.54 39 7.79 54 12.2 53 1.73 69
DF-Auto [113]60.6 2.94 36 5.34 29 1.23 84 3.99 102 5.84 92 1.65 104 3.85 52 6.73 90 1.55 26 5.38 43 7.54 38 3.25 62 10.4 37 13.0 37 3.70 73 6.17 57 11.9 54 2.28 37 7.94 80 18.2 82 1.75 111 7.68 40 12.0 40 1.71 49
ALD-Flow [66]61.3 3.28 120 6.45 121 1.24 98 3.81 77 5.73 83 1.41 50 3.62 28 6.28 71 1.35 10 5.58 72 8.39 95 3.04 11 10.8 47 13.5 45 4.15 107 5.96 36 11.4 35 2.29 42 7.34 30 16.8 29 1.51 25 8.25 105 12.9 98 1.70 37
WLIF-Flow [91]62.4 2.95 38 5.53 41 1.20 18 3.66 56 5.41 58 1.39 42 4.26 86 7.17 118 2.54 104 5.30 32 7.57 41 3.29 73 10.7 44 13.5 45 3.70 73 6.74 128 13.1 124 2.48 129 7.40 34 16.9 32 1.53 32 7.87 63 12.3 57 1.69 29
PH-Flow [99]62.6 3.12 76 6.01 86 1.20 18 3.39 20 4.94 26 1.28 13 3.70 41 6.43 76 2.48 100 5.23 28 7.58 42 3.22 48 10.4 37 13.1 39 3.62 55 6.84 139 13.3 137 2.47 123 7.84 73 18.1 78 1.58 58 7.87 63 12.3 57 1.73 69
Second-order prior [8]63.8 2.91 34 5.39 32 1.24 98 4.26 122 6.21 128 1.56 84 3.82 49 6.34 73 1.62 31 5.39 48 7.68 45 3.04 11 11.1 72 13.9 68 3.59 36 6.14 52 11.9 54 2.31 51 7.61 50 17.4 49 1.63 82 7.90 65 12.4 67 1.78 131
p-harmonic [29]64.8 3.00 47 5.72 51 1.21 34 4.33 127 6.24 133 1.69 114 3.60 27 6.07 62 1.39 12 5.70 85 7.87 58 3.29 73 11.0 61 13.8 61 3.63 61 6.02 40 11.6 40 2.34 65 7.67 55 17.5 54 1.70 99 7.92 69 12.4 67 1.72 60
Brox et al. [5]65.5 3.08 64 5.94 76 1.21 34 3.83 80 5.67 75 1.45 62 3.93 57 5.76 43 1.67 37 5.32 34 7.19 29 3.22 48 10.6 41 13.4 43 3.56 30 6.60 109 12.7 96 2.42 108 8.61 124 19.7 127 3.04 169 7.43 29 11.6 29 1.68 27
FMOF [92]66.3 3.16 90 5.92 74 1.23 84 3.48 28 5.07 35 1.28 13 4.59 109 6.82 94 2.78 115 5.71 87 8.42 96 3.40 108 10.4 37 13.0 37 3.67 69 6.49 88 12.6 89 2.28 37 7.64 52 17.5 54 1.48 14 8.06 79 12.6 77 1.67 25
SIOF [67]67.9 3.06 59 5.74 55 1.24 98 4.40 134 6.40 146 1.63 101 4.17 77 7.43 132 1.93 60 5.40 51 7.75 50 3.44 115 10.1 26 12.6 26 3.58 34 6.10 46 11.8 46 2.29 42 7.52 41 17.2 41 1.53 32 7.96 73 12.5 76 1.73 69
MDP-Flow [26]69.4 2.86 28 5.34 29 1.20 18 3.49 32 5.15 39 1.34 32 4.01 62 5.51 31 2.28 87 5.58 72 7.91 62 3.33 95 11.2 86 14.0 80 4.49 141 6.72 122 13.1 124 2.54 147 7.71 59 17.7 63 1.74 106 7.83 57 12.3 57 1.70 37
HCFN [157]69.9 3.16 90 6.30 105 1.20 18 3.69 61 5.58 69 1.32 25 3.97 60 6.09 63 1.73 44 5.54 65 8.33 88 3.22 48 10.9 54 13.7 55 3.61 49 6.29 66 11.9 54 2.62 161 8.11 94 18.5 93 1.61 68 8.18 89 12.8 90 1.73 69
Local-TV-L1 [65]70.1 3.00 47 5.47 38 1.30 144 4.43 137 6.23 132 1.75 126 3.50 24 5.35 27 1.45 16 5.39 48 7.56 39 3.29 73 11.2 86 14.1 89 3.91 96 6.16 55 11.8 46 2.47 123 7.67 55 17.6 58 1.55 46 7.57 31 11.8 31 1.76 115
OAR-Flow [123]70.7 3.13 81 5.95 78 1.22 64 3.83 80 5.70 78 1.48 70 3.65 33 6.06 59 1.16 2 5.60 78 8.48 101 3.03 8 11.2 86 14.1 89 4.51 160 6.12 49 11.8 46 2.41 105 7.97 83 17.9 71 1.59 61 8.11 84 12.7 82 1.71 49
JOF [136]71.7 3.08 64 5.89 68 1.24 98 3.48 28 5.04 31 1.37 37 3.85 52 5.98 57 2.07 71 5.43 55 7.81 56 3.28 70 11.3 104 14.2 104 4.51 160 6.72 122 13.1 124 2.37 81 7.48 39 17.1 39 1.54 39 8.01 75 12.6 77 1.73 69
SegFlow [156]72.5 3.23 108 6.50 124 1.21 34 3.55 42 5.27 48 1.31 21 4.03 65 5.73 40 1.34 7 6.09 122 9.56 148 3.37 101 11.1 72 14.0 80 4.50 146 6.10 46 11.8 46 2.40 93 7.51 40 17.2 41 1.66 90 8.06 79 12.6 77 1.73 69
Ad-TV-NDC [36]76.0 3.23 108 5.70 49 1.44 167 4.78 161 6.46 149 1.92 147 3.67 36 5.86 50 1.50 20 5.97 112 8.14 79 3.51 124 10.8 47 13.5 45 3.63 61 6.24 61 12.0 60 2.40 93 7.70 57 17.3 43 1.51 25 7.48 30 11.7 30 1.73 69
F-TV-L1 [15]76.0 3.30 122 6.36 114 1.29 140 4.39 133 6.32 141 1.62 99 3.80 48 5.90 53 1.76 47 5.61 80 7.97 67 3.31 88 10.9 54 13.6 50 3.59 36 5.84 30 11.2 29 2.33 62 7.70 57 17.6 58 1.79 117 7.61 35 11.9 34 1.78 131
CPM-Flow [114]76.6 3.17 97 6.31 109 1.21 34 3.54 39 5.26 46 1.31 21 4.22 83 5.88 52 1.45 16 6.11 124 9.48 144 3.31 88 11.1 72 13.9 68 4.50 146 6.28 65 12.1 64 2.32 59 7.66 53 17.6 58 1.74 106 8.18 89 12.8 90 1.76 115
