Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A90   A95   A99  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R1.0
normalized 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
MDP-Flow2 [68]12.0 6.71 2 9.78 3 8.39 9 6.36 9 11.5 11 6.23 12 7.12 4 9.73 7 5.42 2 21.2 5 18.8 9 41.2 11 30.1 6 26.5 4 45.6 50 27.7 17 19.5 27 36.0 18 6.48 2 13.8 5 10.3 6 8.19 23 16.4 18 7.11 28
PMMST [114]13.5 6.84 10 9.80 4 8.50 19 6.74 26 11.7 13 6.36 29 7.10 3 9.45 3 5.41 1 21.1 1 18.6 3 41.1 3 30.2 10 26.5 4 45.7 61 27.3 2 18.1 5 36.0 18 6.51 4 13.9 10 10.3 6 8.22 27 16.5 24 7.15 39
NNF-Local [87]15.1 6.74 4 10.1 7 8.30 2 5.97 1 10.3 2 6.14 3 7.09 2 9.63 6 5.44 3 21.7 32 20.5 65 41.2 11 30.3 20 26.6 9 45.4 24 27.9 34 20.6 62 36.0 18 6.51 4 13.8 5 10.3 6 8.04 10 16.1 7 7.10 26
PH-Flow [101]15.1 7.05 24 10.9 18 8.50 19 6.10 3 10.6 5 6.14 3 7.18 5 9.83 8 5.55 6 21.1 1 18.5 2 41.1 3 30.1 6 26.6 9 45.2 15 27.9 34 21.7 87 35.7 9 6.60 15 14.3 20 10.3 6 8.11 14 16.3 15 7.14 36
CombBMOF [113]16.4 6.93 14 9.87 6 8.43 12 6.33 8 11.4 9 6.22 11 7.60 44 10.3 14 6.25 78 21.5 20 19.4 24 41.2 11 30.2 10 26.6 9 45.3 20 27.7 17 19.2 19 36.1 31 6.57 11 14.1 13 10.3 6 7.67 2 15.4 4 6.82 1
NN-field [71]19.5 6.88 11 10.8 14 8.48 16 5.99 2 10.3 2 6.13 2 7.65 53 9.54 4 5.81 32 21.9 47 21.0 85 41.4 24 30.2 10 26.6 9 45.4 24 27.8 27 20.0 43 36.0 18 6.48 2 13.7 4 10.3 6 8.02 9 16.1 7 7.04 18
IROF++ [58]24.8 7.07 27 11.3 29 8.50 19 6.64 21 12.0 18 6.19 7 7.54 36 10.6 28 5.84 37 21.2 5 18.6 3 41.5 28 30.2 10 26.9 21 45.0 10 27.6 14 18.8 11 36.2 38 6.69 32 14.7 31 10.5 58 8.17 20 16.4 18 7.33 75
Layers++ [37]25.3 7.17 38 11.1 24 8.79 59 6.14 6 10.3 2 6.41 34 7.34 16 10.3 14 5.69 19 21.3 10 19.0 15 41.3 17 30.5 37 27.1 41 45.4 24 28.1 53 21.1 74 36.2 38 6.51 4 13.8 5 10.2 1 8.20 24 16.4 18 7.13 34
nLayers [57]27.1 7.15 36 10.4 11 8.81 64 6.44 12 11.4 9 6.42 35 7.23 8 9.30 1 5.65 14 21.4 15 19.1 18 41.5 28 30.7 72 27.4 82 45.6 50 28.0 43 20.8 66 36.2 38 6.54 9 13.6 2 10.3 6 8.07 11 16.3 15 6.91 5
Sparse-NonSparse [56]28.6 7.09 28 11.3 29 8.57 27 6.53 16 11.8 16 6.21 9 7.40 24 10.5 24 5.64 10 21.5 20 19.0 15 41.7 45 30.4 27 27.0 30 45.4 24 28.3 65 21.5 84 36.4 61 6.66 24 14.4 22 10.3 6 8.23 28 16.6 29 7.09 24
ProbFlowFields [128]29.4 7.03 20 11.8 52 8.66 40 6.41 10 11.7 13 6.31 22 7.18 5 10.3 14 5.58 7 21.7 32 19.6 31 41.8 53 30.7 72 27.1 41 46.0 107 27.9 34 20.5 54 36.2 38 6.51 4 13.8 5 10.3 6 7.80 4 15.6 5 7.14 36
2DHMM-SAS [92]29.4 7.27 50 12.0 59 8.59 30 7.82 64 14.2 55 6.36 29 7.25 9 10.5 24 5.74 25 21.4 15 18.7 6 41.4 24 30.3 20 26.9 21 45.2 15 27.9 34 20.3 47 36.0 18 6.64 22 14.4 22 10.3 6 8.41 46 17.0 44 7.08 21
AGIF+OF [85]30.5 7.11 31 11.3 29 8.46 13 6.68 25 12.2 22 6.27 16 7.38 21 10.1 11 5.71 23 21.2 5 18.6 3 41.1 3 30.8 84 27.6 103 45.4 24 28.3 65 22.2 105 36.0 18 6.67 25 14.0 12 10.3 6 8.34 38 17.0 44 6.91 5
NNF-EAC [103]30.5 7.35 58 11.1 24 8.79 59 6.92 37 12.5 30 6.29 20 7.52 35 10.1 11 5.76 28 21.8 39 19.5 29 42.8 102 30.2 10 26.6 9 45.4 24 27.5 7 18.9 13 36.0 18 6.58 13 14.2 16 10.4 32 8.32 35 16.8 33 7.19 49
FlowFields [110]30.9 7.02 19 11.5 37 8.54 25 6.66 24 12.5 30 6.44 39 7.45 28 11.5 55 5.64 10 21.9 47 20.5 65 41.8 53 30.6 53 27.0 30 45.5 40 27.7 17 20.2 45 36.0 18 6.59 14 14.3 20 10.4 32 8.00 8 16.2 12 7.08 21
FMOF [94]31.4 7.36 60 12.0 59 8.73 50 6.42 11 11.3 8 6.30 21 7.63 49 10.4 19 6.02 65 21.8 39 19.9 38 41.2 11 30.5 37 27.0 30 45.4 24 28.0 43 20.5 54 36.1 31 6.51 4 13.8 5 10.2 1 8.30 33 16.7 32 7.12 30
FlowFields+ [130]31.6 6.99 16 11.4 35 8.47 15 6.61 20 12.3 24 6.48 42 7.42 26 11.5 55 5.67 17 21.7 32 20.3 53 41.6 35 30.7 72 27.2 56 45.6 50 27.8 27 20.3 47 36.1 31 6.61 16 14.4 22 10.4 32 7.99 7 16.2 12 7.03 16
S2F-IF [123]32.2 7.01 18 11.5 37 8.48 16 6.57 17 12.2 22 6.42 35 7.40 24 11.2 51 5.64 10 21.6 24 20.1 45 41.3 17 30.7 72 27.3 70 45.7 61 27.8 27 20.4 51 36.1 31 6.71 37 14.9 46 10.4 32 7.98 6 16.1 7 7.04 18
LSM [39]33.7 7.17 38 11.8 52 8.58 29 6.64 21 12.1 21 6.17 6 7.49 31 10.9 41 5.69 19 21.6 24 19.6 31 41.6 35 30.5 37 27.1 41 45.4 24 28.3 65 21.6 85 36.3 52 6.68 30 14.6 27 10.2 1 8.35 41 16.9 42 7.03 16
