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]11.2 6.71 2 9.78 2 8.39 8 6.36 9 11.5 11 6.23 12 7.12 4 9.73 7 5.42 2 21.2 5 18.8 8 41.2 11 30.1 5 26.5 3 45.6 48 27.7 17 19.5 26 36.0 17 6.48 2 13.8 4 10.3 6 8.19 21 16.4 16 7.11 24
PMMST [114]12.5 6.84 9 9.80 3 8.50 15 6.74 25 11.7 13 6.36 29 7.10 3 9.45 3 5.41 1 21.1 1 18.6 2 41.1 3 30.2 9 26.5 3 45.7 58 27.3 2 18.1 4 36.0 17 6.51 4 13.9 9 10.3 6 8.22 24 16.5 22 7.15 35
PH-Flow [101]14.1 7.05 21 10.9 17 8.50 15 6.10 3 10.6 5 6.14 3 7.18 5 9.83 8 5.55 6 21.1 1 18.5 1 41.1 3 30.1 5 26.6 8 45.2 14 27.9 33 21.7 84 35.7 9 6.60 15 14.3 19 10.3 6 8.11 12 16.3 13 7.14 32
NNF-Local [87]14.2 6.74 4 10.1 6 8.30 2 5.97 1 10.3 2 6.14 3 7.09 2 9.63 6 5.44 3 21.7 31 20.5 60 41.2 11 30.3 19 26.6 8 45.4 23 27.9 33 20.6 60 36.0 17 6.51 4 13.8 4 10.3 6 8.04 8 16.1 6 7.10 22
CombBMOF [113]15.6 6.93 13 9.87 5 8.43 10 6.33 8 11.4 9 6.22 11 7.60 43 10.3 14 6.25 73 21.5 20 19.4 22 41.2 11 30.2 9 26.6 8 45.3 19 27.7 17 19.2 18 36.1 30 6.57 11 14.1 12 10.3 6 7.67 1 15.4 3 6.82 1
NN-field [71]18.4 6.88 10 10.8 13 8.48 12 5.99 2 10.3 2 6.13 2 7.65 52 9.54 4 5.81 31 21.9 45 21.0 80 41.4 24 30.2 9 26.6 8 45.4 23 27.8 27 20.0 42 36.0 17 6.48 2 13.7 3 10.3 6 8.02 7 16.1 6 7.04 15
IROF++ [58]23.4 7.07 24 11.3 27 8.50 15 6.64 20 12.0 18 6.19 7 7.54 35 10.6 27 5.84 36 21.2 5 18.6 2 41.5 28 30.2 9 26.9 20 45.0 9 27.6 14 18.8 10 36.2 36 6.69 31 14.7 29 10.5 56 8.17 18 16.4 16 7.33 70
Layers++ [37]23.9 7.17 34 11.1 22 8.79 55 6.14 6 10.3 2 6.41 33 7.34 16 10.3 14 5.69 18 21.3 10 19.0 14 41.3 17 30.5 35 27.1 39 45.4 23 28.1 51 21.1 72 36.2 36 6.51 4 13.8 4 10.2 1 8.20 22 16.4 16 7.13 30
nLayers [57]25.8 7.15 32 10.4 10 8.81 60 6.44 12 11.4 9 6.42 34 7.23 8 9.30 1 5.65 14 21.4 15 19.1 17 41.5 28 30.7 70 27.4 78 45.6 48 28.0 42 20.8 64 36.2 36 6.54 9 13.6 1 10.3 6 8.07 9 16.3 13 6.91 3
Sparse-NonSparse [56]27.3 7.09 25 11.3 27 8.57 23 6.53 16 11.8 16 6.21 9 7.40 24 10.5 24 5.64 10 21.5 20 19.0 14 41.7 44 30.4 26 27.0 29 45.4 23 28.3 63 21.5 81 36.4 59 6.66 23 14.4 21 10.3 6 8.23 25 16.6 27 7.09 20
2DHMM-SAS [92]27.8 7.27 46 12.0 55 8.59 26 7.82 61 14.2 51 6.36 29 7.25 9 10.5 24 5.74 24 21.4 15 18.7 5 41.4 24 30.3 19 26.9 20 45.2 14 27.9 33 20.3 46 36.0 17 6.64 21 14.4 21 10.3 6 8.41 43 17.0 41 7.08 17
ProbFlowFields [128]27.9 7.03 18 11.8 48 8.66 36 6.41 10 11.7 13 6.31 22 7.18 5 10.3 14 5.58 7 21.7 31 19.6 29 41.8 51 30.7 70 27.1 39 46.0 102 27.9 33 20.5 52 36.2 36 6.51 4 13.8 4 10.3 6 7.80 3 15.6 4 7.14 32
NNF-EAC [103]28.9 7.35 54 11.1 22 8.79 55 6.92 35 12.5 29 6.29 20 7.52 34 10.1 11 5.76 27 21.8 37 19.5 27 42.8 99 30.2 9 26.6 8 45.4 23 27.5 7 18.9 12 36.0 17 6.58 13 14.2 15 10.4 32 8.32 32 16.8 31 7.19 44
AGIF+OF [85]29.0 7.11 27 11.3 27 8.46 11 6.68 24 12.2 22 6.27 16 7.38 21 10.1 11 5.71 22 21.2 5 18.6 2 41.1 3 30.8 81 27.6 98 45.4 23 28.3 63 22.2 102 36.0 17 6.67 24 14.0 11 10.3 6 8.34 35 17.0 41 6.91 3
FlowFields [110]29.2 7.02 17 11.5 34 8.54 21 6.66 23 12.5 29 6.44 38 7.45 27 11.5 52 5.64 10 21.9 45 20.5 60 41.8 51 30.6 51 27.0 29 45.5 38 27.7 17 20.2 44 36.0 17 6.59 14 14.3 19 10.4 32 8.00 6 16.2 11 7.08 17
FMOF [94]29.9 7.36 56 12.0 55 8.73 46 6.42 11 11.3 8 6.30 21 7.63 48 10.4 19 6.02 63 21.8 37 19.9 36 41.2 11 30.5 35 27.0 29 45.4 23 28.0 42 20.5 52 36.1 30 6.51 4 13.8 4 10.2 1 8.30 30 16.7 30 7.12 26
S2F-IF [123]30.8 7.01 16 11.5 34 8.48 12 6.57 17 12.2 22 6.42 34 7.40 24 11.2 48 5.64 10 21.6 24 20.1 42 41.3 17 30.7 70 27.3 66 45.7 58 27.8 27 20.4 49 36.1 30 6.71 36 14.9 44 10.4 32 7.98 5 16.1 6 7.04 15
