Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
A95
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   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
NNF-Local [87]9.1 7.47 3 40.1 11 3.98 3 6.49 13 30.3 3 5.60 17 5.82 4 26.1 3 4.68 16 3.86 10 53.5 6 2.99 18 9.77 1 12.4 1 5.36 3 8.67 5 31.8 3 7.03 3 5.10 18 10.1 49 3.70 7 2.31 9 5.34 11 1.21 2
NN-field [71]12.5 8.38 14 43.1 27 4.19 4 7.34 23 28.7 2 6.26 27 5.82 4 28.9 6 4.68 16 2.94 2 54.1 7 2.16 3 10.4 4 13.2 4 5.24 2 6.12 1 17.5 1 4.46 1 6.24 46 10.6 64 4.10 8 2.35 13 6.44 20 1.14 1
MDP-Flow2 [68]14.5 8.02 8 38.6 6 5.75 19 5.17 2 31.1 4 4.55 3 5.48 3 30.8 9 4.22 9 4.49 19 99.9 46 3.27 26 11.3 13 13.4 6 8.04 19 10.8 14 54.4 33 10.5 21 4.84 7 9.33 32 4.31 12 2.69 27 4.85 6 2.20 4
OFLAF [77]16.1 7.70 5 39.8 8 4.74 8 6.40 12 32.5 7 5.82 22 4.73 2 25.3 2 3.96 5 4.47 18 99.9 46 3.55 42 10.2 3 13.0 2 6.29 7 13.3 32 42.1 19 9.90 18 5.10 18 8.01 10 4.66 22 2.75 28 5.59 15 6.33 35
PMMST [114]17.3 8.63 17 31.3 1 6.03 25 8.51 37 26.8 1 8.18 61 7.50 12 28.0 5 6.07 35 4.26 16 34.8 4 3.29 27 10.9 8 13.2 4 6.26 6 10.4 12 29.9 2 9.42 13 5.00 14 10.1 49 4.37 13 3.25 37 4.40 5 3.36 12
nLayers [57]24.4 8.19 11 45.3 53 4.62 6 9.65 60 31.7 6 8.88 78 8.87 19 33.6 11 8.22 62 3.62 6 99.9 46 2.93 15 10.5 5 13.6 8 6.52 8 11.3 20 33.4 4 9.45 15 6.02 42 8.56 16 4.99 30 2.31 9 6.80 25 5.53 31
NNF-EAC [103]24.7 8.80 18 40.8 14 6.14 27 6.13 7 39.3 27 5.36 11 6.97 9 35.1 12 4.73 18 5.83 39 87.9 31 3.49 38 12.1 27 14.6 20 8.87 30 12.5 29 41.2 15 11.8 35 5.35 24 10.1 49 4.61 20 3.19 35 7.62 35 3.99 22
ComponentFusion [96]25.9 8.30 13 49.1 72 5.87 22 5.69 5 35.4 15 5.40 12 7.24 10 35.3 13 4.99 22 3.69 7 99.9 46 2.32 5 11.7 19 14.1 13 8.75 28 15.8 56 66.6 55 15.0 70 5.71 32 8.88 21 5.09 35 2.64 24 5.25 10 3.68 17
FC-2Layers-FF [74]27.8 8.26 12 41.4 18 6.27 28 8.85 41 37.9 22 7.81 45 6.02 7 31.8 10 6.25 38 3.91 11 88.8 34 2.86 13 11.0 11 13.7 10 7.20 10 16.5 64 40.4 11 16.3 84 7.14 65 10.7 68 6.61 55 2.15 3 3.87 1 2.77 6
FESL [72]28.3 7.69 4 40.2 12 4.90 9 11.0 78 48.5 51 9.07 80 10.5 28 42.1 25 6.42 40 3.60 5 99.9 46 2.55 8 10.9 8 13.6 8 8.86 29 11.1 18 36.4 6 10.6 22 6.73 59 10.2 53 5.95 45 2.51 21 5.37 13 3.35 11