Modified CLG [34]76.8 2.87 29 5.32 28 1.24 98 4.51 143 6.21 128 1.96 157 4.15 75 6.45 80 2.67 112 5.56 69 7.69 46 3.64 140 10.8 47 13.5 45 3.63 61 6.36 76 12.3 74 2.39 90 7.46 38 17.1 39 1.56 51 7.86 60 12.3 57 1.75 101
2DHMM-SAS [90]77.6 3.10 71 5.91 71 1.21 34 4.10 110 6.05 111 1.46 66 4.38 96 7.10 115 2.07 71 5.38 43 7.78 54 3.22 48 11.3 104 14.3 114 4.42 123 6.33 69 12.2 67 2.26 29 7.95 82 18.2 82 1.64 83 8.19 92 12.8 90 1.70 37
TC/T-Flow [77]78.2 3.21 105 6.24 99 1.22 64 3.90 91 5.86 94 1.43 56 3.69 40 5.83 46 1.50 20 5.88 105 8.93 122 3.15 23 11.1 72 13.9 68 4.50 146 6.23 59 12.0 60 2.26 29 8.61 124 19.0 106 1.93 133 8.16 88 12.8 90 1.70 37
COFM [59]79.4 3.03 52 5.76 56 1.22 64 3.55 42 5.21 43 1.32 25 3.82 49 6.98 106 2.81 116 5.41 52 7.97 67 3.30 83 10.8 47 13.6 50 3.62 55 7.01 154 13.7 151 2.40 93 8.00 88 18.5 93 1.98 136 7.91 66 12.4 67 1.80 151
DMF_ROB [135]79.7 3.15 87 6.13 93 1.22 64 3.96 96 5.87 95 1.56 84 5.24 137 7.74 144 2.62 106 5.73 90 8.32 87 3.19 36 11.0 61 13.8 61 4.50 146 6.07 43 11.7 43 2.37 81 7.66 53 17.5 54 1.50 19 8.10 82 12.7 82 1.73 69
Layers++ [37]80.5 2.96 41 5.56 42 1.22 64 3.29 12 4.64 17 1.26 3 4.07 68 7.24 119 3.08 127 5.48 59 8.10 75 3.25 62 12.0 168 15.2 169 4.62 171 7.29 162 14.3 162 2.44 115 7.63 51 17.5 54 1.54 39 7.84 59 12.3 57 1.70 37
FlowFields [108]80.6 3.15 87 6.30 105 1.21 34 3.57 45 5.34 53 1.32 25 4.73 116 6.89 99 3.23 136 5.85 100 8.96 125 3.08 14 10.8 47 13.6 50 4.19 108 6.57 101 12.8 108 2.36 77 7.72 60 17.8 67 1.67 92 8.20 94 12.9 98 1.74 93
LDOF [28]80.8 3.03 52 5.66 47 1.28 132 4.06 107 5.53 67 2.40 172 4.32 91 6.43 76 2.00 65 5.45 58 7.56 39 3.60 138 10.2 28 12.7 28 3.59 36 6.39 78 12.4 80 2.29 42 8.36 109 19.4 116 2.21 152 7.57 31 11.8 31 1.86 164
nLayers [57]81.1 3.03 52 5.72 51 1.21 34 3.48 28 5.09 37 1.31 21 5.60 143 7.52 135 4.26 158 5.61 80 8.33 88 3.29 73 11.6 147 14.6 146 4.31 114 6.66 115 12.9 117 2.40 93 7.58 45 17.3 43 1.59 61 7.94 70 12.4 67 1.69 29
TV-L1-MCT [64]81.2 3.17 97 6.05 89 1.22 64 3.87 83 5.82 90 1.40 46 4.48 103 7.75 145 2.24 84 5.37 41 7.76 52 3.24 59 11.6 147 14.7 152 4.31 114 6.08 44 11.7 43 2.31 51 8.07 92 18.6 97 2.15 149 7.68 40 12.0 40 1.68 27
ComplOF-FED-GPU [35]81.5 3.23 108 6.40 116 1.22 64 3.73 67 5.62 74 1.44 59 5.23 136 6.06 59 3.23 136 5.53 63 8.25 82 3.29 73 11.1 72 13.9 68 4.21 109 6.11 48 11.8 46 2.32 59 8.16 97 18.5 93 1.61 68 8.29 112 12.9 98 1.71 49
TC-Flow [46]82.7 3.31 124 6.70 134 1.22 64 3.91 93 5.95 98 1.45 62 3.64 32 5.84 47 1.28 4 5.70 85 8.50 103 3.22 48 11.2 86 14.1 89 4.44 127 6.34 72 12.3 74 2.41 105 7.79 70 17.9 71 1.55 46 8.42 128 13.2 130 1.74 93
DPOF [18]83.2 3.34 130 6.82 138 1.29 140 3.40 21 4.93 25 1.29 15 5.00 128 6.36 74 3.40 139 5.86 101 8.94 123 3.51 124 11.0 61 13.8 61 3.59 36 6.56 98 12.7 96 2.28 37 7.99 85 18.2 82 1.55 46 8.24 102 12.9 98 1.70 37
AdaConv-v1 [124]83.2 3.57 149 6.88 142 1.41 163 4.34 130 5.67 75 2.52 174 5.00 128 5.86 50 2.98 121 6.91 152 8.89 121 4.89 170 10.2 28 12.8 29 3.21 20 5.33 23 10.1 23 2.27 34 7.30 28 16.6 28 1.92 132 6.94 26 10.8 26 1.67 25
AGIF+OF [84]83.4 3.12 76 5.95 78 1.20 18 3.64 53 5.39 56 1.40 46 3.96 59 6.44 79 2.28 87 5.48 59 8.03 71 3.25 62 11.4 115 14.3 114 4.49 141 6.91 145 13.5 146 2.37 81 7.85 75 17.9 71 1.54 39 8.44 132 13.2 130 1.73 69
CRTflow [81]83.5 3.09 69 5.91 71 1.27 128 4.35 131 6.31 139 1.68 112 4.15 75 7.26 120 1.84 55 5.33 36 7.51 37 3.38 102 11.0 61 13.8 61 4.48 134 6.09 45 11.7 43 2.30 48 8.55 121 19.8 128 1.55 46 8.19 92 12.8 90 1.72 60
PGM-C [118]84.7 3.17 97 6.29 103 1.21 34 3.58 46 5.32 51 1.33 28 5.01 130 6.14 67 1.90 58 6.14 127 9.63 150 3.23 55 11.2 86 14.1 89 4.50 146 6.14 52 11.8 46 2.34 65 8.20 99 18.9 103 1.59 61 8.46 135 13.3 136 1.73 69