LSM [39]32.0 7.17 34 11.8 48 8.58 25 6.64 20 12.1 21 6.17 6 7.49 30 10.9 39 5.69 18 21.6 24 19.6 29 41.6 35 30.5 35 27.1 39 45.4 23 28.3 63 21.6 82 36.3 50 6.68 29 14.6 25 10.2 1 8.35 38 16.9 39 7.03 14
LME [70]32.5 6.72 3 9.86 4 8.36 5 6.97 37 12.4 26 7.40 83 7.51 32 11.8 59 5.70 21 21.3 10 19.2 20 41.3 17 31.0 102 27.6 98 46.6 114 27.8 27 20.5 52 36.0 17 6.45 1 13.6 1 10.2 1 8.08 11 16.3 13 7.12 26
TV-L1-MCT [64]33.8 7.50 75 12.5 82 8.79 55 7.19 42 13.4 41 6.37 31 7.28 11 10.6 27 5.80 30 21.4 15 18.8 8 41.3 17 30.5 35 27.1 39 45.1 12 27.9 33 18.6 7 36.6 72 6.72 40 15.0 51 10.4 32 7.92 4 15.9 5 7.20 47
WLIF-Flow [93]33.8 6.99 15 11.0 19 8.48 12 6.76 26 12.4 26 6.39 32 7.38 21 10.3 14 5.68 17 21.4 15 18.8 8 41.9 64 30.4 26 26.9 20 45.9 92 28.8 96 21.9 91 36.9 91 6.56 10 13.9 9 10.3 6 8.34 35 16.8 31 7.15 35
ComponentFusion [96]33.9 6.91 11 10.8 13 8.55 22 6.49 15 12.0 18 6.10 1 7.49 30 11.2 48 5.72 23 21.3 10 19.4 22 41.2 11 30.6 51 27.2 53 45.8 74 27.8 27 19.6 29 36.2 36 6.92 72 16.4 90 10.4 32 8.43 47 17.0 41 7.16 38
COFM [59]35.0 7.04 19 10.7 12 8.70 40 6.60 18 11.9 17 6.35 26 7.26 10 9.93 9 5.63 9 21.2 5 18.8 8 41.0 1 30.4 26 27.3 66 44.9 8 27.7 17 22.6 105 35.1 2 6.86 65 14.7 29 11.2 109 8.67 74 17.2 58 7.78 106
MDP-Flow [26]35.5 6.83 7 10.8 13 8.50 15 6.65 22 12.4 26 6.51 44 7.46 28 10.6 27 5.88 44 22.1 63 20.6 65 41.7 44 30.4 26 26.8 15 45.6 48 28.2 60 21.9 91 36.3 50 6.69 31 14.8 38 10.4 32 8.15 14 16.6 27 7.10 22
RNLOD-Flow [121]36.9 7.12 29 11.5 34 8.64 33 7.38 48 14.0 48 6.35 26 7.55 36 11.2 48 5.83 35 21.3 10 19.0 14 41.1 3 30.5 35 27.2 53 45.4 23 28.3 63 21.6 82 36.2 36 6.62 16 14.2 15 10.4 32 8.70 77 17.7 78 7.02 12
HAST [109]37.0 6.97 14 10.2 7 8.69 38 6.46 13 11.6 12 6.26 15 7.72 60 11.1 44 5.97 56 21.1 1 18.7 5 41.1 3 30.5 35 27.5 85 44.8 6 28.2 60 22.8 111 35.5 5 6.76 49 15.2 59 10.4 32 8.81 80 18.0 89 6.96 8
OFLAF [77]37.5 6.81 6 10.2 7 8.40 9 6.10 3 10.7 6 6.21 9 7.36 18 10.6 27 5.54 5 21.1 1 18.8 8 41.0 1 30.8 81 27.4 78 45.7 58 28.1 51 21.9 91 36.0 17 7.02 83 16.1 87 10.4 32 8.90 87 18.1 96 7.16 38
Ramp [62]39.7 7.31 52 12.1 59 8.78 52 6.60 18 12.0 18 6.27 16 7.36 18 10.4 19 5.65 14 21.3 10 18.9 13 41.4 24 30.5 35 27.1 39 45.4 23 28.7 91 22.3 103 36.6 72 6.73 45 14.9 44 10.3 6 8.55 61 17.3 63 7.26 58
Second-order prior [8]40.2 7.30 51 11.3 27 8.90 69 8.52 79 15.6 78 6.74 58 8.32 92 13.6 101 6.42 86 21.8 37 20.0 39 41.5 28 30.1 5 26.5 3 45.5 38 27.5 7 19.0 13 36.0 17 6.67 24 14.6 25 10.3 6 8.25 26 16.8 31 7.11 24
PGM-C [120]41.3 7.19 39 12.1 59 8.72 43 6.82 28 12.9 33 6.62 50 7.67 56 12.2 70 5.78 29 21.9 45 20.9 74 41.8 51 30.6 51 27.1 39 45.8 74 27.7 17 19.5 26 36.2 36 6.65 22 14.7 29 10.3 6 8.20 22 16.6 27 7.31 65
DeepFlow2 [108]42.2 7.28 47 11.3 27 8.88 66 7.68 57 14.4 58 6.94 71 7.58 41 12.3 74 5.88 44 21.9 45 20.2 46 41.7 44 30.5 35 26.8 15 45.9 92 27.5 7 18.0 3 36.4 59 6.67 24 14.6 25 10.4 32 8.18 19 16.4 16 7.31 65
Aniso. Huber-L1 [22]42.5 7.61 82 12.2 67 9.19 81 8.99 89 15.7 81 7.12 77 7.73 62 11.0 42 5.86 41 21.8 37 20.0 39 41.6 35 30.2 9 26.6 8 45.5 38 27.4 4 19.6 29 35.7 9 6.68 29 14.6 25 10.3 6 8.34 35 16.8 31 7.29 64
Classic+NL [31]42.5 7.44 69 12.3 70 8.86 63 6.78 27 12.3 24 6.28 18 7.32 15 10.4 19 5.69 18 21.6 24 19.4 22 41.8 51 30.5 35 27.1 39 45.5 38 28.6 86 21.8 87 36.6 72 6.72 40 14.7 29 10.3 6 8.50 55 17.2 58 7.24 55
FC-2Layers-FF [74]42.8 7.22 42 11.9 53 8.70 40 6.10 3 10.2 1 6.47 40 7.31 14 10.5 24 5.64 10 21.4 15 19.1 17 41.6 35 30.7 70 27.5 85 45.6 48 28.6 86 22.7 108 36.4 59 6.77 51 15.0 51 10.3 6 8.57 63 17.2 58 7.20 47