TC/T-Flow [76]29.0 9.01 21 38.1 4 3.81 1 6.64 15 55.1 69 4.62 4 8.13 15 46.4 37 4.20 8 5.32 32 99.9 46 2.88 14 11.5 16 14.1 13 7.28 12 8.85 6 38.5 9 9.44 14 5.85 38 10.7 68 10.0 95 3.61 45 10.0 50 8.53 65
LME [70]29.2 7.85 7 42.7 25 6.01 24 5.33 3 34.6 10 4.91 7 14.6 50 54.5 48 40.7 101 4.66 21 73.0 13 3.25 23 11.5 16 13.8 11 9.65 53 11.6 22 70.4 64 12.1 40 5.14 20 9.97 47 4.51 19 2.86 29 6.45 21 4.29 27
HAST [109]29.8 6.42 1 43.9 36 3.97 2 7.16 19 33.1 8 5.92 24 3.76 1 23.5 1 2.83 1 3.36 3 99.9 46 2.08 2 10.0 2 13.0 2 4.83 1 16.7 69 59.3 40 19.4 99 11.3 108 12.9 94 17.6 118 2.67 26 4.13 3 2.93 8
WLIF-Flow [93]31.5 8.04 9 40.7 13 5.53 16 7.98 32 34.6 10 7.20 39 8.75 18 40.5 20 5.74 32 4.27 17 96.8 44 2.94 16 13.4 77 16.1 85 9.77 57 13.5 36 41.3 17 11.8 35 5.65 30 9.12 27 5.96 46 2.29 8 7.30 28 6.96 44
ALD-Flow [66]32.0 8.18 10 41.6 23 4.51 5 6.32 10 54.8 67 5.03 9 10.7 32 61.8 55 4.24 10 4.24 15 99.9 46 2.61 9 11.7 19 14.3 15 7.21 11 10.8 14 61.4 43 9.93 19 5.96 41 9.55 37 9.77 94 3.87 49 15.7 59 9.38 77
PMF [73]32.1 9.38 29 48.9 70 4.67 7 7.10 17 37.5 19 5.58 16 7.91 13 30.0 8 4.06 6 4.89 28 99.9 46 3.29 27 10.6 7 14.0 12 5.76 5 12.4 28 54.8 34 11.5 32 11.2 107 17.9 126 11.1 100 2.06 1 4.95 9 4.00 23
Layers++ [37]32.8 9.07 22 44.4 39 8.41 63 8.47 36 31.5 5 8.03 54 5.85 6 37.9 15 6.02 34 3.76 9 62.6 8 2.79 11 10.5 5 13.5 7 8.22 24 17.6 77 55.0 35 14.5 67 7.44 70 10.9 72 5.70 44 2.27 7 4.86 7 9.14 70
3DFlow [135]33.0 9.37 27 41.4 18 5.02 11 7.10 17 38.0 23 5.51 15 7.41 11 53.2 46 3.81 4 4.74 22 14.8 1 4.00 54 12.0 25 15.2 43 8.89 32 19.9 92 60.3 41 18.1 96 8.06 78 9.24 31 10.1 96 2.26 5 4.12 2 2.04 3
Efficient-NL [60]33.8 8.40 15 43.6 33 5.38 14 9.12 45 37.4 18 7.83 47 11.1 36 56.6 50 6.16 36 5.71 36 99.9 46 3.32 30 11.3 13 14.7 23 7.66 13 16.6 68 37.6 7 12.7 48 6.93 63 10.8 70 5.98 48 2.89 31 5.47 14 2.90 7
RNLOD-Flow [121]34.1 7.26 2 38.7 7 5.25 13 7.65 28 43.0 34 6.20 26 12.7 43 75.2 61 4.59 14 3.52 4 99.9 46 2.46 6 11.4 15 14.9 32 7.74 15 16.2 58 40.2 10 16.2 81 8.20 80 12.2 86 7.63 72 2.49 20 5.98 18 7.10 47
SVFilterOh [111]34.8 8.96 20 55.2 98 5.63 17 7.20 20 37.8 21 6.39 30 6.18 8 43.0 28 5.02 23 3.71 8 99.9 46 2.49 7 11.1 12 14.3 15 5.54 4 13.5 36 50.6 32 14.1 62 10.1 99 16.8 122 12.4 110 2.20 4 4.91 8 2.50 5