LME [70]34.2 6.72 3 9.86 5 8.36 5 6.97 39 12.4 27 7.40 86 7.51 33 11.8 63 5.70 22 21.3 10 19.2 21 41.3 17 31.0 107 27.6 103 46.6 119 27.8 27 20.5 54 36.0 18 6.45 1 13.6 2 10.2 1 8.08 13 16.3 15 7.12 30
WLIF-Flow [93]35.4 6.99 16 11.0 21 8.48 16 6.76 27 12.4 27 6.39 32 7.38 21 10.3 14 5.68 18 21.4 15 18.8 9 41.9 66 30.4 27 26.9 21 45.9 96 28.8 99 21.9 94 36.9 95 6.56 10 13.9 10 10.3 6 8.34 38 16.8 33 7.15 39
TV-L1-MCT [64]35.5 7.50 79 12.5 86 8.79 59 7.19 44 13.4 44 6.37 31 7.28 11 10.6 28 5.80 31 21.4 15 18.8 9 41.3 17 30.5 37 27.1 41 45.1 13 27.9 34 18.6 8 36.6 76 6.72 41 15.0 54 10.4 32 7.92 5 15.9 6 7.20 52
ComponentFusion [96]35.6 6.91 12 10.8 14 8.55 26 6.49 15 12.0 18 6.10 1 7.49 31 11.2 51 5.72 24 21.3 10 19.4 24 41.2 11 30.6 53 27.2 56 45.8 77 27.8 27 19.6 30 36.2 38 6.92 74 16.4 94 10.4 32 8.43 50 17.0 44 7.16 43
COFM [59]36.5 7.04 21 10.7 13 8.70 44 6.60 18 11.9 17 6.35 26 7.26 10 9.93 9 5.63 9 21.2 5 18.8 9 41.0 1 30.4 27 27.3 70 44.9 9 27.7 17 22.6 108 35.1 2 6.86 67 14.7 31 11.2 113 8.67 77 17.2 61 7.78 111
MDP-Flow [26]37.3 6.83 8 10.8 14 8.50 19 6.65 23 12.4 27 6.51 46 7.46 29 10.6 28 5.88 45 22.1 65 20.6 70 41.7 45 30.4 27 26.8 16 45.6 50 28.2 62 21.9 94 36.3 52 6.69 32 14.8 40 10.4 32 8.15 16 16.6 29 7.10 26
HAST [109]38.6 6.97 15 10.2 8 8.69 42 6.46 13 11.6 12 6.26 15 7.72 61 11.1 47 5.97 57 21.1 1 18.7 6 41.1 3 30.5 37 27.5 89 44.8 7 28.2 62 22.8 114 35.5 5 6.76 51 15.2 62 10.4 32 8.81 84 18.0 93 6.96 10
RNLOD-Flow [121]38.8 7.12 33 11.5 37 8.64 37 7.38 50 14.0 51 6.35 26 7.55 37 11.2 51 5.83 36 21.3 10 19.0 15 41.1 3 30.5 37 27.2 56 45.4 24 28.3 65 21.6 85 36.2 38 6.62 17 14.2 16 10.4 32 8.70 80 17.7 81 7.02 14
OFLAF [77]39.2 6.81 7 10.2 8 8.40 10 6.10 3 10.7 6 6.21 9 7.36 18 10.6 28 5.54 5 21.1 1 18.8 9 41.0 1 30.8 84 27.4 82 45.7 61 28.1 53 21.9 94 36.0 18 7.02 85 16.1 90 10.4 32 8.90 92 18.1 101 7.16 43
Ramp [62]41.5 7.31 56 12.1 63 8.78 56 6.60 18 12.0 18 6.27 16 7.36 18 10.4 19 5.65 14 21.3 10 18.9 14 41.4 24 30.5 37 27.1 41 45.4 24 28.7 94 22.3 106 36.6 76 6.73 47 14.9 46 10.3 6 8.55 64 17.3 66 7.26 63
Second-order prior [8]42.7 7.30 55 11.3 29 8.90 73 8.52 83 15.6 83 6.74 61 8.32 98 13.6 107 6.42 91 21.8 39 20.0 41 41.5 28 30.1 6 26.5 4 45.5 40 27.5 7 19.0 14 36.0 18 6.67 25 14.6 27 10.3 6 8.25 29 16.8 33 7.11 28
PGM-C [120]43.5 7.19 43 12.1 63 8.72 47 6.82 29 12.9 34 6.62 52 7.67 57 12.2 74 5.78 30 21.9 47 20.9 79 41.8 53 30.6 53 27.1 41 45.8 77 27.7 17 19.5 27 36.2 38 6.65 23 14.7 31 10.3 6 8.20 24 16.6 29 7.31 70
DeepFlow2 [108]44.4 7.28 51 11.3 29 8.88 70 7.68 59 14.4 62 6.94 74 7.58 42 12.3 78 5.88 45 21.9 47 20.2 49 41.7 45 30.5 37 26.8 16 45.9 96 27.5 7 18.0 4 36.4 61 6.67 25 14.6 27 10.4 32 8.18 21 16.4 18 7.31 70
Classic+NL [31]44.5 7.44 73 12.3 74 8.86 67 6.78 28 12.3 24 6.28 18 7.32 15 10.4 19 5.69 19 21.6 24 19.4 24 41.8 53 30.5 37 27.1 41 45.5 40 28.6 89 21.8 90 36.6 76 6.72 41 14.7 31 10.3 6 8.50 58 17.2 61 7.24 60
Aniso. Huber-L1 [22]44.6 7.61 86 12.2 71 9.19 85 8.99 93 15.7 86 7.12 80 7.73 63 11.0 44 5.86 42 21.8 39 20.0 41 41.6 35 30.2 10 26.6 9 45.5 40 27.4 4 19.6 30 35.7 9 6.68 30 14.6 27 10.3 6 8.34 38 16.8 33 7.29 69
FC-2Layers-FF [74]44.7 7.22 46 11.9 57 8.70 44 6.10 3 10.2 1 6.47 41 7.31 14 10.5 24 5.64 10 21.4 15 19.1 18 41.6 35 30.7 72 27.5 89 45.6 50 28.6 89 22.7 111 36.4 61 6.77 53 15.0 54 10.3 6 8.57 66 17.2 61 7.20 52
SRR-TVOF-NL [91]45.7 7.42 71 11.5 37 8.86 67 7.79 61 14.8 70 7.08 78 7.62 46 11.5 55 5.85 40 21.7 32 19.6 31 41.1 3 30.3 20 27.1 41 45.2 15 27.5 7 20.5 54 35.3 4 6.72 41 14.8 40 10.4 32 8.97 99 18.3 107 7.17 46
DF-Auto [115]46.8 7.54 81 11.1 24 9.32 93 8.42 79 14.5 65 8.82 98 7.35 17 10.3 14 5.65 14 22.0 57 20.2 49 41.5 28 30.4 27 26.7 15 45.8 77 27.5 7 18.7 10 36.1 31 6.82 60 15.3 66 10.5 58 8.43 50 17.1 52 7.20 52
FESL [72]46.9 7.36 60 11.7 46 8.65 39 6.82 29 12.6 32 6.33 24 7.51 33 10.7 36 5.89 48 21.6 24 19.6 31 41.3 17 30.9 102 27.5 89 45.7 61 28.4 77 22.1 103 36.2 38 6.70 35 14.8 40 10.2 1 8.59 67 17.4 72 7.08 21