Classic++ [32]85.2 3.05 57 5.85 62 1.24 98 4.08 109 6.08 113 1.52 78 3.74 44 5.58 34 1.53 25 5.72 89 8.12 77 3.21 44 11.4 115 14.3 114 3.74 84 6.68 117 13.0 119 2.42 108 8.35 108 19.2 109 1.62 78 8.21 96 12.9 98 1.73 69
Sparse-NonSparse [56]85.8 3.07 61 5.88 66 1.21 34 3.61 48 5.33 52 1.33 28 4.29 89 7.47 133 2.19 79 5.37 41 7.74 48 3.21 44 11.5 130 14.5 135 4.36 118 6.66 115 12.9 117 2.41 105 8.69 131 20.1 134 1.67 92 8.27 109 13.0 112 1.70 37
EAI-Flow [147]86.0 3.37 133 6.27 101 1.32 150 3.79 73 5.59 71 1.52 78 4.30 90 7.09 113 2.39 96 5.60 78 8.34 90 2.96 6 11.2 86 14.1 89 4.34 117 6.04 42 11.6 40 2.34 65 7.72 60 17.6 58 3.12 170 7.77 52 12.1 45 1.82 161
ProbFlowFields [126]86.8 3.15 87 6.32 111 1.21 34 3.53 35 5.26 46 1.29 15 5.03 131 7.35 127 3.73 146 5.43 55 7.97 67 3.25 62 11.1 72 14.0 80 4.50 146 6.48 86 12.6 89 2.55 150 7.99 85 18.4 92 2.57 161 7.78 53 12.2 53 1.75 101
ProFlow_ROB [142]87.0 3.16 90 6.30 105 1.21 34 3.77 71 5.71 80 1.39 42 4.12 72 5.27 26 1.62 31 6.15 128 9.68 151 3.11 19 11.5 130 14.5 135 4.50 146 5.85 31 11.2 29 2.24 25 8.50 117 19.4 116 1.56 51 8.70 149 13.6 148 1.85 163
S2F-IF [121]87.8 3.26 115 6.66 131 1.20 18 3.53 35 5.25 45 1.29 15 4.11 71 6.64 88 2.34 92 5.89 106 9.06 130 3.08 14 11.4 115 14.3 114 4.51 160 6.41 79 12.4 80 2.40 93 7.84 73 18.1 78 1.76 114 8.33 119 13.1 121 1.75 101
OFLAF [78]87.9 3.10 71 5.98 83 1.20 18 3.44 22 5.03 29 1.26 3 3.73 43 5.82 45 1.66 34 5.33 36 7.74 48 3.10 17 11.6 147 14.7 152 4.50 146 6.58 106 12.8 108 2.48 129 9.33 156 21.6 157 2.06 144 8.45 134 13.2 130 1.80 151
PMF [73]88.0 3.14 83 6.13 93 1.20 18 3.73 67 5.60 72 1.27 8 5.24 137 8.98 161 3.76 147 5.75 91 8.56 109 3.28 70 10.8 47 13.6 50 3.62 55 6.55 95 12.7 96 2.35 74 8.41 114 19.5 122 1.64 83 8.57 142 13.4 141 1.70 37
MLDP_OF [87]88.1 3.08 64 5.98 83 1.21 34 4.01 103 6.01 107 1.49 73 3.67 36 6.14 67 1.47 18 5.78 94 8.13 78 3.95 158 11.3 104 14.2 104 3.87 92 6.71 120 13.0 119 2.51 139 7.73 63 17.7 63 1.71 101 8.18 89 12.8 90 1.76 115
Sparse Occlusion [54]88.3 3.16 90 6.18 97 1.23 84 4.14 117 6.24 133 1.45 62 3.67 36 5.84 47 1.52 24 5.61 80 8.26 83 3.15 23 11.5 130 14.4 125 4.48 134 6.26 63 12.1 64 2.46 120 8.52 119 19.6 125 1.54 39 8.28 111 13.0 112 1.75 101
BlockOverlap [61]88.6 2.98 43 5.47 38 1.33 153 4.38 132 6.09 114 1.88 140 4.26 86 5.57 33 3.14 130 5.56 69 7.32 31 4.14 163 11.1 72 13.9 68 3.77 87 6.41 79 12.3 74 2.54 147 7.75 64 17.4 49 3.02 168 7.32 28 11.4 28 1.78 131
HAST [107]88.8 3.01 49 5.73 53 1.21 34 3.45 24 5.01 28 1.27 8 6.39 157 8.24 152 4.09 152 5.43 55 7.96 65 3.03 8 11.2 86 14.2 104 3.59 36 7.47 166 14.7 166 2.47 123 8.68 130 20.1 134 1.53 32 8.35 122 13.1 121 1.77 125
TF+OM [98]88.8 3.33 129 6.83 139 1.25 108 3.65 54 5.43 60 1.47 68 3.82 49 6.43 76 1.68 39 6.01 117 9.04 129 3.19 36 11.2 86 14.1 89 4.38 120 6.46 85 12.5 85 2.34 65 8.30 107 19.2 109 1.86 125 8.05 78 12.6 77 1.75 101
FlowFields+ [128]88.8 3.14 83 6.26 100 1.22 64 3.54 39 5.27 48 1.30 20 4.74 119 7.10 115 3.20 134 6.01 117 9.35 140 3.11 19 11.1 72 13.9 68 4.50 146 6.57 101 12.8 108 2.40 93 7.89 79 18.2 82 1.80 119 8.22 98 12.9 98 1.73 69
FlowNetS+ft+v [110]90.0 3.07 61 5.81 59 1.28 132 4.57 150 6.29 137 2.41 173 4.01 62 5.64 36 2.13 76 5.55 67 7.77 53 3.88 154 11.3 104 14.2 104 4.46 130 5.99 39 11.5 37 2.35 74 8.63 127 20.0 131 1.62 78 7.70 43 12.0 40 1.74 93
Filter Flow [19]91.1 3.13 81 5.90 69 1.28 132 4.56 149 6.38 145 1.85 138 4.22 83 6.28 71 2.10 74 5.91 107 7.97 67 3.44 115 10.4 37 13.1 39 3.69 72 6.43 83 12.5 85 2.40 93 8.17 98 18.8 102 1.62 78 7.94 70 12.4 67 1.78 131
LSM [39]93.3 3.12 76 6.05 89 1.21 34 3.68 59 5.47 62 1.33 28 4.38 96 7.66 142 2.01 66 5.55 67 8.19 80 3.19 36 11.5 130 14.5 135 4.43 124 6.83 136 13.3 137 2.37 81 8.70 132 20.1 134 1.72 104 8.34 121 13.1 121 1.71 49
EpicFlow [100]93.6 3.17 97 6.34 112 1.21 34 3.79 73 5.70 78 1.44 59 4.28 88 5.73 40 1.67 37 6.37 140 10.1 156 3.39 105 11.2 86 14.1 89 4.50 146 6.23 59 12.0 60 2.38 88 8.11 94 18.5 93 1.76 114 8.76 153 13.8 153 1.74 93