TC-Flow [46]35.2 8.59 16 41.0 16 5.12 12 5.47 4 45.6 42 4.31 2 10.2 25 94.7 74 3.49 2 6.08 45 99.9 46 3.50 39 11.9 24 14.5 18 7.90 18 11.9 26 61.7 45 11.5 32 5.72 33 9.85 43 11.5 104 4.02 52 15.0 57 9.14 70
AGIF+OF [85]35.2 8.89 19 44.1 37 6.77 32 10.2 66 44.4 38 8.51 74 10.2 25 43.5 30 6.63 44 4.80 25 99.9 46 3.25 23 11.7 19 14.7 23 9.52 49 13.7 39 40.9 12 12.6 45 5.73 35 8.99 22 5.96 46 2.36 15 7.50 31 7.55 50
IROF++ [58]37.7 9.29 26 45.0 51 6.30 29 9.55 57 43.0 34 8.20 62 10.8 33 43.1 29 7.57 54 6.28 49 99.9 46 3.90 49 12.2 31 14.8 28 9.41 47 15.2 54 44.1 27 14.5 67 5.27 21 9.48 35 3.69 6 2.62 23 6.48 22 4.14 24
PH-Flow [101]37.7 10.2 38 44.6 43 7.86 45 9.41 52 42.0 33 8.11 57 8.41 17 38.9 17 7.40 53 6.39 51 99.9 46 3.93 51 11.8 22 14.5 18 7.72 14 13.8 40 42.9 23 13.1 51 7.21 66 10.3 56 7.61 71 2.34 12 4.20 4 4.20 25
Correlation Flow [75]37.8 9.27 25 38.3 5 5.40 15 6.33 11 36.7 16 4.85 6 18.4 54 99.9 83 3.58 3 4.87 27 35.8 5 3.47 35 12.9 57 15.8 69 9.17 41 16.0 57 68.6 58 16.5 89 6.59 55 9.85 43 7.93 79 2.88 30 7.57 34 3.06 9
Classic+CPF [83]38.2 9.64 32 43.4 29 7.93 48 9.43 53 46.1 45 7.82 46 10.6 31 51.0 42 6.68 45 5.09 30 99.9 46 3.22 22 12.0 25 15.2 43 9.15 39 14.7 48 34.4 5 13.4 55 6.42 50 10.1 49 6.89 60 2.26 5 6.77 24 7.08 46
CostFilter [40]41.1 10.5 44 46.8 62 6.98 36 7.51 25 38.1 24 6.31 29 9.22 20 29.7 7 4.74 19 5.86 41 99.9 46 3.97 53 10.9 8 14.3 15 6.77 9 13.4 33 56.1 36 12.3 42 11.6 111 20.5 130 14.2 112 2.12 2 8.52 41 6.71 41
OAR-Flow [125]42.5 11.1 50 48.8 69 5.85 20 9.88 62 82.9 104 6.47 31 27.3 71 99.9 83 8.06 58 6.75 57 99.9 46 2.80 12 12.4 37 15.1 41 8.20 23 10.3 10 58.1 38 8.37 9 4.07 2 8.06 12 5.45 41 4.81 60 9.74 49 6.36 36
IIOF-NLDP [131]42.7 12.0 57 43.5 31 5.86 21 9.35 48 35.0 12 6.81 33 11.2 37 88.4 70 4.51 12 6.09 46 28.8 3 4.09 58 14.6 102 18.4 115 9.71 54 14.6 47 66.2 54 14.7 69 4.90 12 9.54 36 4.82 28 3.09 33 7.73 37 3.18 10
ProbFlowFields [128]43.4 16.3 85 53.8 90 10.9 97 7.72 29 40.6 30 7.12 35 14.1 48 45.2 36 10.5 67 6.67 56 62.6 8 4.39 65 12.9 57 15.4 54 9.64 52 10.1 9 63.2 50 10.8 23 4.86 9 8.16 14 4.69 24 3.36 39 9.23 46 3.72 18
Sparse-NonSparse [56]43.5 9.96 33 44.2 38 8.85 71 9.39 51 50.6 56 8.08 56 10.1 24 43.7 32 7.21 49 6.10 47 88.2 32 3.41 33 12.5 42 15.5 62 8.96 33 16.3 60 41.9 18 16.2 81 6.48 52 9.05 24 6.27 51 2.33 11 7.33 29 7.76 58