CPM-Flow [116]47.2 7.21 44 12.2 71 8.71 46 6.83 32 12.9 34 6.65 55 7.61 45 11.7 60 5.88 45 22.2 71 21.4 98 41.8 53 30.6 53 27.1 41 45.8 77 27.9 34 19.1 15 36.6 76 6.67 25 14.7 31 10.3 6 8.16 18 16.5 24 7.34 78
Classic+CPF [83]47.6 7.22 46 11.6 42 8.52 24 6.90 36 12.6 32 6.28 18 7.37 20 10.6 28 5.76 28 21.2 5 18.7 6 41.1 3 31.1 112 27.9 111 45.5 40 28.7 94 23.1 118 36.3 52 6.92 74 15.3 66 10.3 6 8.75 82 17.9 89 6.99 11
S2D-Matching [84]49.3 7.37 63 12.3 74 8.80 62 7.62 58 14.2 55 6.43 38 7.28 11 10.4 19 5.74 25 21.6 24 19.1 18 42.2 81 30.6 53 27.3 70 45.4 24 28.6 89 22.5 107 36.4 61 6.76 51 14.5 25 10.3 6 8.46 53 17.0 44 7.32 72
IROF-TV [53]49.5 7.33 57 12.3 74 8.82 65 6.83 32 12.3 24 6.23 12 7.70 60 12.9 96 5.93 52 21.5 20 19.5 29 42.0 72 30.8 84 27.3 70 45.9 96 27.5 7 20.2 45 35.6 6 6.75 49 15.1 60 10.5 58 8.18 21 16.4 18 7.37 82
DeepFlow [86]49.6 7.21 44 11.0 21 8.88 70 7.79 61 14.3 58 7.33 85 7.64 51 12.6 87 5.95 54 22.1 65 20.1 45 42.0 72 30.6 53 26.8 16 46.1 110 28.0 43 17.9 3 37.2 102 6.57 11 14.1 13 10.4 32 8.07 11 16.2 12 7.32 72
EPPM w/o HM [88]50.1 6.77 6 10.4 11 8.32 3 7.00 40 13.4 44 6.16 5 8.19 91 13.6 107 6.26 79 21.7 32 20.3 53 41.5 28 30.5 37 27.2 56 45.5 40 28.5 83 21.8 90 36.5 70 6.84 61 15.6 76 10.6 84 8.41 46 17.1 52 6.95 9
Brox et al. [5]50.3 7.28 51 11.4 35 8.76 52 7.86 65 14.6 67 6.92 73 8.03 81 13.1 98 6.34 85 21.9 47 19.9 38 41.4 24 30.6 53 27.0 30 45.8 77 27.7 17 19.5 27 36.2 38 6.80 56 15.4 71 10.4 32 8.16 18 16.5 24 7.19 49
p-harmonic [29]50.4 7.04 21 11.3 29 8.62 35 8.81 87 15.8 89 6.98 75 7.76 66 13.1 98 6.18 76 22.4 83 20.7 73 41.9 66 30.5 37 27.0 30 45.5 40 27.8 27 19.2 19 36.4 61 6.71 37 15.1 60 10.3 6 8.29 32 16.8 33 7.12 30
Efficient-NL [60]51.0 7.28 51 11.6 42 8.61 34 7.24 47 13.3 43 6.35 26 8.21 93 10.8 38 6.39 90 21.7 32 19.6 31 41.2 11 30.4 27 27.0 30 45.3 20 28.3 65 22.8 114 35.6 6 6.86 67 15.6 76 10.4 32 9.10 106 18.3 107 7.14 36
SepConv-v1 [127]51.5 4.07 1 8.88 1 4.61 1 6.87 34 13.0 38 7.47 87 6.42 1 9.58 5 9.25 128 23.4 109 20.0 41 44.0 113 30.2 10 26.3 3 45.7 61 27.9 34 16.5 2 37.4 108 7.61 116 15.6 76 12.9 132 7.71 3 13.8 2 9.78 131
SuperSlomo [132]53.7 6.74 4 9.03 2 8.40 10 9.03 95 13.1 40 12.7 126 8.09 88 10.5 24 9.15 126 22.7 93 18.4 1 43.7 111 28.3 1 24.4 1 44.1 2 28.5 83 15.3 1 38.7 123 7.11 90 12.9 1 12.9 132 7.43 1 13.2 1 9.86 132
EpicFlow [102]54.1 7.18 40 12.0 59 8.72 47 7.42 52 14.4 62 6.72 60 7.68 58 12.1 71 5.92 51 22.1 65 21.1 89 42.0 72 30.7 72 27.1 41 45.8 77 27.5 7 19.9 41 35.9 13 6.79 55 15.2 62 10.4 32 8.40 45 17.1 52 7.33 75
DPOF [18]54.5 7.58 85 13.2 104 9.07 76 6.27 7 11.0 7 6.54 48 8.10 89 10.6 28 6.27 81 22.0 57 20.5 65 41.9 66 30.2 10 26.8 16 45.4 24 28.0 43 21.2 76 35.8 12 6.84 61 15.0 54 10.7 94 8.62 71 17.4 72 7.26 63
PMF [73]55.0 6.83 8 10.3 10 8.37 7 6.96 38 13.1 40 6.19 7 7.86 71 13.1 98 6.03 66 21.5 20 19.4 24 41.3 17 31.0 107 27.7 107 45.8 77 28.7 94 20.5 54 37.2 102 6.80 56 15.0 54 10.5 58 8.87 88 18.2 104 7.00 12
ComplOF-FED-GPU [35]55.8 7.23 48 11.8 52 8.72 47 7.20 45 13.9 48 6.62 52 8.43 101 12.6 87 6.45 92 21.9 47 20.8 78 42.3 83 30.4 27 26.9 21 45.4 24 27.7 17 20.1 44 36.1 31 6.86 67 15.4 71 10.5 58 8.55 64 17.3 66 7.28 68
Sparse Occlusion [54]56.8 7.37 63 12.3 74 8.87 69 8.04 69 15.3 77 6.48 42 7.58 42 10.8 38 5.87 43 22.0 57 20.4 59 41.5 28 30.6 53 27.2 56 45.5 40 28.3 65 21.8 90 36.4 61 6.80 56 15.3 66 10.3 6 8.74 81 17.7 81 7.18 48
TC/T-Flow [76]57.1 7.37 63 11.8 52 8.59 30 7.31 48 14.0 51 6.42 35 7.47 30 11.1 47 5.81 32 21.8 39 20.5 65 41.7 45 30.8 84 27.5 89 45.7 61 28.1 53 20.9 67 36.2 38 7.03 87 16.0 88 10.6 84 8.62 71 17.6 78 7.13 34
AggregFlow [97]58.8 7.71 92 12.6 88 9.11 78 7.50 55 13.9 48 7.06 76 7.19 7 9.98 10 5.53 4 21.9 47 20.4 59 41.6 35 30.8 84 27.3 70 46.1 110 29.0 103 19.7 37 37.9 116 6.75 49 14.7 31 10.5 58 8.32 35 16.8 33 7.40 86
CLG-TV [48]59.0 7.52 80 12.3 74 9.14 80 8.67 85 15.8 89 7.11 79 7.97 78 12.7 91 6.26 79 22.1 65 20.3 53 42.0 72 30.5 37 26.9 21 45.7 61 27.6 14 19.1 15 36.2 38 6.71 37 14.9 46 10.4 32 8.53 63 17.3 66 7.24 60