SRR-TVOF-NL [91]43.5 7.42 67 11.5 34 8.86 63 7.79 59 14.8 66 7.08 75 7.62 45 11.5 52 5.85 39 21.7 31 19.6 29 41.1 3 30.3 19 27.1 39 45.2 14 27.5 7 20.5 52 35.3 4 6.72 40 14.8 38 10.4 32 8.97 94 18.3 102 7.17 41
DF-Auto [115]44.7 7.54 77 11.1 22 9.32 89 8.42 75 14.5 61 8.82 94 7.35 17 10.3 14 5.65 14 22.0 55 20.2 46 41.5 28 30.4 26 26.7 14 45.8 74 27.5 7 18.7 9 36.1 30 6.82 58 15.3 63 10.5 56 8.43 47 17.1 49 7.20 47
FESL [72]44.8 7.36 56 11.7 43 8.65 35 6.82 28 12.6 31 6.33 24 7.51 32 10.7 34 5.89 47 21.6 24 19.6 29 41.3 17 30.9 98 27.5 85 45.7 58 28.4 75 22.1 100 36.2 36 6.70 34 14.8 38 10.2 1 8.59 64 17.4 69 7.08 17
CPM-Flow [116]44.8 7.21 40 12.2 67 8.71 42 6.83 31 12.9 33 6.65 52 7.61 44 11.7 56 5.88 44 22.2 69 21.4 93 41.8 51 30.6 51 27.1 39 45.8 74 27.9 33 19.1 14 36.6 72 6.67 24 14.7 29 10.3 6 8.16 16 16.5 22 7.34 73
Classic+CPF [83]45.5 7.22 42 11.6 39 8.52 20 6.90 34 12.6 31 6.28 18 7.37 20 10.6 27 5.76 27 21.2 5 18.7 5 41.1 3 31.1 106 27.9 106 45.5 38 28.7 91 23.1 115 36.3 50 6.92 72 15.3 63 10.3 6 8.75 79 17.9 85 6.99 9
S2D-Matching [84]47.0 7.37 59 12.3 70 8.80 58 7.62 56 14.2 51 6.43 37 7.28 11 10.4 19 5.74 24 21.6 24 19.1 17 42.2 78 30.6 51 27.3 66 45.4 23 28.6 86 22.5 104 36.4 59 6.76 49 14.5 23 10.3 6 8.46 50 17.0 41 7.32 67
DeepFlow [86]47.2 7.21 40 11.0 19 8.88 66 7.79 59 14.3 54 7.33 82 7.64 50 12.6 82 5.95 53 22.1 63 20.1 42 42.0 69 30.6 51 26.8 15 46.1 105 28.0 42 17.9 2 37.2 98 6.57 11 14.1 12 10.4 32 8.07 9 16.2 11 7.32 67
IROF-TV [53]47.3 7.33 53 12.3 70 8.82 61 6.83 31 12.3 24 6.23 12 7.70 59 12.9 90 5.93 51 21.5 20 19.5 27 42.0 69 30.8 81 27.3 66 45.9 92 27.5 7 20.2 44 35.6 6 6.75 47 15.1 57 10.5 56 8.18 19 16.4 16 7.37 77
EPPM w/o HM [88]47.6 6.77 5 10.4 10 8.32 3 7.00 38 13.4 41 6.16 5 8.19 85 13.6 101 6.26 74 21.7 31 20.3 49 41.5 28 30.5 35 27.2 53 45.5 38 28.5 81 21.8 87 36.5 67 6.84 59 15.6 73 10.6 80 8.41 43 17.1 49 6.95 7
p-harmonic [29]47.7 7.04 19 11.3 27 8.62 31 8.81 83 15.8 83 6.98 72 7.76 65 13.1 92 6.18 71 22.4 79 20.7 68 41.9 64 30.5 35 27.0 29 45.5 38 27.8 27 19.2 18 36.4 59 6.71 36 15.1 57 10.3 6 8.29 29 16.8 31 7.12 26
Brox et al. [5]47.8 7.28 47 11.4 33 8.76 48 7.86 62 14.6 63 6.92 70 8.03 79 13.1 92 6.34 80 21.9 45 19.9 36 41.4 24 30.6 51 27.0 29 45.8 74 27.7 17 19.5 26 36.2 36 6.80 54 15.4 68 10.4 32 8.16 16 16.5 22 7.19 44
Efficient-NL [60]48.5 7.28 47 11.6 39 8.61 30 7.24 45 13.3 40 6.35 26 8.21 87 10.8 36 6.39 85 21.7 31 19.6 29 41.2 11 30.4 26 27.0 29 45.3 19 28.3 63 22.8 111 35.6 6 6.86 65 15.6 73 10.4 32 9.10 100 18.3 102 7.14 32
SepConv-v1 [127]49.2 4.07 1 8.88 1 4.61 1 6.87 33 13.0 37 7.47 84 6.42 1 9.58 5 9.25 122 23.4 103 20.0 39 44.0 107 30.2 9 26.3 2 45.7 58 27.9 33 16.5 1 37.4 104 7.61 111 15.6 73 12.9 127 7.71 2 13.8 1 9.78 126
EpicFlow [102]51.5 7.18 36 12.0 55 8.72 43 7.42 50 14.4 58 6.72 57 7.68 57 12.1 67 5.92 50 22.1 63 21.1 84 42.0 69 30.7 70 27.1 39 45.8 74 27.5 7 19.9 40 35.9 13 6.79 53 15.2 59 10.4 32 8.40 42 17.1 49 7.33 70
DPOF [18]52.0 7.58 81 13.2 100 9.07 72 6.27 7 11.0 7 6.54 46 8.10 83 10.6 27 6.27 76 22.0 55 20.5 60 41.9 64 30.2 9 26.8 15 45.4 23 28.0 42 21.2 74 35.8 12 6.84 59 15.0 51 10.7 90 8.62 68 17.4 69 7.26 58
PMF [73]52.5 6.83 7 10.3 9 8.37 6 6.96 36 13.1 38 6.19 7 7.86 70 13.1 92 6.03 64 21.5 20 19.4 22 41.3 17 31.0 102 27.7 102 45.8 74 28.7 91 20.5 52 37.2 98 6.80 54 15.0 51 10.5 56 8.87 83 18.2 99 7.00 10