MLDP_OF [89]43.9 11.8 56 41.7 24 8.40 62 6.97 16 35.2 14 5.88 23 11.3 40 65.3 57 5.23 26 4.76 24 99.9 46 3.09 19 12.2 31 14.8 28 8.87 30 13.4 33 48.1 29 17.2 94 10.0 98 10.9 72 18.1 119 3.58 44 8.07 40 4.53 29
LSM [39]44.2 10.0 36 42.9 26 8.48 64 9.36 50 49.6 54 7.99 51 10.5 28 43.6 31 6.80 46 5.80 37 88.6 33 3.38 32 12.5 42 15.4 54 9.03 35 16.5 64 42.3 21 16.3 84 6.94 64 9.84 40 6.71 56 2.42 18 7.96 39 7.72 55
Ramp [62]44.2 10.2 38 44.4 39 8.09 57 9.47 54 46.1 45 8.17 60 9.51 22 42.4 27 6.88 48 5.40 33 99.9 46 3.53 40 12.5 42 15.2 43 9.71 54 16.7 69 42.1 19 16.5 89 6.76 60 10.0 48 7.07 63 2.46 19 5.84 17 5.24 30
MDP-Flow [26]46.8 11.2 51 43.1 27 9.86 89 8.14 35 35.1 13 8.21 63 11.2 37 42.1 25 9.44 65 6.41 52 99.9 46 4.20 62 12.2 31 14.6 20 10.0 68 11.7 24 63.6 51 9.60 16 5.56 28 10.9 72 4.39 14 5.78 68 99.9 98 8.99 67
FMOF [94]47.2 9.17 23 43.6 33 8.04 54 10.0 64 48.1 48 8.48 72 8.35 16 38.3 16 6.49 42 5.08 29 99.9 46 3.45 34 12.6 48 15.4 54 9.19 42 18.1 83 41.2 15 15.5 75 6.67 58 10.6 64 7.47 69 3.00 32 16.1 60 7.74 56
Classic+NL [31]47.5 10.1 37 44.9 49 8.90 72 9.49 55 51.6 59 7.87 48 9.93 23 43.9 34 7.31 52 6.07 44 99.9 46 3.78 47 12.5 42 15.3 50 9.06 36 17.1 73 41.0 13 15.8 78 7.32 69 10.8 70 6.80 59 2.35 13 5.62 16 7.69 54
OFH [38]47.9 12.6 63 43.4 29 9.45 80 7.30 22 64.4 79 5.27 10 27.6 72 99.9 83 4.87 21 6.60 55 99.9 46 3.74 45 12.4 37 14.7 23 9.62 51 15.5 55 74.1 69 15.6 77 4.60 6 9.39 33 4.64 21 5.39 64 26.0 69 6.68 40
IROF-TV [53]48.1 10.4 42 44.5 42 8.16 58 9.69 61 51.1 58 8.44 67 12.6 42 46.8 38 7.27 51 6.80 58 87.5 30 3.93 51 13.0 63 15.7 66 10.4 73 18.3 85 86.9 91 13.7 59 4.44 5 7.40 5 3.05 4 2.60 22 7.55 33 7.56 51
TV-L1-MCT [64]48.2 9.57 30 44.7 45 8.66 67 10.9 77 48.1 48 9.11 81 11.8 41 58.1 52 6.61 43 4.74 22 99.9 46 3.34 31 12.9 57 15.2 43 9.89 62 17.8 81 47.8 28 16.0 80 5.28 22 8.09 13 7.71 73 3.33 38 7.26 27 7.53 49
CombBMOF [113]48.4 12.5 62 41.3 17 6.50 31 8.58 39 36.9 17 6.88 34 10.9 34 35.9 14 5.21 25 10.4 77 85.0 28 5.90 86 11.6 18 15.2 43 8.15 21 27.3 105 60.9 42 35.6 119 9.20 90 14.7 110 6.75 58 3.17 34 7.53 32 4.20 25