Black & Anandan [4]94.3 3.22 107 5.87 64 1.30 144 4.82 164 6.55 154 1.78 130 7.16 161 7.10 115 3.93 149 6.25 134 8.49 102 3.35 99 10.9 54 13.7 55 3.56 30 6.33 69 12.2 67 2.37 81 8.23 102 18.6 97 1.64 83 7.67 39 11.9 34 1.69 29
RNLOD-Flow [119]94.5 3.06 59 5.87 64 1.21 34 3.96 96 5.97 104 1.42 53 4.39 98 8.08 149 2.44 98 5.35 38 7.75 50 3.18 31 11.5 130 14.5 135 4.49 141 6.71 120 13.1 124 2.43 111 7.85 75 18.0 76 2.18 150 8.44 132 13.2 130 1.73 69
TCOF [69]95.1 3.12 76 5.94 76 1.21 34 4.60 153 6.64 160 1.76 128 4.13 73 7.30 122 1.81 51 5.42 54 7.88 59 3.25 62 11.3 104 14.2 104 3.63 61 6.42 81 12.4 80 2.36 77 9.08 153 21.0 153 1.59 61 8.37 124 13.1 121 1.76 115
Ramp [62]95.5 3.11 75 5.96 80 1.22 64 3.61 48 5.34 53 1.40 46 4.91 125 8.45 155 3.20 134 5.29 31 7.66 44 3.21 44 11.5 130 14.5 135 4.31 114 6.88 144 13.4 141 2.48 129 8.73 138 20.2 138 1.52 31 8.29 112 13.0 112 1.73 69
Fusion [6]96.3 3.04 56 5.86 63 1.22 64 3.75 70 5.47 62 1.42 53 4.08 69 5.55 32 3.08 127 5.80 96 8.10 75 3.19 36 11.4 115 14.3 114 3.73 81 6.99 151 13.7 151 2.60 156 8.40 113 19.4 116 1.65 88 8.50 137 13.3 136 1.80 151
Classic+NL [31]96.9 3.10 71 5.92 74 1.23 84 3.66 56 5.40 57 1.39 42 4.78 121 8.42 154 3.01 125 5.36 39 7.78 54 3.30 83 11.5 130 14.5 135 4.24 111 6.73 124 13.1 124 2.40 93 8.74 139 20.2 138 1.70 99 8.29 112 13.0 112 1.71 49
ComponentFusion [94]97.0 3.41 135 7.08 145 1.20 18 3.63 51 5.44 61 1.27 8 4.20 81 6.49 82 2.43 97 5.59 75 8.38 94 3.32 92 11.4 115 14.4 125 4.11 105 6.26 63 12.1 64 2.35 74 9.30 155 21.6 157 2.80 166 8.68 147 13.6 148 1.73 69
AggregFlow [95]97.0 3.80 160 8.08 160 1.23 84 3.87 83 5.83 91 1.43 56 4.21 82 6.79 92 2.85 118 6.11 124 9.36 141 3.31 88 10.6 41 13.3 41 3.67 69 6.13 50 11.8 46 2.34 65 8.70 132 19.8 128 2.30 156 8.27 109 13.0 112 1.75 101
Occlusion-TV-L1 [63]99.3 3.14 83 6.13 93 1.25 108 4.47 141 6.61 157 1.66 107 3.51 25 5.71 39 1.70 41 6.33 136 9.58 149 3.51 124 11.0 61 13.9 68 3.57 32 6.48 86 12.6 89 2.52 144 8.36 109 18.1 78 2.00 139 8.32 118 13.0 112 1.79 145
Bartels [41]99.4 3.48 142 7.24 149 1.30 144 4.02 104 6.12 119 1.68 112 3.74 44 5.80 44 1.95 63 5.87 103 8.44 98 3.78 152 10.3 33 12.8 29 3.75 86 6.77 131 13.0 119 2.73 173 7.53 42 17.3 43 2.72 164 8.13 85 12.7 82 1.77 125
Classic+CPF [82]99.6 3.12 76 5.96 80 1.21 34 3.72 66 5.51 66 1.39 42 4.39 98 7.38 130 2.27 86 5.32 34 7.70 47 3.18 31 11.7 156 14.8 158 4.50 146 7.18 160 14.0 160 2.45 117 8.79 140 20.2 138 1.57 55 8.71 151 13.7 150 1.73 69
HBM-GC [103]99.7 3.08 64 5.90 69 1.26 122 3.97 99 6.04 110 1.41 50 3.92 56 5.62 35 2.87 120 5.54 65 8.03 71 3.21 44 11.7 156 14.7 152 4.58 170 7.66 170 15.0 170 2.69 170 8.36 109 19.3 112 1.55 46 7.86 60 12.3 57 1.76 115
LFNet_ROB [145]99.9 3.65 154 7.73 155 1.23 84 3.88 86 5.80 89 1.49 73 4.57 106 8.96 160 2.02 68 5.62 83 8.44 98 3.18 31 11.0 61 13.8 61 4.47 131 7.19 161 14.1 161 2.47 123 7.59 47 17.4 49 1.82 121 8.10 82 12.7 82 1.78 131
Efficient-NL [60]100.2 3.05 57 5.77 57 1.21 34 3.90 91 5.84 92 1.38 39 5.90 149 6.94 103 4.19 155 5.59 75 8.09 74 3.20 43 11.5 130 14.4 125 4.40 122 6.87 140 13.4 141 2.40 93 8.85 141 20.5 143 1.68 96 8.57 142 13.4 141 1.66 22
CNN-flow-warp+ref [115]100.6 2.90 32 5.43 33 1.25 108 4.10 110 5.95 98 1.83 137 4.92 126 7.63 140 2.45 99 6.13 126 7.85 57 3.72 146 11.3 104 14.2 104 4.51 160 6.03 41 11.6 40 2.46 120 9.00 146 20.8 151 1.65 88 7.91 66 12.4 67 1.76 115
FC-2Layers-FF [74]100.6 3.18 101 6.16 96 1.22 64 3.33 18 4.73 20 1.35 34 4.34 95 7.09 113 3.11 129 5.56 69 8.29 84 3.29 73 11.5 130 14.5 135 4.48 134 7.00 152 13.7 151 2.48 129 8.92 145 20.6 146 1.71 101 8.30 115 13.0 112 1.73 69
Horn & Schunck [3]101.0 3.16 90 5.83 60 1.26 122 4.91 165 6.65 161 1.92 147 6.13 152 6.85 95 3.53 142 6.80 149 9.10 131 3.57 133 10.9 54 13.7 55 3.59 36 6.16 55 11.9 54 2.32 59 8.63 127 19.5 122 1.84 124 7.91 66 12.3 57 1.73 69