SuperFlow [81]59.0 7.43 72 11.5 37 9.30 90 8.55 84 14.8 70 9.15 102 7.91 75 12.0 68 6.31 82 22.1 65 19.9 38 42.0 72 30.7 72 27.2 56 45.9 96 27.3 2 18.4 7 35.9 13 6.86 67 15.8 82 10.6 84 8.15 16 16.5 24 7.16 43
RFlow [90]59.4 7.24 49 12.1 63 8.90 73 8.42 79 15.6 83 6.49 44 7.72 61 12.2 74 6.01 64 22.0 57 20.6 70 41.7 45 30.4 27 27.1 41 45.7 61 27.4 4 19.8 40 35.6 6 6.84 61 15.9 86 10.5 58 8.91 95 18.0 93 7.47 91
SIOF [67]60.0 7.66 89 12.6 88 9.09 77 9.45 102 16.6 102 8.48 94 7.65 53 11.9 66 5.98 58 21.9 47 20.1 45 41.8 53 30.0 4 26.5 4 45.3 20 28.1 53 19.7 37 36.6 76 6.63 20 14.7 31 10.5 58 8.82 85 17.9 89 7.46 88
TCOF [69]60.2 7.36 60 12.1 63 8.68 41 9.41 101 16.6 102 7.17 82 7.38 21 10.7 36 5.61 8 21.8 39 20.4 59 41.8 53 30.4 27 27.0 30 45.6 50 28.1 53 21.8 90 35.9 13 6.85 64 15.7 81 10.4 32 9.30 115 19.0 119 7.61 105
TC-Flow [46]60.6 7.18 40 11.8 52 8.78 56 7.46 54 14.6 67 6.77 65 7.86 71 12.6 87 5.89 48 21.8 39 20.3 53 41.9 66 30.7 72 27.4 82 45.7 61 28.3 65 21.0 70 36.6 76 6.73 47 14.8 40 10.5 58 8.51 59 17.3 66 7.24 60
IAOF [50]60.7 8.70 113 12.9 97 10.3 111 12.4 125 19.2 129 9.77 113 7.74 64 12.0 68 6.21 77 22.8 94 20.2 49 42.0 72 30.2 10 26.5 4 45.5 40 27.7 17 19.6 30 36.1 31 6.67 25 15.0 54 10.3 6 8.41 46 17.1 52 7.12 30
3DFlow [135]61.1 7.09 28 11.7 46 8.46 13 6.89 35 13.0 38 6.39 32 8.03 81 10.6 28 5.98 58 21.6 24 19.3 22 41.9 66 30.8 84 27.1 41 47.6 125 29.0 103 23.9 125 36.4 61 7.05 88 16.2 91 10.5 58 8.83 87 18.0 93 7.15 39
OAR-Flow [125]61.9 7.45 75 11.7 46 8.98 75 7.57 57 14.4 62 6.91 72 7.62 46 12.4 81 5.82 34 21.6 24 20.3 53 41.6 35 30.9 102 27.5 89 45.8 77 28.0 43 20.5 54 36.4 61 6.97 82 15.6 76 10.5 58 8.46 53 17.1 52 7.34 78
ALD-Flow [66]63.9 7.54 81 12.1 63 9.14 80 7.43 53 14.3 58 6.85 69 7.66 56 12.5 84 5.87 43 21.8 39 20.4 59 42.3 83 30.8 84 27.4 82 45.9 96 28.1 53 19.9 41 36.6 76 6.62 17 14.2 16 10.5 58 8.68 78 17.5 77 7.46 88
OFH [38]64.6 7.39 68 12.1 63 8.88 70 8.07 70 15.0 75 6.66 57 8.03 81 13.8 110 5.96 56 21.9 47 21.1 89 42.1 78 30.5 37 27.3 70 45.4 24 27.8 27 20.4 51 36.2 38 7.11 90 16.4 94 10.5 58 8.61 70 17.6 78 7.19 49
SVFilterOh [111]65.0 7.18 40 10.9 18 8.76 52 6.48 14 11.7 13 6.45 40 7.62 46 10.2 13 5.99 61 21.7 32 19.4 24 42.5 93 31.3 116 28.0 116 46.6 119 28.6 89 22.0 99 36.5 70 6.92 74 14.1 13 11.4 118 8.97 99 17.8 86 8.09 116
MLDP_OF [89]66.5 7.10 30 11.2 28 8.64 37 7.33 49 13.7 46 6.31 22 7.44 27 10.9 41 5.75 27 22.0 57 19.8 37 42.3 83 30.6 53 27.3 70 46.2 116 31.0 129 22.6 108 40.0 129 6.93 77 15.2 62 11.0 107 8.65 75 17.4 72 7.79 113
CostFilter [40]66.8 6.91 12 11.1 24 8.37 7 6.82 29 12.9 34 6.25 14 7.99 79 13.9 111 6.10 69 21.9 47 20.6 70 41.7 45 31.1 112 27.9 111 45.9 96 29.8 117 20.3 47 39.1 125 6.94 79 15.8 82 10.6 84 8.82 85 18.1 101 7.09 24
Modified CLG [34]67.5 7.63 87 11.6 42 9.65 96 10.7 113 17.2 110 10.7 117 8.25 95 14.3 116 6.60 98 22.4 83 21.1 89 41.8 53 30.6 53 26.9 21 45.8 77 27.7 17 19.2 19 36.3 52 6.69 32 14.9 46 10.4 32 8.41 46 17.0 44 7.35 81
Fusion [6]67.8 7.13 35 12.3 74 8.60 33 7.18 43 13.1 40 6.56 49 7.63 49 10.9 41 6.13 73 22.5 89 21.1 89 41.5 28 30.7 72 28.2 119 44.3 3 28.1 53 23.8 123 35.2 3 7.22 100 17.9 108 10.6 84 9.64 122 19.9 126 7.32 72
F-TV-L1 [15]68.5 8.24 103 13.1 101 9.92 103 9.28 97 16.3 97 7.48 88 8.00 80 13.2 103 6.35 87 22.3 77 20.9 79 42.3 83 29.9 3 26.9 21 44.8 7 27.9 34 19.4 24 36.5 70 6.87 71 15.4 71 10.5 58 8.46 53 16.8 33 7.58 101
IIOF-NLDP [131]69.0 7.04 21 10.9 18 8.36 5 7.81 63 14.8 70 6.64 54 8.07 87 11.0 44 6.12 70 22.3 77 20.0 41 42.8 102 30.4 27 27.0 30 45.9 96 29.1 109 23.2 119 36.5 70 8.40 132 24.6 133 11.3 115 8.78 83 17.8 86 6.86 3
EPMNet [133]69.2 9.02 115 14.8 121 10.2 109 8.29 75 14.1 54 8.78 97 8.03 81 12.5 84 6.15 75 22.8 94 23.9 125 41.7 45 30.9 102 27.5 89 45.8 77 28.0 43 21.4 81 35.9 13 6.72 41 14.9 46 10.4 32 8.21 26 16.8 33 6.83 2
FlowNet2 [122]69.2 9.30 117 14.6 118 10.5 114 8.42 79 14.6 67 9.24 106 8.03 81 12.5 84 6.14 74 22.2 71 21.9 107 41.8 53 30.9 102 27.5 89 45.8 77 28.0 43 20.5 54 36.0 18 6.72 41 14.9 46 10.4 32 8.31 34 16.9 42 7.01 13