NL-TV-NCC [25]48.4 10.7 46 40.8 14 6.45 30 8.52 38 41.1 31 6.30 28 11.2 37 93.6 73 4.18 7 5.99 43 75.9 16 4.02 55 13.2 69 16.2 91 10.1 70 16.7 69 70.9 65 16.3 84 6.56 54 9.91 46 7.05 62 4.76 58 16.9 61 3.56 15
COFM [59]48.5 9.37 27 55.5 99 6.86 34 7.28 21 44.2 37 6.17 25 14.3 49 47.6 41 8.22 62 4.15 14 99.9 46 2.23 4 13.2 69 16.2 91 12.2 94 17.6 77 75.4 71 15.5 75 6.20 45 8.77 20 7.35 67 3.62 46 5.35 12 6.43 38
Adaptive [20]49.2 10.2 38 46.1 56 4.95 10 9.63 58 55.4 70 7.80 44 36.7 86 99.9 83 7.64 55 6.15 48 78.7 18 2.96 17 12.1 27 14.8 28 9.09 37 12.3 27 85.8 89 6.06 2 8.72 85 12.5 90 4.97 29 3.55 43 34.8 73 9.13 69
AggregFlow [97]50.5 13.2 65 62.1 118 6.79 33 14.9 88 73.1 88 10.6 88 26.8 70 55.1 49 20.5 90 5.48 34 99.9 46 3.67 43 12.5 42 15.0 35 7.76 16 8.55 4 38.2 8 8.90 11 5.78 36 10.6 64 4.74 26 5.43 65 8.53 42 7.58 52
S2F-IF [123]51.8 20.0 97 51.4 79 9.91 90 9.64 59 48.3 50 7.93 49 19.7 56 41.7 23 13.6 79 9.98 74 84.3 25 5.40 79 12.8 55 15.3 50 9.92 65 10.9 17 62.4 48 10.9 26 5.00 14 10.4 59 5.30 39 3.71 47 8.55 43 3.87 20
RFlow [90]52.0 11.5 54 45.3 53 8.80 70 6.22 9 49.2 53 5.41 13 26.2 68 99.9 83 5.04 24 4.14 13 99.9 46 3.11 20 12.6 48 15.0 35 9.87 60 16.5 64 83.2 84 13.8 61 6.62 56 8.58 17 6.16 49 6.33 73 99.9 98 12.0 96
Sparse Occlusion [54]52.4 9.98 35 41.5 22 7.82 44 9.00 44 40.5 29 8.28 65 13.5 46 85.5 67 5.96 33 5.82 38 99.9 46 3.90 49 13.0 63 15.9 70 9.77 57 13.8 40 49.9 31 12.3 42 13.6 122 15.7 118 7.81 76 3.51 40 9.05 44 6.42 37
Complementary OF [21]52.5 13.6 69 46.2 57 9.35 77 6.20 8 50.4 55 4.92 8 12.8 44 58.8 54 5.45 28 7.89 65 99.9 46 5.59 81 12.3 35 14.6 20 9.99 67 18.9 87 69.9 62 14.3 65 5.44 25 7.80 7 7.78 75 6.13 71 26.9 70 9.66 84
S2D-Matching [84]52.5 9.96 33 53.0 87 8.51 65 9.53 56 53.0 61 7.94 50 20.5 58 99.9 83 6.80 46 5.30 31 83.0 20 3.53 40 12.4 37 15.2 43 9.16 40 17.3 74 41.1 14 16.8 92 7.75 74 10.5 62 7.90 78 2.36 15 6.34 19 9.58 82
FlowFields+ [130]52.5 20.3 98 52.0 81 10.3 93 10.3 68 44.8 40 8.44 67 19.5 55 40.2 19 14.1 80 10.2 76 66.6 11 6.28 91 12.8 55 15.4 54 9.97 66 10.3 10 61.8 46 10.2 20 4.85 8 10.9 72 4.79 27 3.97 51 12.8 54 3.85 19
Occlusion-TV-L1 [63]53.7 10.4 42 44.9 49 6.90 35 8.77 40 53.3 63 7.54 41 33.8 82 99.9 83 7.96 56 5.88 42 99.9 46 3.48 37 13.6 85 16.3 93 10.6 76 9.50 7 80.1 77 8.60 10 6.12 44 8.69 19 4.39 14 6.52 76 99.9 98 9.37 74