2D-CLG [1]101.4 3.01 49 5.65 45 1.28 132 4.59 152 6.17 122 1.95 156 5.18 134 6.06 59 3.15 132 6.01 117 7.88 59 3.97 159 11.4 115 14.4 125 4.69 172 5.98 38 11.5 37 2.45 117 8.89 144 20.5 143 1.67 92 7.74 45 12.0 40 1.71 49
FESL [72]101.7 3.16 90 6.02 87 1.21 34 3.65 54 5.42 59 1.35 34 4.39 98 7.61 139 2.18 78 5.71 87 8.35 92 3.30 83 11.6 147 14.7 152 4.51 160 6.73 124 13.1 124 2.47 123 8.70 132 20.1 134 1.56 51 8.42 128 13.2 130 1.75 101
SRR-TVOF-NL [89]101.9 3.32 127 6.46 122 1.23 84 3.96 96 5.96 101 1.59 89 4.68 112 7.90 147 3.52 141 5.99 115 8.77 116 3.23 55 11.2 86 14.1 89 4.45 129 6.79 134 13.2 134 2.31 51 7.88 77 18.0 76 1.50 19 8.37 124 13.1 121 1.75 101
RFlow [88]102.7 3.08 64 5.99 85 1.23 84 4.33 127 6.31 139 1.66 107 4.83 122 7.32 123 3.14 130 5.87 103 8.72 115 3.47 119 11.1 72 14.0 80 3.60 43 6.54 94 12.7 96 2.39 90 8.54 120 19.8 128 1.61 68 8.26 107 12.9 98 1.80 151
TriFlow [93]103.8 3.71 157 7.95 159 1.25 108 4.31 126 6.36 144 1.71 118 4.05 66 6.86 97 1.84 55 6.21 133 9.44 143 3.17 27 11.3 104 14.2 104 4.48 134 6.76 130 13.1 124 2.29 42 8.01 90 18.2 82 1.75 111 8.24 102 12.9 98 1.70 37
OFH [38]103.9 3.18 101 6.29 103 1.23 84 4.11 112 5.96 101 1.61 96 4.68 112 8.40 153 1.68 39 5.84 98 8.99 126 3.03 8 11.3 104 14.2 104 4.25 113 6.30 68 12.2 67 2.40 93 8.59 122 19.3 112 1.89 128 8.55 139 13.4 141 1.97 170
PWC-Net_RVC [143]104.6 3.66 156 7.76 156 1.21 34 3.91 93 5.97 104 1.37 37 3.88 55 6.73 90 1.48 19 6.36 138 10.1 156 3.13 21 11.8 161 14.9 162 4.49 141 6.78 133 13.1 124 2.34 65 7.72 60 17.7 63 1.66 90 8.57 142 13.5 146 1.88 165
3DFlow [133]104.9 3.26 115 6.37 115 1.21 34 3.70 62 5.55 68 1.46 66 4.51 104 6.52 83 2.28 87 5.84 98 8.84 119 3.59 136 11.2 86 14.1 89 3.79 89 7.04 157 13.7 151 2.68 169 8.59 122 19.4 116 1.82 121 8.26 107 12.9 98 1.77 125
CostFilter [40]105.5 3.46 141 7.24 149 1.19 12 3.71 64 5.60 72 1.27 8 5.63 145 9.41 167 3.86 148 6.37 140 10.1 156 3.23 55 11.2 86 14.0 80 3.78 88 6.35 74 12.2 67 2.40 93 8.86 143 20.6 146 1.69 97 8.80 155 13.8 153 1.74 93
S2D-Matching [83]106.0 3.21 105 6.22 98 1.22 64 3.97 99 5.95 98 1.48 70 4.57 106 7.70 143 2.84 117 5.48 59 8.06 73 3.48 121 11.4 115 14.3 114 4.14 106 6.97 149 13.6 149 2.56 154 8.09 93 18.6 97 1.74 106 8.21 96 12.9 98 1.76 115
Nguyen [33]106.1 3.26 115 6.11 92 1.33 153 4.94 166 6.51 152 1.91 146 4.09 70 7.32 123 1.96 64 6.19 132 8.53 106 3.60 138 11.1 72 13.9 68 3.58 34 6.55 95 12.7 96 2.36 77 9.44 158 21.8 161 1.80 119 7.86 60 12.3 57 1.74 93
SVFilterOh [109]106.2 3.23 108 6.35 113 1.23 84 3.53 35 5.19 41 1.31 21 5.91 150 8.20 151 4.22 156 5.75 91 8.52 105 3.43 113 11.4 115 14.3 114 4.53 167 6.97 149 13.6 149 2.38 88 7.94 80 18.3 89 1.57 55 8.31 117 13.0 112 1.79 145
FlowNet2 [120]107.6 4.84 170 10.1 171 1.29 140 4.11 112 6.13 120 1.61 96 4.73 116 7.06 111 2.36 93 6.36 138 10.0 154 3.38 102 11.2 86 14.1 89 3.71 76 6.44 84 12.5 85 2.33 62 8.45 115 19.4 116 1.61 68 8.03 77 12.6 77 1.77 125
Adaptive [20]107.8 3.24 112 6.44 119 1.25 108 4.57 150 6.61 157 1.72 119 3.94 58 6.12 66 1.81 51 5.86 101 8.66 113 3.47 119 11.6 147 14.6 146 3.59 36 6.55 95 12.7 96 2.51 139 9.03 149 20.6 146 1.59 61 8.13 85 12.7 82 1.78 131
Steered-L1 [116]107.8 2.97 42 5.73 53 1.21 34 3.81 77 5.72 82 1.60 93 8.15 164 9.24 164 6.46 172 6.42 142 9.21 138 4.28 167 11.4 115 14.3 114 3.80 90 6.52 92 12.7 96 2.43 111 8.20 99 19.0 106 2.54 159 8.33 119 13.1 121 1.70 37
IAOF [50]108.2 3.53 147 6.60 129 1.32 150 5.39 174 7.19 174 1.96 157 5.81 147 7.32 123 3.63 144 6.15 128 8.34 90 3.72 146 11.1 72 14.0 80 3.60 43 6.50 89 12.6 89 2.34 65 8.28 106 19.0 106 1.53 32 7.94 70 12.4 67 1.73 69
CompactFlow_ROB [155]108.6 3.91 163 8.50 167 1.24 98 3.94 95 5.94 97 1.54 82 5.28 139 8.58 157 2.62 106 8.69 171 14.5 173 3.26 67 10.9 54 13.7 55 3.64 68 6.87 140 13.4 141 2.33 62 8.50 117 19.6 125 1.53 32 8.22 98 12.9 98 1.75 101