ComplOF-FED-GPU [35]52.9 7.23 44 11.8 48 8.72 43 7.20 43 13.9 45 6.62 50 8.43 95 12.6 82 6.45 87 21.9 45 20.8 73 42.3 80 30.4 26 26.9 20 45.4 23 27.7 17 20.1 43 36.1 30 6.86 65 15.4 68 10.5 56 8.55 61 17.3 63 7.28 63
Sparse Occlusion [54]54.2 7.37 59 12.3 70 8.87 65 8.04 66 15.3 72 6.48 41 7.58 41 10.8 36 5.87 42 22.0 55 20.4 54 41.5 28 30.6 51 27.2 53 45.5 38 28.3 63 21.8 87 36.4 59 6.80 54 15.3 63 10.3 6 8.74 78 17.7 78 7.18 43
TC/T-Flow [76]54.4 7.37 59 11.8 48 8.59 26 7.31 46 14.0 48 6.42 34 7.47 29 11.1 44 5.81 31 21.8 37 20.5 60 41.7 44 30.8 81 27.5 85 45.7 58 28.1 51 20.9 65 36.2 36 7.03 85 16.0 85 10.6 80 8.62 68 17.6 75 7.13 30
CLG-TV [48]56.1 7.52 76 12.3 70 9.14 76 8.67 81 15.8 83 7.11 76 7.97 76 12.7 86 6.26 74 22.1 63 20.3 49 42.0 69 30.5 35 26.9 20 45.7 58 27.6 14 19.1 14 36.2 36 6.71 36 14.9 44 10.4 32 8.53 60 17.3 63 7.24 55
AggregFlow [97]56.1 7.71 88 12.6 84 9.11 74 7.50 53 13.9 45 7.06 73 7.19 7 9.98 10 5.53 4 21.9 45 20.4 54 41.6 35 30.8 81 27.3 66 46.1 105 29.0 100 19.7 36 37.9 111 6.75 47 14.7 29 10.5 56 8.32 32 16.8 31 7.40 81
SuperFlow [81]56.2 7.43 68 11.5 34 9.30 86 8.55 80 14.8 66 9.15 97 7.91 74 12.0 64 6.31 77 22.1 63 19.9 36 42.0 69 30.7 70 27.2 53 45.9 92 27.3 2 18.4 6 35.9 13 6.86 65 15.8 79 10.6 80 8.15 14 16.5 22 7.16 38
RFlow [90]56.6 7.24 45 12.1 59 8.90 69 8.42 75 15.6 78 6.49 42 7.72 60 12.2 70 6.01 62 22.0 55 20.6 65 41.7 44 30.4 26 27.1 39 45.7 58 27.4 4 19.8 39 35.6 6 6.84 59 15.9 83 10.5 56 8.91 90 18.0 89 7.47 86
SIOF [67]57.2 7.66 85 12.6 84 9.09 73 9.45 97 16.6 96 8.48 91 7.65 52 11.9 62 5.98 57 21.9 45 20.1 42 41.8 51 30.0 3 26.5 3 45.3 19 28.1 51 19.7 36 36.6 72 6.63 19 14.7 29 10.5 56 8.82 81 17.9 85 7.46 83
TCOF [69]57.3 7.36 56 12.1 59 8.68 37 9.41 96 16.6 96 7.17 79 7.38 21 10.7 34 5.61 8 21.8 37 20.4 54 41.8 51 30.4 26 27.0 29 45.6 48 28.1 51 21.8 87 35.9 13 6.85 62 15.7 78 10.4 32 9.30 109 19.0 113 7.61 100
TC-Flow [46]57.7 7.18 36 11.8 48 8.78 52 7.46 52 14.6 63 6.77 62 7.86 70 12.6 82 5.89 47 21.8 37 20.3 49 41.9 64 30.7 70 27.4 78 45.7 58 28.3 63 21.0 68 36.6 72 6.73 45 14.8 38 10.5 56 8.51 56 17.3 63 7.24 55
IAOF [50]57.8 8.70 109 12.9 93 10.3 106 12.4 119 19.2 123 9.77 108 7.74 63 12.0 64 6.21 72 22.8 89 20.2 46 42.0 69 30.2 9 26.5 3 45.5 38 27.7 17 19.6 29 36.1 30 6.67 24 15.0 51 10.3 6 8.41 43 17.1 49 7.12 26
OAR-Flow [125]59.2 7.45 71 11.7 43 8.98 71 7.57 55 14.4 58 6.91 69 7.62 45 12.4 77 5.82 33 21.6 24 20.3 49 41.6 35 30.9 98 27.5 85 45.8 74 28.0 42 20.5 52 36.4 59 6.97 80 15.6 73 10.5 56 8.46 50 17.1 49 7.34 73
ALD-Flow [66]61.0 7.54 77 12.1 59 9.14 76 7.43 51 14.3 54 6.85 66 7.66 55 12.5 80 5.87 42 21.8 37 20.4 54 42.3 80 30.8 81 27.4 78 45.9 92 28.1 51 19.9 40 36.6 72 6.62 16 14.2 15 10.5 56 8.68 75 17.5 74 7.46 83
OFH [38]61.5 7.39 64 12.1 59 8.88 66 8.07 67 15.0 70 6.66 54 8.03 79 13.8 104 5.96 55 21.9 45 21.1 84 42.1 75 30.5 35 27.3 66 45.4 23 27.8 27 20.4 49 36.2 36 7.11 87 16.4 90 10.5 56 8.61 67 17.6 75 7.19 44
SVFilterOh [111]62.3 7.18 36 10.9 17 8.76 48 6.48 14 11.7 13 6.45 39 7.62 45 10.2 13 5.99 59 21.7 31 19.4 22 42.5 90 31.3 110 28.0 110 46.6 114 28.6 86 22.0 96 36.5 67 6.92 72 14.1 12 11.4 113 8.97 94 17.8 83 8.09 111
MLDP_OF [89]63.5 7.10 26 11.2 26 8.64 33 7.33 47 13.7 43 6.31 22 7.44 26 10.9 39 5.75 26 22.0 55 19.8 35 42.3 80 30.6 51 27.3 66 46.2 111 31.0 123 22.6 105 40.0 123 6.93 75 15.2 59 11.0 103 8.65 72 17.4 69 7.79 108
CostFilter [40]63.7 6.91 11 11.1 22 8.37 6 6.82 28 12.9 33 6.25 14 7.99 77 13.9 105 6.10 66 21.9 45 20.6 65 41.7 44 31.1 106 27.9 106 45.9 92 29.8 111 20.3 46 39.1 119 6.94 77 15.8 79 10.6 80 8.82 81 18.1 96 7.09 20