FlowFields [110]53.7 20.3 98 52.3 83 10.2 91 10.2 66 49.0 52 8.46 70 20.3 57 40.5 20 14.7 81 10.8 81 76.6 17 6.16 89 12.9 57 15.4 54 10.0 68 11.1 18 69.9 62 11.0 28 4.97 13 8.63 18 5.12 36 4.04 54 14.0 55 3.98 21
2DHMM-SAS [92]53.8 10.3 41 44.8 47 8.03 53 10.5 73 52.4 60 8.21 63 21.6 59 97.4 78 8.20 61 6.88 59 99.9 46 3.86 48 12.4 37 15.0 35 9.87 60 17.7 79 43.3 25 15.9 79 6.81 61 10.2 53 7.15 66 2.65 25 7.68 36 7.29 48
HBM-GC [105]53.9 10.9 48 57.5 107 7.03 38 9.35 48 40.2 28 8.80 76 8.09 14 52.3 44 6.42 40 6.91 60 84.3 25 6.17 90 11.8 22 14.7 23 8.40 25 14.7 48 43.2 24 12.6 45 9.81 97 17.8 125 8.50 85 3.54 42 10.1 51 10.1 88
Aniso-Texture [82]54.7 7.75 6 40.0 10 5.87 22 7.36 24 41.5 32 7.19 38 41.3 94 99.9 83 6.22 37 2.73 1 65.4 10 1.92 1 12.9 57 15.3 50 10.1 70 29.2 107 99.9 104 16.5 89 11.8 114 14.9 114 8.22 82 3.80 48 12.6 53 8.58 66
SimpleFlow [49]55.0 11.3 53 46.6 59 9.79 88 10.7 75 45.0 41 9.15 82 23.1 62 99.9 83 8.38 64 8.00 67 99.9 46 3.72 44 12.7 52 15.5 62 9.36 46 16.3 60 42.6 22 15.3 74 5.91 40 9.61 38 5.39 40 2.39 17 7.08 26 9.41 78
ACK-Prior [27]55.1 10.7 46 37.9 3 7.90 47 6.01 6 38.5 25 4.80 5 10.2 25 41.5 22 4.35 11 4.56 20 99.9 46 3.75 46 13.2 69 15.9 70 11.3 85 27.3 105 82.2 80 23.1 106 11.6 111 14.9 114 16.2 116 6.43 74 15.5 58 6.11 33
EPPM w/o HM [88]56.2 15.3 81 41.4 18 8.08 56 7.60 26 33.9 9 5.66 19 13.0 45 47.0 39 5.57 29 8.73 71 99.9 46 4.81 74 12.6 48 15.7 66 10.8 79 18.6 86 62.9 49 16.4 87 11.9 117 12.5 90 17.2 117 3.20 36 7.49 30 6.00 32
PGM-C [120]56.8 20.6 101 54.2 93 9.59 84 10.1 65 60.8 74 8.47 71 22.3 61 44.3 35 14.8 83 10.7 80 99.9 46 4.15 60 13.1 67 15.4 54 9.90 63 11.8 25 64.6 53 12.0 39 4.86 9 7.96 8 5.01 32 4.78 59 14.4 56 7.01 45
ROF-ND [107]58.1 12.0 57 39.9 9 8.22 61 6.49 13 45.6 42 5.49 14 13.5 46 92.7 71 4.83 20 8.05 68 23.7 2 5.54 80 14.2 97 17.5 104 11.2 84 20.1 94 72.0 67 15.0 70 13.0 120 13.3 100 10.5 99 3.52 41 6.67 23 3.36 12
ComplOF-FED-GPU [35]58.6 13.2 65 44.7 45 7.95 49 9.18 46 82.6 103 5.63 18 15.3 51 58.5 53 5.67 30 7.59 63 99.9 46 4.68 70 12.3 35 14.8 28 9.20 43 18.2 84 83.8 85 16.4 87 7.54 72 9.84 40 11.1 100 5.44 66 31.6 72 7.74 56