Complementary OF [21]109.0 3.48 142 7.32 153 1.20 18 3.89 89 5.96 101 1.45 62 8.94 168 6.94 103 5.45 166 6.33 136 10.0 154 3.09 16 11.3 104 14.2 104 4.24 111 6.33 69 12.3 74 2.42 108 8.62 126 19.3 112 1.75 111 9.07 164 14.3 165 1.72 60
TVL1_RVC [176]110.4 3.32 127 6.27 101 1.36 160 5.03 168 6.77 168 1.94 155 4.84 123 6.87 98 2.98 121 6.16 131 8.51 104 3.58 135 10.9 54 13.7 55 3.63 61 6.57 101 12.7 96 2.43 111 9.00 146 20.6 146 2.20 151 7.72 44 12.1 45 1.71 49
FF++_ROB [141]110.7 3.27 118 6.67 132 1.20 18 3.74 69 5.58 69 1.38 39 4.86 124 7.42 131 2.99 123 6.57 146 10.4 159 3.54 129 11.5 130 14.5 135 4.51 160 6.62 112 12.8 108 2.47 123 7.97 83 18.3 89 1.90 129 8.24 102 12.9 98 1.78 131
AugFNG_ROB [139]111.0 3.73 158 7.90 158 1.25 108 4.12 115 6.02 108 1.74 123 4.70 115 8.79 159 1.94 62 8.14 169 13.4 170 3.29 73 12.0 168 15.1 167 4.50 146 6.50 89 12.6 89 2.28 37 8.03 91 18.3 89 1.62 78 7.75 46 12.1 45 1.75 101
TV-L1-improved [17]111.3 3.09 69 6.03 88 1.25 108 4.55 148 6.59 156 1.70 116 5.88 148 5.66 37 4.09 152 5.53 63 7.88 59 3.22 48 11.4 115 14.4 125 3.61 49 6.73 124 13.1 124 2.51 139 9.48 159 22.1 163 1.94 134 8.25 105 12.9 98 1.79 145
TI-DOFE [24]112.1 3.41 135 6.44 119 1.44 167 5.20 172 6.82 171 2.01 161 4.19 80 6.41 75 1.88 57 6.98 153 9.50 145 3.70 144 10.8 47 13.6 50 3.61 49 6.59 107 12.8 108 2.36 77 8.13 96 18.2 82 1.77 116 8.53 138 12.4 67 2.33 174
EPPM w/o HM [86]112.3 3.35 131 6.86 141 1.21 34 3.85 82 5.88 96 1.29 15 7.03 159 9.47 170 3.97 151 6.15 128 9.51 146 3.38 102 10.6 41 13.3 41 3.62 55 7.00 152 13.7 151 2.37 81 8.85 141 20.5 143 2.62 163 8.42 128 13.2 130 1.76 115
GraphCuts [14]114.3 3.65 154 7.01 144 1.27 128 3.89 89 5.71 80 1.59 89 7.54 162 5.84 47 4.31 159 5.98 114 8.42 96 3.45 118 11.4 115 14.4 125 4.09 103 6.56 98 12.8 108 2.30 48 8.70 132 20.2 138 1.98 136 8.59 146 13.5 146 1.73 69
BriefMatch [122]115.0 3.25 114 6.49 123 1.25 108 3.87 83 5.67 75 1.97 159 6.16 153 6.17 69 4.79 162 6.83 151 8.37 93 5.73 173 11.0 61 13.8 61 3.73 81 6.75 129 13.0 119 2.61 158 7.99 85 17.9 71 3.29 171 8.22 98 12.8 90 2.32 173
NL-TV-NCC [25]115.8 3.37 133 6.58 128 1.24 98 4.23 121 6.41 147 1.49 73 4.39 98 6.68 89 2.07 71 7.19 161 11.2 164 3.35 99 10.7 44 13.4 43 4.00 100 6.95 146 13.4 141 2.44 115 9.06 150 20.0 131 2.13 148 8.42 128 13.1 121 1.78 131
EPMNet [131]116.8 4.90 171 10.5 175 1.28 132 4.04 106 5.98 106 1.60 93 4.73 116 7.06 111 2.36 93 8.74 173 15.0 174 3.48 121 11.2 86 14.1 89 3.71 76 6.70 119 13.0 119 2.34 65 8.45 115 19.4 116 1.61 68 8.38 126 13.1 121 1.78 131
IAOF2 [51]117.5 3.43 138 6.70 134 1.28 132 4.62 155 6.77 168 1.74 123 4.41 102 6.89 99 2.12 75 5.97 112 8.53 106 3.33 95 11.6 147 14.7 152 4.06 102 6.87 140 13.4 141 2.51 139 8.26 103 18.7 101 1.61 68 8.22 98 12.9 98 1.74 93
TriangleFlow [30]118.7 3.24 112 6.31 109 1.26 122 4.29 125 6.29 137 1.66 107 4.67 111 6.85 95 2.48 100 5.78 94 8.47 100 3.30 83 11.4 115 14.4 125 3.47 28 6.63 114 12.8 108 2.37 81 9.67 163 22.5 164 2.08 146 9.69 171 15.2 171 1.90 167
ResPWCR_ROB [140]119.2 3.52 146 7.36 154 1.23 84 4.06 107 6.18 125 1.53 81 4.57 106 6.90 101 1.91 59 7.44 164 12.2 168 3.40 108 11.5 130 14.6 146 4.39 121 7.10 158 13.7 151 2.54 147 7.81 72 17.8 67 1.67 92 9.04 163 14.2 162 1.71 49
LocallyOriented [52]119.5 3.29 121 6.53 126 1.26 122 4.64 156 6.69 163 1.74 123 5.61 144 7.56 136 3.67 145 6.73 147 9.84 153 3.18 31 11.5 130 14.4 125 3.71 76 6.57 101 12.7 96 2.45 117 8.71 136 19.3 112 1.71 101 8.40 127 13.1 121 1.72 60
Correlation Flow [76]121.1 3.27 118 6.50 124 1.20 18 4.42 135 6.56 155 1.65 104 3.98 61 6.10 64 2.30 91 5.93 109 8.94 123 3.32 92 11.6 147 14.6 146 3.84 91 7.63 169 14.8 167 2.65 167 9.95 167 23.0 167 2.01 141 8.73 152 13.7 150 1.71 49