Complementary OF [21]70.5 7.11 31 12.1 63 8.50 19 7.17 42 14.0 51 6.58 51 8.76 110 12.0 68 6.55 95 22.3 77 21.4 98 42.6 99 30.6 53 27.5 89 45.2 15 28.1 53 20.9 67 36.4 61 7.15 94 16.7 98 10.5 58 9.09 104 18.7 114 7.38 83
SimpleFlow [49]70.9 7.37 63 12.4 83 8.74 51 7.88 66 14.3 58 6.50 45 8.59 106 11.5 55 6.51 93 21.6 24 19.3 22 41.8 53 30.6 53 27.3 70 45.5 40 28.5 83 22.9 116 36.2 38 7.66 119 20.5 127 10.8 102 8.89 91 18.2 104 7.15 39
LDOF [28]71.3 8.08 98 12.3 74 9.79 101 8.94 91 14.9 73 9.18 104 8.23 94 13.5 106 6.52 94 22.3 77 21.1 89 42.4 91 30.6 53 27.0 30 45.8 77 27.9 34 18.8 11 36.6 76 6.77 53 15.3 66 10.4 32 8.44 52 17.1 52 7.38 83
TF+OM [100]72.0 7.41 69 12.1 63 9.19 85 7.21 46 12.9 34 7.83 89 7.55 37 12.3 78 5.82 34 22.2 71 21.0 85 41.9 66 30.8 84 27.5 89 46.0 107 28.3 65 20.5 54 36.8 90 6.97 82 16.3 92 10.5 58 8.65 75 17.3 66 7.75 109
ROF-ND [107]72.2 7.46 76 11.0 21 8.77 54 7.96 67 15.4 78 6.76 64 7.55 37 11.0 44 5.85 40 23.3 106 23.5 124 41.6 35 30.6 53 27.1 41 45.8 77 28.3 65 22.7 111 35.9 13 7.52 113 17.5 104 11.4 118 9.25 113 18.7 114 7.27 65
Local-TV-L1 [65]72.8 8.46 109 12.6 88 10.4 112 9.68 104 16.0 95 8.93 100 7.56 41 11.2 51 5.84 37 23.1 102 20.4 59 46.0 125 30.6 53 27.1 41 45.9 96 30.1 122 19.1 15 39.9 128 6.72 41 14.9 46 10.5 58 8.13 15 16.1 7 7.58 101
TriFlow [95]73.0 7.77 94 13.7 113 9.28 88 8.98 92 15.7 86 9.30 108 7.65 53 12.4 81 5.84 37 22.0 57 20.9 79 41.1 3 30.9 102 27.7 107 45.7 61 28.4 77 21.3 80 36.3 52 6.85 64 15.5 75 10.4 32 8.69 79 17.4 72 7.23 59
Classic++ [32]73.7 7.49 78 12.5 86 9.11 78 8.07 70 15.2 76 6.67 58 7.89 74 12.6 87 6.04 67 22.3 77 20.7 73 42.2 81 30.6 53 27.2 56 45.7 61 29.0 103 21.0 70 37.6 111 6.81 59 15.2 62 10.5 58 8.62 71 17.4 72 7.46 88
Occlusion-TV-L1 [63]74.0 7.44 73 12.3 74 9.14 80 8.91 90 16.5 100 6.85 69 7.83 69 12.8 93 6.32 83 22.6 92 21.5 102 42.5 93 30.5 37 26.9 21 45.8 77 28.4 77 19.6 30 37.1 99 7.15 94 14.8 40 10.7 94 8.51 59 17.1 52 7.34 78
2D-CLG [1]74.7 8.44 107 12.3 74 10.6 116 11.9 121 18.0 120 12.3 124 8.94 113 13.9 111 7.33 115 23.1 102 21.2 96 41.3 17 30.5 37 26.9 21 45.8 77 27.6 14 19.2 19 36.2 38 7.14 92 17.2 102 10.5 58 8.37 43 16.5 24 7.20 52
Nguyen [33]74.8 9.74 121 12.6 88 12.4 125 12.3 123 18.6 125 11.1 118 8.27 97 14.8 118 6.69 100 23.4 109 21.7 104 41.8 53 30.3 20 26.8 16 45.3 20 27.4 4 19.6 30 35.7 9 7.24 102 18.3 111 10.5 58 8.37 43 17.0 44 7.22 58
FlowNetS+ft+v [112]75.5 7.81 96 11.7 46 9.63 95 9.77 106 16.8 104 9.16 103 8.06 86 13.4 105 6.36 88 22.1 65 20.7 73 42.1 78 30.8 84 27.4 82 45.8 77 27.7 17 19.4 24 36.3 52 7.01 84 16.4 94 10.5 58 8.51 59 17.2 61 7.33 75
Aniso-Texture [82]76.3 7.16 37 11.6 42 8.78 56 8.84 88 16.5 100 6.86 71 8.38 100 11.8 63 5.99 61 22.4 83 21.4 98 42.5 93 31.0 107 27.5 89 46.0 107 29.0 103 24.2 127 36.7 85 6.70 35 14.7 31 10.3 6 8.90 92 18.0 93 7.27 65
Shiralkar [42]76.6 7.48 77 12.8 95 8.80 62 9.00 94 15.8 89 6.65 55 8.52 104 16.1 122 6.84 104 23.4 109 22.3 111 41.6 35 30.0 4 27.0 30 44.5 4 28.7 94 21.1 74 37.1 99 7.49 111 18.7 119 10.6 84 8.64 74 17.7 81 6.93 7
Adaptive [20]77.1 7.71 92 13.2 104 9.21 87 9.40 100 16.8 104 7.07 77 7.87 73 12.4 81 6.12 70 22.0 57 20.3 53 41.8 53 30.7 72 27.3 70 45.6 50 28.4 77 20.7 65 36.8 90 6.95 81 16.0 88 10.4 32 8.87 88 17.9 89 7.55 98
CNN-flow-warp+ref [117]79.8 7.35 58 10.8 14 9.30 90 8.87 89 16.2 96 8.14 93 8.60 107 14.1 114 6.62 99 23.7 113 21.9 107 42.7 100 30.8 84 27.3 70 45.9 96 28.0 43 19.1 15 36.7 85 7.37 106 18.5 116 10.6 84 8.33 37 16.8 33 7.27 65
CRTflow [80]80.1 7.69 90 12.6 88 9.28 88 8.45 82 15.5 80 6.81 67 8.55 105 14.0 113 7.29 113 22.4 83 20.7 73 43.8 112 30.7 72 27.2 56 45.7 61 28.1 53 19.6 30 36.7 85 6.87 71 15.8 82 10.6 84 8.59 67 17.2 61 7.65 106
Black & Anandan [4]80.2 8.54 110 12.8 95 10.2 109 10.9 115 17.3 113 9.40 109 9.06 115 13.6 107 6.99 108 22.9 99 21.3 97 41.7 45 30.7 72 27.2 56 45.9 96 28.0 43 18.6 8 36.7 85 6.93 77 15.9 86 10.4 32 8.46 53 17.0 44 7.20 52