Steered-L1 [118]60.5 9.19 24 36.3 2 6.06 26 4.59 1 39.2 26 4.30 1 9.30 21 52.3 44 4.57 13 4.86 26 99.9 46 3.30 29 13.6 85 15.9 70 12.3 95 24.7 104 77.0 73 20.2 100 15.1 125 13.7 105 40.0 126 14.7 106 91.5 96 20.9 108
CPM-Flow [116]60.8 20.6 101 54.3 94 9.58 82 10.3 68 62.5 77 8.50 73 21.9 60 43.8 33 14.7 81 10.6 79 99.9 46 4.06 56 13.2 69 15.4 54 9.85 59 12.6 30 68.9 59 13.3 52 5.02 16 9.16 29 5.04 34 5.27 62 19.2 62 9.63 83
EpicFlow [102]61.4 20.6 101 54.1 92 9.59 84 10.3 68 62.9 78 8.55 75 26.3 69 99.4 82 15.1 85 10.4 77 99.9 46 4.07 57 13.1 67 15.4 54 9.90 63 11.6 22 67.3 56 11.9 38 4.86 9 7.97 9 4.99 30 5.34 63 19.2 62 9.74 86
DeepFlow2 [108]61.6 14.3 74 47.4 65 7.03 38 10.4 71 77.1 93 8.01 52 23.3 63 99.9 83 11.8 73 16.1 89 99.9 46 4.41 66 12.4 37 15.0 35 8.16 22 13.4 33 68.4 57 14.2 63 5.65 30 9.07 26 8.50 85 8.52 90 92.9 97 10.6 91
SRR-TVOF-NL [91]61.8 14.4 77 46.7 60 8.18 60 13.1 83 74.0 90 8.44 67 24.1 65 63.2 56 11.9 74 6.51 54 85.1 29 3.25 23 12.1 27 15.0 35 10.3 72 17.5 75 61.6 44 13.4 55 10.4 103 12.3 88 8.92 88 5.52 67 7.83 38 7.58 52
TCOF [69]63.0 13.6 69 44.8 47 8.02 52 9.90 63 54.6 66 8.02 53 31.3 78 99.9 83 15.4 87 6.49 53 82.4 19 4.76 72 14.9 106 18.0 112 9.50 48 9.71 8 48.3 30 12.6 45 10.1 99 12.7 92 8.96 89 4.29 55 9.21 45 6.80 42
F-TV-L1 [15]64.3 15.6 82 47.4 65 13.4 102 18.8 97 99.1 113 11.6 89 43.1 98 99.9 83 11.3 72 14.7 87 99.9 46 7.03 94 12.2 31 14.9 32 9.00 34 13.5 36 99.9 104 7.56 6 6.41 49 10.5 62 4.23 10 3.91 50 80.3 87 3.38 14
DPOF [18]64.4 17.4 93 49.1 72 7.77 43 12.3 79 45.6 42 8.91 79 10.9 34 26.6 4 8.09 59 7.81 64 99.3 45 5.31 76 13.5 81 16.0 81 11.0 82 17.5 75 61.8 46 12.2 41 13.1 121 10.9 72 18.1 119 5.04 61 9.50 48 4.49 28
TF+OM [100]64.6 12.1 59 51.3 78 7.13 40 8.92 43 44.4 38 8.13 59 33.8 82 54.4 47 45.8 104 6.28 49 90.1 36 4.63 69 12.7 52 15.2 43 10.6 76 18.9 87 99.9 104 11.3 30 7.81 75 14.2 107 6.33 52 7.09 84 43.5 75 8.22 61
Aniso. Huber-L1 [22]65.1 11.7 55 43.8 35 8.16 58 13.6 85 66.3 81 12.0 91 35.9 84 99.9 83 10.5 67 10.0 75 72.9 12 5.00 75 13.4 77 16.3 93 9.61 50 15.1 53 63.7 52 7.96 7 8.96 88 11.6 80 7.95 80 4.02 52 26.9 70 7.97 60
TV-L1-improved [17]67.0 10.9 48 45.2 52 7.42 41 8.12 33 54.0 64 6.79 32 36.5 85 99.9 83 7.26 50 5.84 40 99.9 46 3.15 21 13.2 69 15.9 70 9.11 38 22.1 98 99.9 104 20.8 101 9.59 95 13.3 100 9.04 90 6.19 72 88.8 92 9.71 85