ContinualFlow_ROB [148]121.2 3.79 159 8.09 161 1.25 108 4.03 105 6.11 117 1.61 96 4.76 120 7.58 137 2.38 95 7.09 156 11.7 165 3.17 27 12.2 172 15.4 172 4.49 141 6.35 74 12.3 74 2.29 42 8.71 136 20.0 131 1.61 68 9.02 161 14.2 162 1.78 131
ACK-Prior [27]122.2 3.30 122 6.56 127 1.21 34 3.81 77 5.78 85 1.42 53 7.13 160 6.90 101 5.04 163 6.02 120 8.78 117 3.70 144 11.7 156 14.7 152 4.57 169 6.95 146 13.5 146 2.50 135 8.36 109 19.2 109 2.53 158 8.56 141 13.4 141 1.73 69
ROF-ND [105]122.3 3.18 101 5.83 60 1.21 34 4.13 116 6.13 120 1.92 147 4.22 83 7.51 134 2.22 83 7.10 157 10.8 160 3.53 127 11.4 115 14.3 114 4.48 134 6.95 146 13.5 146 2.53 145 8.21 101 18.6 97 1.90 129 9.08 165 14.2 162 1.81 159
HBpMotionGpu [43]123.4 3.63 152 7.28 151 1.35 158 4.78 161 6.69 163 1.92 147 4.33 94 7.01 109 2.56 105 6.46 143 9.81 152 3.40 108 11.5 130 14.4 125 5.69 177 6.83 136 13.3 137 2.55 150 7.40 34 16.9 32 1.51 25 8.30 115 13.0 112 1.79 145
StereoOF-V1MT [117]123.4 3.56 148 7.20 148 1.22 64 4.27 124 6.18 125 1.70 116 6.10 151 6.80 93 3.43 140 7.17 160 9.52 147 4.01 162 11.2 86 14.1 89 4.43 124 6.61 111 12.5 85 2.60 156 9.49 160 21.6 157 2.05 142 8.01 75 12.4 67 1.78 131
H+S_RVC [177]123.8 3.43 138 6.69 133 1.28 132 4.50 142 6.02 108 1.90 143 5.12 132 7.34 126 2.66 110 7.02 155 8.60 111 3.54 129 11.5 130 14.5 135 3.88 93 6.62 112 12.8 108 2.43 111 8.64 129 19.5 122 2.06 144 8.36 123 12.8 90 1.76 115
Dynamic MRF [7]128.0 3.19 104 6.41 117 1.22 64 4.11 112 6.21 128 1.56 84 5.37 141 7.35 127 2.70 113 6.74 148 9.18 136 4.19 164 11.1 72 13.9 68 4.48 134 7.02 155 13.7 151 2.62 161 9.26 154 21.4 156 2.23 153 8.57 142 13.3 136 1.80 151
LiteFlowNet [138]128.2 3.86 161 8.34 163 1.22 64 3.80 75 5.75 84 1.44 59 5.33 140 9.45 169 2.66 110 8.72 172 14.4 172 3.88 154 11.8 161 14.8 158 4.50 146 7.03 156 13.7 151 2.40 93 9.07 152 20.4 142 1.69 97 8.13 85 12.7 82 1.78 131
FOLKI [16]128.8 3.64 153 7.12 146 1.65 172 5.22 173 6.72 166 2.36 171 5.20 135 8.08 149 3.96 150 7.93 166 9.33 139 5.52 172 11.2 86 14.0 80 3.70 73 6.56 98 12.6 89 2.74 174 8.00 88 18.2 82 2.88 167 7.96 73 12.3 57 1.78 131
Shiralkar [42]129.0 3.57 149 7.31 152 1.22 64 4.46 140 6.33 143 1.65 104 5.49 142 6.98 106 2.73 114 7.42 163 10.9 161 3.43 113 11.5 130 14.4 125 3.73 81 6.57 101 12.7 96 2.48 129 9.58 161 21.9 162 1.88 127 9.18 167 14.4 166 1.75 101
SimpleFlow [49]129.8 3.10 71 5.97 82 1.22 64 4.19 119 6.11 117 1.64 103 9.91 171 9.43 168 6.53 173 5.58 72 8.29 84 3.30 83 11.6 147 14.6 146 4.43 124 7.42 164 14.6 165 2.56 154 10.7 171 25.2 171 2.73 165 9.16 166 14.4 166 1.73 69
Rannacher [23]130.1 3.31 124 6.72 137 1.25 108 4.60 153 6.66 162 1.72 119 6.36 156 6.54 84 4.25 157 5.91 107 8.87 120 3.49 123 11.5 130 14.5 135 3.63 61 6.73 124 13.1 124 2.53 145 9.35 157 21.7 160 1.98 136 8.70 149 13.7 150 1.75 101
Learning Flow [11]130.5 3.14 83 6.09 91 1.27 128 4.51 143 6.53 153 1.67 110 11.5 176 12.9 176 7.17 176 6.31 135 8.30 86 3.66 141 11.7 156 14.8 158 3.89 94 6.59 107 12.8 108 2.48 129 8.27 105 18.9 103 1.96 135 8.68 147 13.4 141 1.80 151
SILK [80]130.7 3.45 140 6.85 140 1.36 160 5.11 170 6.70 165 2.21 168 11.1 173 9.96 171 6.24 171 6.49 144 8.82 118 3.59 136 11.4 115 14.3 114 3.54 29 6.87 140 13.3 137 2.63 163 7.76 66 17.7 63 1.87 126 8.20 94 12.7 82 1.80 151
OFRF [132]133.6 4.02 164 8.26 162 1.33 153 4.53 146 6.49 150 1.81 134 4.60 110 7.27 121 2.13 76 6.02 120 9.15 133 3.39 105 11.8 161 14.9 162 4.23 110 7.13 159 13.9 159 2.39 90 9.02 148 20.8 151 1.59 61 8.79 154 13.8 153 1.77 125
Adaptive flow [45]134.3 3.60 151 6.30 105 1.54 171 5.14 171 6.79 170 2.14 167 4.52 105 6.60 86 3.01 125 6.54 145 8.64 112 4.23 165 12.1 171 15.2 169 4.09 103 7.57 167 14.9 169 2.64 165 7.75 64 17.8 67 2.28 155 8.47 136 13.3 136 1.71 49
UnFlow [127]134.9 4.05 165 8.73 168 1.31 148 4.44 139 6.28 136 1.87 139 4.92 126 7.36 129 2.62 106 5.95 111 9.00 127 3.27 68 12.0 168 15.2 169 4.37 119 7.59 168 14.8 167 2.61 158 7.77 68 17.6 58 1.64 83 10.4 172 15.4 172 2.33 174