Modified CLG [34]64.2 7.63 83 11.6 39 9.65 92 10.7 107 17.2 104 10.7 112 8.25 89 14.3 110 6.60 93 22.4 79 21.1 84 41.8 51 30.6 51 26.9 20 45.8 74 27.7 17 19.2 18 36.3 50 6.69 31 14.9 44 10.4 32 8.41 43 17.0 41 7.35 76
Fusion [6]64.5 7.13 31 12.3 70 8.60 29 7.18 41 13.1 38 6.56 47 7.63 48 10.9 39 6.13 69 22.5 85 21.1 84 41.5 28 30.7 70 28.2 113 44.3 2 28.1 51 23.8 118 35.2 3 7.22 96 17.9 103 10.6 80 9.64 116 19.9 120 7.32 67
F-TV-L1 [15]65.4 8.24 99 13.1 97 9.92 99 9.28 92 16.3 91 7.48 85 8.00 78 13.2 97 6.35 82 22.3 75 20.9 74 42.3 80 29.9 2 26.9 20 44.8 6 27.9 33 19.4 23 36.5 67 6.87 69 15.4 68 10.5 56 8.46 50 16.8 31 7.58 96
FlowNet2 [122]66.2 9.30 112 14.6 113 10.5 109 8.42 75 14.6 63 9.24 101 8.03 79 12.5 80 6.14 70 22.2 69 21.9 102 41.8 51 30.9 98 27.5 85 45.8 74 28.0 42 20.5 52 36.0 17 6.72 40 14.9 44 10.4 32 8.31 31 16.9 39 7.01 11
Complementary OF [21]67.1 7.11 27 12.1 59 8.50 15 7.17 40 14.0 48 6.58 49 8.76 104 12.0 64 6.55 90 22.3 75 21.4 93 42.6 96 30.6 51 27.5 85 45.2 14 28.1 51 20.9 65 36.4 59 7.15 90 16.7 94 10.5 56 9.09 99 18.7 109 7.38 78
SimpleFlow [49]67.5 7.37 59 12.4 79 8.74 47 7.88 63 14.3 54 6.50 43 8.59 100 11.5 52 6.51 88 21.6 24 19.3 21 41.8 51 30.6 51 27.3 66 45.5 38 28.5 81 22.9 113 36.2 36 7.66 114 20.5 122 10.8 98 8.89 86 18.2 99 7.15 35
LDOF [28]67.9 8.08 94 12.3 70 9.79 97 8.94 87 14.9 68 9.18 99 8.23 88 13.5 100 6.52 89 22.3 75 21.1 84 42.4 88 30.6 51 27.0 29 45.8 74 27.9 33 18.8 10 36.6 72 6.77 51 15.3 63 10.4 32 8.44 49 17.1 49 7.38 78
ROF-ND [107]69.0 7.46 72 11.0 19 8.77 50 7.96 64 15.4 73 6.76 61 7.55 36 11.0 42 5.85 39 23.3 100 23.5 119 41.6 35 30.6 51 27.1 39 45.8 74 28.3 63 22.7 108 35.9 13 7.52 108 17.5 100 11.4 113 9.25 107 18.7 109 7.27 60
TF+OM [100]69.0 7.41 65 12.1 59 9.19 81 7.21 44 12.9 33 7.83 86 7.55 36 12.3 74 5.82 33 22.2 69 21.0 80 41.9 64 30.8 81 27.5 85 46.0 102 28.3 63 20.5 52 36.8 86 6.97 80 16.3 88 10.5 56 8.65 72 17.3 63 7.75 104
Local-TV-L1 [65]69.2 8.46 105 12.6 84 10.4 107 9.68 98 16.0 89 8.93 96 7.56 40 11.2 48 5.84 36 23.1 96 20.4 54 46.0 119 30.6 51 27.1 39 45.9 92 30.1 116 19.1 14 39.9 122 6.72 40 14.9 44 10.5 56 8.13 13 16.1 6 7.58 96
TriFlow [95]69.9 7.77 90 13.7 108 9.28 84 8.98 88 15.7 81 9.30 103 7.65 52 12.4 77 5.84 36 22.0 55 20.9 74 41.1 3 30.9 98 27.7 102 45.7 58 28.4 75 21.3 78 36.3 50 6.85 62 15.5 72 10.4 32 8.69 76 17.4 69 7.23 54
Classic++ [32]70.5 7.49 74 12.5 82 9.11 74 8.07 67 15.2 71 6.67 55 7.89 73 12.6 82 6.04 65 22.3 75 20.7 68 42.2 78 30.6 51 27.2 53 45.7 58 29.0 100 21.0 68 37.6 106 6.81 57 15.2 59 10.5 56 8.62 68 17.4 69 7.46 83
Occlusion-TV-L1 [63]70.5 7.44 69 12.3 70 9.14 76 8.91 86 16.5 94 6.85 66 7.83 68 12.8 87 6.32 78 22.6 88 21.5 97 42.5 90 30.5 35 26.9 20 45.8 74 28.4 75 19.6 29 37.1 95 7.15 90 14.8 38 10.7 90 8.51 56 17.1 49 7.34 73
2D-CLG [1]71.1 8.44 103 12.3 70 10.6 111 11.9 115 18.0 114 12.3 119 8.94 107 13.9 105 7.33 110 23.1 96 21.2 91 41.3 17 30.5 35 26.9 20 45.8 74 27.6 14 19.2 18 36.2 36 7.14 88 17.2 98 10.5 56 8.37 40 16.5 22 7.20 47
Nguyen [33]71.1 9.74 115 12.6 84 12.4 119 12.3 117 18.6 119 11.1 113 8.27 91 14.8 112 6.69 95 23.4 103 21.7 99 41.8 51 30.3 19 26.8 15 45.3 19 27.4 4 19.6 29 35.7 9 7.24 98 18.3 106 10.5 56 8.37 40 17.0 41 7.22 53
FlowNetS+ft+v [112]72.0 7.81 92 11.7 43 9.63 91 9.77 100 16.8 98 9.16 98 8.06 82 13.4 99 6.36 83 22.1 63 20.7 68 42.1 75 30.8 81 27.4 78 45.8 74 27.7 17 19.4 23 36.3 50 7.01 82 16.4 90 10.5 56 8.51 56 17.2 58 7.33 70