HBpMotionGpu [43]81.0 9.39 119 14.6 118 11.3 121 11.7 120 18.9 127 11.5 121 7.55 37 11.1 47 6.00 63 23.3 106 22.3 111 43.5 110 30.3 20 27.2 56 45.2 15 28.7 94 20.9 67 37.1 99 6.62 17 14.2 16 10.5 58 8.99 101 17.8 86 8.04 115
StereoOF-V1MT [119]81.5 7.65 88 13.5 110 8.77 54 8.69 86 15.9 94 6.52 47 9.43 120 15.4 120 7.23 111 24.4 119 22.3 111 43.2 108 30.5 37 27.2 56 45.0 10 28.9 101 21.2 76 37.2 102 7.77 122 19.4 122 11.0 107 8.26 31 16.4 18 6.93 7
GraphCuts [14]81.6 8.65 112 14.1 117 9.83 102 8.28 74 14.2 55 9.28 107 9.89 124 10.6 28 7.38 116 23.0 100 21.1 89 42.5 93 30.3 20 27.3 70 44.7 6 27.2 1 21.4 81 34.7 1 7.42 109 17.8 106 11.0 107 9.32 116 18.9 117 7.66 107
HBM-GC [105]82.8 7.91 97 12.6 88 9.75 99 7.51 56 13.9 48 6.80 66 7.29 13 9.43 2 5.94 53 22.0 57 19.7 36 42.3 83 32.1 126 28.6 123 48.0 127 30.0 119 24.6 130 37.8 113 7.14 92 14.8 40 11.6 121 8.95 98 17.7 81 8.28 118
CBF [12]83.0 7.41 69 11.9 57 9.31 92 8.07 70 14.9 73 7.14 81 7.69 59 11.1 47 5.95 54 22.8 94 20.7 73 45.1 121 30.8 84 27.3 70 47.0 123 28.2 62 20.6 62 36.5 70 7.17 97 16.6 97 11.2 113 9.16 110 17.9 89 8.83 125
Steered-L1 [118]83.2 7.06 26 12.2 71 8.59 30 7.40 51 14.3 58 6.83 68 8.48 103 11.7 60 6.69 100 22.8 94 20.9 79 42.7 100 31.2 115 28.1 117 45.8 77 28.3 65 21.2 76 36.7 85 7.25 103 17.8 106 10.9 103 9.00 102 18.3 107 7.58 101
TriangleFlow [30]83.3 7.79 95 13.0 100 9.16 84 8.36 78 15.5 80 6.69 59 8.20 92 11.9 66 6.59 96 22.5 89 21.0 85 42.5 93 30.1 6 27.0 30 45.0 10 28.9 101 22.6 108 36.5 70 7.42 109 18.3 111 11.0 107 9.49 119 19.3 121 7.47 91
Correlation Flow [75]83.8 7.05 24 11.7 46 8.32 3 8.29 75 15.6 83 6.56 49 7.64 51 10.8 38 5.89 48 22.2 71 20.1 45 42.9 106 31.7 120 27.7 107 49.9 132 29.6 113 23.8 123 37.2 102 7.62 117 19.0 121 11.3 115 9.22 112 18.6 113 7.51 97
IAOF2 [51]85.5 8.43 106 13.6 112 9.76 100 9.86 108 17.4 114 8.67 95 7.74 64 12.2 74 6.33 84 23.1 102 21.7 104 42.3 83 31.0 107 27.9 111 45.6 50 28.5 83 21.0 70 36.6 76 6.71 37 15.0 54 10.3 6 9.14 108 18.4 110 7.49 95
BriefMatch [124]87.7 7.38 67 12.0 59 8.85 66 7.71 60 14.5 65 7.86 90 8.77 111 11.7 60 7.25 112 24.2 117 22.0 109 46.2 126 30.8 84 27.4 82 46.1 110 31.8 132 21.7 87 41.3 132 6.85 64 15.3 66 10.7 94 8.51 59 17.1 52 7.56 100
SegOF [10]89.2 8.16 101 12.4 83 10.1 108 9.10 96 15.5 80 8.83 99 9.48 121 14.1 114 7.46 118 22.8 94 23.0 122 41.6 35 30.8 84 27.4 82 45.8 77 28.3 65 22.0 99 36.3 52 7.83 123 21.5 129 11.0 107 8.46 53 17.1 52 7.17 46
TV-L1-improved [17]90.5 7.55 83 12.9 97 9.15 83 9.36 98 16.9 106 7.19 83 8.63 108 12.2 74 6.92 106 22.2 71 21.0 85 42.3 83 30.8 84 27.5 89 45.6 50 28.5 83 21.4 81 36.8 90 7.38 107 18.6 118 10.7 94 8.94 96 18.0 93 7.75 109
BlockOverlap [61]90.5 8.81 114 12.4 83 11.1 120 10.0 110 15.8 89 10.6 116 7.84 70 10.4 19 6.59 96 23.3 106 20.4 59 46.3 127 31.9 123 27.9 111 48.8 130 30.3 125 19.7 37 39.8 127 7.08 89 14.5 25 11.7 124 8.35 41 16.1 7 8.60 123
OFRF [134]91.2 9.30 117 13.4 109 11.0 119 9.59 103 15.7 86 9.07 101 7.92 76 12.7 91 6.05 68 22.3 77 20.2 49 42.8 102 31.0 107 27.9 111 45.4 24 29.6 113 23.3 120 37.4 108 7.34 104 17.7 105 10.5 58 9.09 104 18.8 116 7.05 20
Dynamic MRF [7]91.4 7.29 54 13.1 101 8.69 42 8.20 73 16.3 97 6.74 61 9.18 117 16.4 125 7.22 110 24.5 121 23.1 123 44.4 115 30.3 20 27.2 56 45.1 13 29.2 110 23.4 121 37.2 102 7.64 118 19.8 125 10.7 94 9.14 108 18.0 93 7.48 94
LocallyOriented [52]92.1 8.08 98 13.1 101 9.72 97 9.73 105 17.0 108 7.88 91 8.34 99 12.8 93 6.34 85 23.0 100 22.1 110 43.0 107 30.6 53 27.2 56 45.6 50 30.0 119 21.9 94 38.5 122 7.02 85 15.8 82 10.5 58 9.05 103 18.4 110 7.39 85
AdaConv-v1 [126]92.2 9.81 123 13.9 115 11.6 123 12.1 122 17.6 116 16.0 131 11.4 131 16.1 122 13.1 133 26.5 130 24.4 130 45.3 122 28.4 2 24.4 1 44.6 5 28.4 77 18.1 5 37.7 112 7.74 121 16.3 92 13.1 134 8.25 29 15.1 3 10.1 133
SPSA-learn [13]92.9 8.28 104 12.9 97 9.95 105 9.92 109 16.3 97 9.49 110 9.15 116 12.8 93 7.30 114 23.1 102 20.5 65 41.6 35 30.8 84 27.5 89 45.7 61 28.0 43 20.4 51 36.3 52 8.81 134 27.1 135 11.8 125 10.0 127 21.0 130 7.20 52