StereoFlow [44]135.5 5.35 176 10.3 173 1.42 165 5.03 168 7.21 175 1.76 128 4.14 74 6.94 103 2.01 66 5.83 97 8.55 108 3.33 95 13.7 174 17.3 174 4.70 173 8.71 175 17.2 175 2.70 171 7.88 77 18.1 78 1.61 68 8.82 157 13.9 158 1.79 145
2bit-BM-tele [96]136.9 3.31 124 6.41 117 1.34 157 4.53 146 6.62 159 1.80 133 6.23 154 9.24 164 6.19 170 5.94 110 8.59 110 3.55 131 11.3 104 14.2 104 4.03 101 7.72 171 15.1 171 3.02 175 12.2 175 28.7 176 4.77 177 7.76 50 12.1 45 1.82 161
IIOF-NLDP [129]138.0 3.36 132 6.62 130 1.21 34 4.22 120 6.32 141 1.59 89 5.16 133 7.63 140 2.63 109 6.10 123 9.20 137 3.53 127 11.6 147 14.6 146 4.79 175 7.42 164 14.5 164 2.71 172 12.0 174 28.2 174 3.38 172 8.93 159 13.9 158 1.74 93
SPSA-learn [13]141.6 3.89 162 7.79 157 1.27 128 4.43 137 6.17 122 1.81 134 9.03 169 8.47 156 5.47 167 6.80 149 9.40 142 3.72 146 11.5 130 14.5 135 3.91 96 6.51 91 12.6 89 2.46 120 11.9 172 27.9 173 4.54 175 10.5 174 16.5 174 1.75 101
FFV1MT [104]142.5 4.09 167 8.38 164 1.31 148 4.68 158 6.18 125 2.02 162 6.95 158 11.5 173 3.35 138 7.12 158 9.16 134 3.98 160 11.3 104 14.1 89 3.74 84 6.77 131 12.7 96 2.50 135 9.59 162 21.0 153 2.05 142 8.87 158 13.8 153 1.90 167
SegOF [10]144.7 3.51 144 7.12 146 1.32 150 4.17 118 6.10 115 1.59 89 8.69 166 7.75 145 5.15 164 8.58 170 14.3 171 4.29 168 11.7 156 14.8 158 4.50 146 6.79 134 13.2 134 2.50 135 10.1 168 23.5 168 2.55 160 8.80 155 13.8 153 1.72 60
PGAM+LK [55]147.5 4.08 166 8.41 165 1.65 172 4.74 160 6.45 148 2.27 170 8.87 167 12.2 174 6.88 174 8.06 168 10.9 161 4.83 169 11.4 115 14.3 114 3.90 95 6.83 136 13.2 134 2.55 150 8.26 103 18.9 103 2.27 154 8.55 139 13.3 136 1.90 167
Heeger++ [102]147.5 4.76 169 9.63 170 1.33 153 4.65 157 6.22 131 1.90 143 7.84 163 9.26 166 3.57 143 7.12 158 9.16 134 3.98 160 11.9 165 15.0 165 4.47 131 6.52 92 12.2 67 2.61 158 9.82 164 20.6 146 2.00 139 9.02 161 14.0 160 1.79 145
SLK [47]148.7 3.51 144 6.96 143 1.41 163 4.72 159 6.10 115 1.98 160 9.84 170 7.59 138 5.20 165 7.98 167 11.0 163 6.14 174 11.8 161 14.9 162 3.71 76 6.60 109 12.7 96 2.50 135 9.87 166 22.8 166 2.08 146 8.94 160 14.0 160 2.03 171
WRT [146]151.0 3.42 137 6.71 136 1.23 84 4.33 127 6.06 112 1.89 142 9.93 172 8.00 148 5.95 169 6.98 153 9.01 128 3.77 151 11.9 165 15.1 167 3.97 99 7.82 172 15.4 172 2.64 165 12.5 176 29.5 177 3.47 173 10.5 174 16.6 175 1.80 151
HCIC-L [97]151.1 4.98 173 9.28 169 1.77 175 4.97 167 6.87 173 2.11 165 5.70 146 10.0 172 4.41 161 7.85 165 11.8 166 3.68 143 10.9 54 13.7 55 3.72 80 8.18 174 16.1 174 2.55 150 9.06 150 21.0 153 2.58 162 9.57 170 15.0 170 1.81 159
WOLF_ROB [144]153.3 5.06 174 10.3 173 1.30 144 4.79 163 6.72 166 1.75 126 6.29 155 9.03 162 4.14 154 7.37 162 11.8 166 3.33 95 11.9 165 15.0 165 4.48 134 7.40 163 14.3 162 2.51 139 10.5 170 23.9 169 1.74 106 9.44 168 14.8 168 1.78 131
Pyramid LK [2]161.5 4.16 168 8.44 166 1.74 174 5.83 175 6.82 171 2.76 175 11.4 174 8.60 158 5.89 168 12.4 176 16.7 175 7.03 176 14.3 175 18.1 175 3.92 98 6.69 118 12.2 67 2.63 163 10.3 169 24.0 170 2.45 157 11.1 176 17.4 176 2.55 176
GroupFlow [9]164.0 4.94 172 10.2 172 1.36 160 4.51 143 6.50 151 1.92 147 8.67 165 9.13 163 4.38 160 8.83 174 13.0 169 5.40 171 12.9 173 16.3 173 4.53 167 7.89 173 15.5 173 2.65 167 9.85 165 22.6 165 1.91 131 9.52 169 14.9 169 1.88 165
Periodicity [79]174.7 5.27 175 11.1 176 1.83 176 7.09 176 7.33 176 2.86 176 11.4 174 12.2 174 7.13 175 10.5 175 17.1 176 6.14 174 14.9 176 19.0 176 4.71 174 9.13 176 17.9 176 3.16 176 11.9 172 27.8 172 3.76 174 10.4 172 15.8 173 2.29 172
AVG_FLOW_ROB [137]176.8 14.6 177 20.0 177 3.66 177 11.3 177 12.1 177 4.33 177 13.4 177 14.1 177 7.93 177 19.0 177 25.3 177 10.2 177 18.3 177 23.1 177 5.58 176 16.7 177 32.2 177 4.90 177 16.6 177 28.6 175 4.56 176 15.9 177 19.8 177 4.61 177
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.
* 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.