Aniso-Texture [82]72.5 7.16 33 11.6 39 8.78 52 8.84 84 16.5 94 6.86 68 8.38 94 11.8 59 5.99 59 22.4 79 21.4 93 42.5 90 31.0 102 27.5 85 46.0 102 29.0 100 24.2 121 36.7 81 6.70 34 14.7 29 10.3 6 8.90 87 18.0 89 7.27 60
Shiralkar [42]73.0 7.48 73 12.8 91 8.80 58 9.00 90 15.8 83 6.65 52 8.52 98 16.1 116 6.84 99 23.4 103 22.3 106 41.6 35 30.0 3 27.0 29 44.5 3 28.7 91 21.1 72 37.1 95 7.49 106 18.7 114 10.6 80 8.64 71 17.7 78 6.93 5
Adaptive [20]73.9 7.71 88 13.2 100 9.21 83 9.40 95 16.8 98 7.07 74 7.87 72 12.4 77 6.12 67 22.0 55 20.3 49 41.8 51 30.7 70 27.3 66 45.6 48 28.4 75 20.7 63 36.8 86 6.95 79 16.0 85 10.4 32 8.87 83 17.9 85 7.55 93
CNN-flow-warp+ref [117]75.8 7.35 54 10.8 13 9.30 86 8.87 85 16.2 90 8.14 90 8.60 101 14.1 108 6.62 94 23.7 107 21.9 102 42.7 97 30.8 81 27.3 66 45.9 92 28.0 42 19.1 14 36.7 81 7.37 101 18.5 111 10.6 80 8.33 34 16.8 31 7.27 60
CRTflow [80]76.3 7.69 86 12.6 84 9.28 84 8.45 78 15.5 75 6.81 64 8.55 99 14.0 107 7.29 108 22.4 79 20.7 68 43.8 106 30.7 70 27.2 53 45.7 58 28.1 51 19.6 29 36.7 81 6.87 69 15.8 79 10.6 80 8.59 64 17.2 58 7.65 101
Black & Anandan [4]76.5 8.54 106 12.8 91 10.2 105 10.9 109 17.3 107 9.40 104 9.06 109 13.6 101 6.99 103 22.9 93 21.3 92 41.7 44 30.7 70 27.2 53 45.9 92 28.0 42 18.6 7 36.7 81 6.93 75 15.9 83 10.4 32 8.46 50 17.0 41 7.20 47
HBpMotionGpu [43]77.4 9.39 113 14.6 113 11.3 115 11.7 114 18.9 121 11.5 116 7.55 36 11.1 44 6.00 61 23.3 100 22.3 106 43.5 105 30.3 19 27.2 53 45.2 14 28.7 91 20.9 65 37.1 95 6.62 16 14.2 15 10.5 56 8.99 96 17.8 83 8.04 110
StereoOF-V1MT [119]77.6 7.65 84 13.5 105 8.77 50 8.69 82 15.9 88 6.52 45 9.43 114 15.4 114 7.23 106 24.4 113 22.3 106 43.2 103 30.5 35 27.2 53 45.0 9 28.9 98 21.2 74 37.2 98 7.77 117 19.4 117 11.0 103 8.26 28 16.4 16 6.93 5
GraphCuts [14]77.8 8.65 108 14.1 112 9.83 98 8.28 71 14.2 51 9.28 102 9.89 118 10.6 27 7.38 111 23.0 94 21.1 84 42.5 90 30.3 19 27.3 66 44.7 5 27.2 1 21.4 79 34.7 1 7.42 104 17.8 101 11.0 103 9.32 110 18.9 111 7.66 102
Steered-L1 [118]79.1 7.06 23 12.2 67 8.59 26 7.40 49 14.3 54 6.83 65 8.48 97 11.7 56 6.69 95 22.8 89 20.9 74 42.7 97 31.2 109 28.1 111 45.8 74 28.3 63 21.2 74 36.7 81 7.25 99 17.8 101 10.9 99 9.00 97 18.3 102 7.58 96
HBM-GC [105]79.1 7.91 93 12.6 84 9.75 95 7.51 54 13.9 45 6.80 63 7.29 13 9.43 2 5.94 52 22.0 55 19.7 34 42.3 80 32.1 120 28.6 117 48.0 121 30.0 113 24.6 124 37.8 108 7.14 88 14.8 38 11.6 116 8.95 93 17.7 78 8.28 113
CBF [12]79.2 7.41 65 11.9 53 9.31 88 8.07 67 14.9 68 7.14 78 7.69 58 11.1 44 5.95 53 22.8 89 20.7 68 45.1 115 30.8 81 27.3 66 47.0 118 28.2 60 20.6 60 36.5 67 7.17 93 16.6 93 11.2 109 9.16 104 17.9 85 8.83 120
TriangleFlow [30]79.4 7.79 91 13.0 96 9.16 80 8.36 74 15.5 75 6.69 56 8.20 86 11.9 62 6.59 91 22.5 85 21.0 80 42.5 90 30.1 5 27.0 29 45.0 9 28.9 98 22.6 105 36.5 67 7.42 104 18.3 106 11.0 103 9.49 113 19.3 115 7.47 86
Correlation Flow [75]80.0 7.05 21 11.7 43 8.32 3 8.29 72 15.6 78 6.56 47 7.64 50 10.8 36 5.89 47 22.2 69 20.1 42 42.9 101 31.7 114 27.7 102 49.9 126 29.6 108 23.8 118 37.2 98 7.62 112 19.0 116 11.3 111 9.22 106 18.6 108 7.51 92
IAOF2 [51]81.7 8.43 102 13.6 107 9.76 96 9.86 102 17.4 108 8.67 92 7.74 63 12.2 70 6.33 79 23.1 96 21.7 99 42.3 80 31.0 102 27.9 106 45.6 48 28.5 81 21.0 68 36.6 72 6.71 36 15.0 51 10.3 6 9.14 102 18.4 105 7.49 90
BriefMatch [124]83.5 7.38 63 12.0 55 8.85 62 7.71 58 14.5 61 7.86 87 8.77 105 11.7 56 7.25 107 24.2 111 22.0 104 46.2 120 30.8 81 27.4 78 46.1 105 31.8 126 21.7 84 41.3 126 6.85 62 15.3 63 10.7 90 8.51 56 17.1 49 7.56 95