Rannacher [23]93.2 7.69 90 13.2 104 9.32 93 9.37 99 16.9 106 7.28 84 8.67 109 13.0 97 6.91 105 22.2 71 21.1 89 42.4 91 30.8 84 27.5 89 45.7 61 28.5 83 21.2 76 36.9 95 7.35 105 18.5 116 10.7 94 8.90 92 18.0 93 7.78 111
Ad-TV-NDC [36]94.0 10.8 126 13.9 115 13.4 126 11.6 119 17.6 116 11.2 119 7.77 67 12.3 78 6.12 70 24.0 115 21.6 103 44.4 115 31.1 112 27.6 103 46.1 110 29.0 103 19.3 23 38.0 117 6.87 71 15.4 71 10.5 58 8.59 67 17.0 44 7.71 108
ACK-Prior [27]95.3 7.12 33 11.7 46 8.57 27 7.08 41 13.8 47 6.34 25 8.81 112 11.8 63 6.69 100 22.5 89 21.4 98 42.3 83 32.6 130 29.3 129 48.2 128 30.7 128 25.6 132 38.1 119 7.95 126 18.8 120 12.0 126 10.8 132 21.8 132 8.53 122
Horn & Schunck [3]95.7 8.45 108 13.3 108 10.0 106 11.4 118 18.1 122 9.84 114 9.65 122 16.1 122 7.89 121 24.6 122 22.8 116 42.8 102 30.6 53 27.2 56 45.6 50 28.3 65 19.4 24 36.8 90 7.41 108 18.0 110 10.6 84 8.94 96 17.7 81 7.55 98
UnFlow [129]97.8 9.13 116 15.0 123 10.7 117 10.9 115 18.1 122 9.23 105 9.21 118 16.9 128 7.18 109 22.4 83 21.8 106 41.8 53 30.8 84 27.6 103 45.9 96 28.6 89 22.7 111 36.0 18 6.94 79 15.6 76 10.5 58 10.0 127 19.3 121 7.47 91
TI-DOFE [24]98.6 11.8 128 14.7 120 14.8 129 13.9 130 20.3 131 13.5 129 9.26 119 16.5 127 7.69 120 25.1 124 22.8 116 43.3 109 30.2 10 27.1 41 45.4 24 28.4 77 19.6 30 36.8 90 7.22 100 17.2 102 10.7 94 9.21 111 18.1 101 7.59 104
StereoFlow [44]98.6 13.8 131 20.2 134 14.0 127 14.1 131 21.3 134 12.0 123 7.79 68 13.3 104 5.98 58 22.4 83 20.9 79 42.1 78 33.7 134 32.3 134 46.1 110 30.5 126 31.8 135 36.3 52 6.63 20 14.7 31 10.4 32 9.98 126 21.0 130 7.42 87
Filter Flow [19]103.8 8.30 105 13.2 104 10.0 106 10.8 114 17.1 109 11.7 122 7.96 77 12.1 71 6.38 89 23.7 113 20.9 79 44.5 119 31.5 119 28.2 119 46.7 121 28.8 99 21.0 70 37.3 107 7.15 94 17.0 101 10.7 94 9.54 121 18.9 117 8.47 121
NL-TV-NCC [25]106.3 7.56 84 12.7 94 8.62 35 8.00 68 15.4 78 6.74 61 8.46 102 13.1 98 6.70 103 24.2 117 24.0 128 45.0 120 32.8 131 28.3 122 52.0 135 29.4 111 24.1 126 36.9 95 7.89 125 17.9 108 12.4 130 10.1 129 19.9 126 8.92 126
Bartels [41]107.4 8.10 100 13.8 114 9.94 104 8.35 77 15.8 89 8.75 96 8.11 90 12.1 71 6.97 107 24.1 116 22.7 114 47.6 129 32.4 127 27.8 110 51.1 134 35.4 134 23.0 117 46.5 134 7.18 98 14.9 46 12.3 129 9.36 118 18.0 93 9.76 130
SILK [79]107.4 9.77 122 15.1 124 11.8 124 12.3 123 18.7 126 11.2 119 10.3 125 16.4 125 8.14 123 25.2 125 22.8 116 45.9 124 30.8 84 27.5 89 45.7 61 30.6 127 20.3 47 40.1 130 7.19 99 16.8 99 10.9 103 8.87 88 17.6 78 7.50 96
SLK [47]112.8 11.4 127 15.4 125 14.4 128 12.4 125 18.0 120 12.6 125 10.9 129 17.6 130 8.85 125 27.8 131 25.2 131 46.6 128 30.6 53 28.1 117 43.6 1 29.0 103 21.9 94 37.0 98 8.25 129 22.4 130 11.3 115 9.33 117 18.5 112 7.91 114
GroupFlow [9]113.7 10.1 125 16.9 129 11.3 121 10.4 112 17.8 119 10.0 115 10.8 128 17.5 129 9.21 127 23.6 112 23.9 125 42.5 93 31.9 123 29.3 129 46.2 116 30.1 122 24.5 129 37.8 113 7.55 114 18.4 114 10.6 84 9.52 120 19.8 125 6.89 4
Heeger++ [104]113.8 9.81 123 17.3 130 10.4 112 11.3 117 17.2 110 9.67 111 13.6 133 23.8 134 10.2 131 26.3 128 22.8 116 44.4 115 31.8 122 28.9 128 46.3 118 29.6 113 22.0 99 37.5 110 8.17 128 19.8 125 10.9 103 9.10 106 18.2 104 7.02 14
Learning Flow [11]115.5 8.21 102 14.8 121 9.74 98 9.78 107 17.6 116 8.11 92 9.68 123 15.5 121 7.56 119 25.0 123 24.3 129 45.4 123 31.9 123 28.7 126 47.3 124 29.4 111 22.0 99 37.8 113 7.49 111 18.3 111 10.9 103 10.2 130 20.2 128 8.31 119
2bit-BM-tele [98]116.6 8.61 111 13.5 110 10.5 114 10.0 110 17.5 115 9.73 112 8.26 96 11.5 55 7.40 117 24.4 119 22.7 114 48.1 130 32.5 129 28.6 123 50.2 133 34.7 133 24.3 128 44.9 133 9.35 135 26.2 134 13.8 135 9.25 113 17.3 66 10.2 134
FFV1MT [106]120.4 9.53 120 16.7 128 10.7 117 12.6 128 18.2 124 12.8 127 13.3 132 23.5 133 10.5 132 26.3 128 22.8 116 44.4 115 31.4 118 28.2 119 46.1 110 29.8 117 20.6 62 38.1 119 8.32 131 20.5 127 11.0 107 10.5 131 20.4 129 8.45 120
Adaptive flow [45]123.2 13.2 130 15.9 126 16.2 131 14.2 132 19.9 130 16.4 132 9.02 114 13.1 98 8.03 122 26.0 127 22.8 116 48.6 131 32.4 127 29.4 131 47.9 126 30.1 122 24.6 130 38.0 117 7.55 114 16.9 100 12.2 127 9.85 123 19.5 123 8.97 129