SegOF [10]85.2 8.16 97 12.4 79 10.1 104 9.10 91 15.5 75 8.83 95 9.48 115 14.1 108 7.46 113 22.8 89 23.0 117 41.6 35 30.8 81 27.4 78 45.8 74 28.3 63 22.0 96 36.3 50 7.83 118 21.5 124 11.0 103 8.46 50 17.1 49 7.17 41
BlockOverlap [61]86.2 8.81 110 12.4 79 11.1 114 10.0 104 15.8 83 10.6 111 7.84 69 10.4 19 6.59 91 23.3 100 20.4 54 46.3 121 31.9 117 27.9 106 48.8 124 30.3 119 19.7 36 39.8 121 7.08 86 14.5 23 11.7 119 8.35 38 16.1 6 8.60 118
TV-L1-improved [17]86.5 7.55 79 12.9 93 9.15 79 9.36 93 16.9 100 7.19 80 8.63 102 12.2 70 6.92 101 22.2 69 21.0 80 42.3 80 30.8 81 27.5 85 45.6 48 28.5 81 21.4 79 36.8 86 7.38 102 18.6 113 10.7 90 8.94 91 18.0 89 7.75 104
Dynamic MRF [7]87.0 7.29 50 13.1 97 8.69 38 8.20 70 16.3 91 6.74 58 9.18 111 16.4 119 7.22 105 24.5 115 23.1 118 44.4 109 30.3 19 27.2 53 45.1 12 29.2 105 23.4 116 37.2 98 7.64 113 19.8 120 10.7 90 9.14 102 18.0 89 7.48 89
AdaConv-v1 [126]87.8 9.81 117 13.9 110 11.6 117 12.1 116 17.6 110 16.0 125 11.4 125 16.1 116 13.1 127 26.5 124 24.4 124 45.3 116 28.4 1 24.4 1 44.6 4 28.4 75 18.1 4 37.7 107 7.74 116 16.3 88 13.1 128 8.25 26 15.1 2 10.1 127
LocallyOriented [52]87.8 8.08 94 13.1 97 9.72 93 9.73 99 17.0 102 7.88 88 8.34 93 12.8 87 6.34 80 23.0 94 22.1 105 43.0 102 30.6 51 27.2 53 45.6 48 30.0 113 21.9 91 38.5 117 7.02 83 15.8 79 10.5 56 9.05 98 18.4 105 7.39 80
SPSA-learn [13]88.5 8.28 100 12.9 93 9.95 101 9.92 103 16.3 91 9.49 105 9.15 110 12.8 87 7.30 109 23.1 96 20.5 60 41.6 35 30.8 81 27.5 85 45.7 58 28.0 42 20.4 49 36.3 50 8.81 128 27.1 129 11.8 120 10.0 121 21.0 124 7.20 47
Rannacher [23]89.1 7.69 86 13.2 100 9.32 89 9.37 94 16.9 100 7.28 81 8.67 103 13.0 91 6.91 100 22.2 69 21.1 84 42.4 88 30.8 81 27.5 85 45.7 58 28.5 81 21.2 74 36.9 91 7.35 100 18.5 111 10.7 90 8.90 87 18.0 89 7.78 106
Ad-TV-NDC [36]89.8 10.8 120 13.9 110 13.4 120 11.6 113 17.6 110 11.2 114 7.77 66 12.3 74 6.12 67 24.0 109 21.6 98 44.4 109 31.1 106 27.6 98 46.1 105 29.0 100 19.3 22 38.0 112 6.87 69 15.4 68 10.5 56 8.59 64 17.0 41 7.71 103
ACK-Prior [27]90.8 7.12 29 11.7 43 8.57 23 7.08 39 13.8 44 6.34 25 8.81 106 11.8 59 6.69 95 22.5 85 21.4 93 42.3 80 32.6 124 29.3 123 48.2 122 30.7 122 25.6 126 38.1 114 7.95 121 18.8 115 12.0 121 10.8 126 21.8 126 8.53 117
Horn & Schunck [3]91.5 8.45 104 13.3 104 10.0 102 11.4 112 18.1 116 9.84 109 9.65 116 16.1 116 7.89 116 24.6 116 22.8 111 42.8 99 30.6 51 27.2 53 45.6 48 28.3 63 19.4 23 36.8 86 7.41 103 18.0 105 10.6 80 8.94 91 17.7 78 7.55 93
UnFlow [129]93.5 9.13 111 15.0 117 10.7 112 10.9 109 18.1 116 9.23 100 9.21 112 16.9 122 7.18 104 22.4 79 21.8 101 41.8 51 30.8 81 27.6 98 45.9 92 28.6 86 22.7 108 36.0 17 6.94 77 15.6 73 10.5 56 10.0 121 19.3 115 7.47 86
TI-DOFE [24]94.1 11.8 122 14.7 115 14.8 123 13.9 124 20.3 125 13.5 123 9.26 113 16.5 121 7.69 115 25.1 118 22.8 111 43.3 104 30.2 9 27.1 39 45.4 23 28.4 75 19.6 29 36.8 86 7.22 96 17.2 98 10.7 90 9.21 105 18.1 96 7.59 99
StereoFlow [44]94.2 13.8 125 20.2 128 14.0 121 14.1 125 21.3 128 12.0 118 7.79 67 13.3 98 5.98 57 22.4 79 20.9 74 42.1 75 33.7 128 32.3 128 46.1 105 30.5 120 31.8 129 36.3 50 6.63 19 14.7 29 10.4 32 9.98 120 21.0 124 7.42 82
Filter Flow [19]99.1 8.30 101 13.2 100 10.0 102 10.8 108 17.1 103 11.7 117 7.96 75 12.1 67 6.38 84 23.7 107 20.9 74 44.5 113 31.5 113 28.2 113 46.7 116 28.8 96 21.0 68 37.3 103 7.15 90 17.0 97 10.7 90 9.54 115 18.9 111 8.47 116
NL-TV-NCC [25]101.2 7.56 80 12.7 90 8.62 31 8.00 65 15.4 73 6.74 58 8.46 96 13.1 92 6.70 98 24.2 111 24.0 122 45.0 114 32.8 125 28.3 116 52.0 129 29.4 106 24.1 120 36.9 91 7.89 120 17.9 103 12.4 125 10.1 123 19.9 120 8.92 121