FOLKI [16]123.4 15.0 133 17.4 131 19.4 133 14.3 133 20.9 133 14.4 130 10.7 127 19.2 132 9.99 130 29.8 133 26.8 132 53.1 134 31.3 116 28.6 123 45.8 77 30.0 119 21.7 87 38.9 124 7.85 124 19.4 122 11.6 121 9.85 123 19.2 120 8.80 124
Pyramid LK [2]125.7 16.3 134 16.1 127 21.6 134 16.0 134 20.3 131 18.2 134 16.7 134 15.3 119 14.3 134 35.7 135 36.7 135 56.5 135 32.8 131 31.2 133 45.7 61 29.7 116 22.1 103 38.2 121 8.31 130 23.1 131 11.6 121 11.8 133 25.0 133 8.22 117
PGAM+LK [55]126.9 12.7 129 18.1 132 15.3 130 12.4 125 19.1 128 13.0 128 11.1 130 18.6 131 9.33 129 29.2 132 27.5 133 51.6 133 31.7 120 28.8 127 46.7 121 31.3 130 23.7 122 40.1 130 7.67 120 19.4 122 11.4 118 9.89 125 19.5 123 8.95 127
HCIC-L [99]127.6 18.0 135 18.7 133 23.1 135 12.7 129 17.2 110 17.0 133 10.5 126 14.4 117 8.49 124 25.7 126 23.9 125 44.3 114 33.2 133 29.8 132 49.0 131 31.7 131 26.4 134 39.2 126 7.98 127 18.4 114 12.4 130 12.4 134 25.3 135 8.96 128
Periodicity [78]133.6 14.9 132 20.8 135 18.2 132 20.1 135 22.0 135 21.5 135 17.7 135 26.4 135 16.1 135 29.8 133 34.8 134 49.7 132 35.4 135 34.2 135 48.7 129 37.1 135 25.8 133 47.4 135 8.68 133 23.6 132 12.2 127 13.3 135 25.1 134 11.6 135
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 T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[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 D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[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 A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[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 L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[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 M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to 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 W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[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] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] 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.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] 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.
[89] 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.
[90] 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.
[91] 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.
[92] 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.
[93] 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.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] 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.
[98] 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.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] 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.
[107] 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.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] 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.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] 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.)
[114] 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.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] 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.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] 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.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] 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. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] 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.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] 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.
[131] 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.
[132] 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.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] 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.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
* 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.