SILK [79]102.5 9.77 116 15.1 118 11.8 118 12.3 117 18.7 120 11.2 114 10.3 119 16.4 119 8.14 118 25.2 119 22.8 111 45.9 118 30.8 81 27.5 85 45.7 58 30.6 121 20.3 46 40.1 124 7.19 95 16.8 95 10.9 99 8.87 83 17.6 75 7.50 91
Bartels [41]102.5 8.10 96 13.8 109 9.94 100 8.35 73 15.8 83 8.75 93 8.11 84 12.1 67 6.97 102 24.1 110 22.7 109 47.6 123 32.4 121 27.8 105 51.1 128 35.4 128 23.0 114 46.5 128 7.18 94 14.9 44 12.3 124 9.36 112 18.0 89 9.76 125
SLK [47]107.9 11.4 121 15.4 119 14.4 122 12.4 119 18.0 114 12.6 120 10.9 123 17.6 124 8.85 120 27.8 125 25.2 125 46.6 122 30.6 51 28.1 111 43.6 1 29.0 100 21.9 91 37.0 94 8.25 124 22.4 125 11.3 111 9.33 111 18.5 107 7.91 109
GroupFlow [9]108.3 10.1 119 16.9 123 11.3 115 10.4 106 17.8 113 10.0 110 10.8 122 17.5 123 9.21 121 23.6 106 23.9 120 42.5 90 31.9 117 29.3 123 46.2 111 30.1 116 24.5 123 37.8 108 7.55 109 18.4 109 10.6 80 9.52 114 19.8 119 6.89 2
Heeger++ [104]108.5 9.81 117 17.3 124 10.4 107 11.3 111 17.2 104 9.67 106 13.6 127 23.8 128 10.2 125 26.3 122 22.8 111 44.4 109 31.8 116 28.9 122 46.3 113 29.6 108 22.0 96 37.5 105 8.17 123 19.8 120 10.9 99 9.10 100 18.2 99 7.02 12
Learning Flow [11]110.3 8.21 98 14.8 116 9.74 94 9.78 101 17.6 110 8.11 89 9.68 117 15.5 115 7.56 114 25.0 117 24.3 123 45.4 117 31.9 117 28.7 120 47.3 119 29.4 106 22.0 96 37.8 108 7.49 106 18.3 106 10.9 99 10.2 124 20.2 122 8.31 114
2bit-BM-tele [98]111.2 8.61 107 13.5 105 10.5 109 10.0 104 17.5 109 9.73 107 8.26 90 11.5 52 7.40 112 24.4 113 22.7 109 48.1 124 32.5 123 28.6 117 50.2 127 34.7 127 24.3 122 44.9 127 9.35 129 26.2 128 13.8 129 9.25 107 17.3 63 10.2 128
FFV1MT [106]115.0 9.53 114 16.7 122 10.7 112 12.6 122 18.2 118 12.8 121 13.3 126 23.5 127 10.5 126 26.3 122 22.8 111 44.4 109 31.4 112 28.2 113 46.1 105 29.8 111 20.6 60 38.1 114 8.32 126 20.5 122 11.0 103 10.5 125 20.4 123 8.45 115
Adaptive flow [45]117.6 13.2 124 15.9 120 16.2 125 14.2 126 19.9 124 16.4 126 9.02 108 13.1 92 8.03 117 26.0 121 22.8 111 48.6 125 32.4 121 29.4 125 47.9 120 30.1 116 24.6 124 38.0 112 7.55 109 16.9 96 12.2 122 9.85 117 19.5 117 8.97 124
FOLKI [16]117.8 15.0 127 17.4 125 19.4 127 14.3 127 20.9 127 14.4 124 10.7 121 19.2 126 9.99 124 29.8 127 26.8 126 53.1 128 31.3 110 28.6 117 45.8 74 30.0 113 21.7 84 38.9 118 7.85 119 19.4 117 11.6 116 9.85 117 19.2 114 8.80 119
Pyramid LK [2]120.1 16.3 128 16.1 121 21.6 128 16.0 128 20.3 125 18.2 128 16.7 128 15.3 113 14.3 128 35.7 129 36.7 129 56.5 129 32.8 125 31.2 127 45.7 58 29.7 110 22.1 100 38.2 116 8.31 125 23.1 126 11.6 116 11.8 127 25.0 127 8.22 112
PGAM+LK [55]121.1 12.7 123 18.1 126 15.3 124 12.4 119 19.1 122 13.0 122 11.1 124 18.6 125 9.33 123 29.2 126 27.5 127 51.6 127 31.7 114 28.8 121 46.7 116 31.3 124 23.7 117 40.1 124 7.67 115 19.4 117 11.4 113 9.89 119 19.5 117 8.95 122
HCIC-L [99]121.8 18.0 129 18.7 127 23.1 129 12.7 123 17.2 104 17.0 127 10.5 120 14.4 111 8.49 119 25.7 120 23.9 120 44.3 108 33.2 127 29.8 126 49.0 125 31.7 125 26.4 128 39.2 120 7.98 122 18.4 109 12.4 125 12.4 128 25.3 129 8.96 123
Periodicity [78]127.7 14.9 126 20.8 129 18.2 126 20.1 129 22.0 129 21.5 129 17.7 129 26.4 129 16.1 129 29.8 127 34.8 128 49.7 126 35.4 129 34.2 129 48.7 123 37.1 129 25.8 127 47.4 129 8.68 127 23.6 127 12.2 122 13.3 129 25.1 128 11.6 129
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 Anonymous. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015 submission 744.
[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.
* 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.