SIOF [67]68.2 10.6 45 49.7 76 7.01 37 14.8 87 85.9 106 8.40 66 49.7 107 98.3 79 49.2 107 12.0 84 99.9 46 5.88 84 13.5 81 15.9 70 10.8 79 16.3 60 74.2 70 13.6 58 5.51 27 9.02 23 4.42 17 6.52 76 19.5 65 9.85 87
CRTflow [80]69.6 15.0 79 46.3 58 7.89 46 8.87 42 54.9 68 7.15 36 30.1 74 99.9 83 8.03 57 9.30 73 99.9 46 4.50 68 13.0 63 15.7 66 8.05 20 32.5 111 99.9 104 34.3 118 6.62 56 9.72 39 7.52 70 9.30 94 99.9 98 14.7 101
DeepFlow [86]70.2 14.7 78 49.0 71 9.78 87 12.9 81 79.3 97 9.80 84 30.1 74 96.1 77 24.4 92 21.4 98 99.9 46 5.36 78 12.5 42 15.1 41 8.59 26 14.0 43 71.9 66 15.1 73 5.46 26 8.01 10 8.73 87 14.2 104 99.9 98 15.7 105
Brox et al. [5]70.2 16.0 83 49.2 74 12.0 99 12.3 79 80.4 98 10.3 86 23.7 64 73.1 60 13.2 76 24.2 99 99.9 46 4.23 63 14.7 103 16.8 98 15.4 116 10.7 13 96.7 97 9.71 17 5.88 39 9.05 24 3.01 3 8.78 91 67.7 83 9.37 74
LocallyOriented [52]71.2 17.0 92 55.7 100 8.00 51 17.0 94 82.3 102 12.1 92 42.4 97 99.9 83 14.8 83 9.13 72 89.2 35 4.79 73 13.4 77 16.1 85 9.20 43 10.8 14 58.1 38 11.8 35 6.89 62 10.6 64 7.14 65 7.78 88 74.9 84 9.42 79
BriefMatch [124]71.6 9.63 31 44.4 39 5.74 18 7.64 27 51.0 57 5.70 20 10.5 28 39.2 18 4.63 15 3.95 12 99.9 46 2.72 10 16.2 117 17.6 108 33.0 128 41.4 123 99.4 103 43.4 125 12.7 119 13.2 98 67.6 130 79.5 123 99.9 98 99.9 126
Dynamic MRF [7]72.9 14.0 73 50.7 77 9.58 82 7.75 30 85.7 105 5.76 21 31.5 79 99.9 83 5.23 26 7.97 66 99.9 46 4.10 59 13.0 63 15.6 65 10.7 78 30.4 110 99.9 104 29.5 115 5.64 29 7.52 6 9.61 93 67.3 121 99.9 98 66.7 121
Classic++ [32]73.3 11.2 51 49.4 75 9.13 73 9.34 47 68.4 83 8.11 57 30.7 77 95.1 76 10.2 66 5.59 35 99.9 46 3.47 35 13.5 81 16.1 85 10.4 73 19.7 91 99.9 104 17.6 95 8.38 81 11.5 79 8.30 84 7.20 86 99.9 98 9.54 81
Rannacher [23]75.7 13.8 72 47.5 67 10.8 96 10.5 73 62.0 76 8.84 77 41.1 93 99.9 83 11.0 70 8.49 69 99.9 46 4.28 64 13.5 81 16.1 85 9.72 56 22.5 100 99.9 104 17.0 93 7.66 73 9.88 45 7.82 77 4.72 57 75.1 85 9.37 74
SuperFlow [81]75.7 14.3 74 47.0 64 9.26 75 19.5 99 58.7 73 17.9 99 45.9 101 99.9 83 56.1 110 19.0 96 99.9 46 5.88 84 13.3 76 16.1 85 12.6 99 11.5 21 74.0 68 8.27 8 9.24 91 12.9 94 4.70 25 8.27 89 89.2 94 8.28 62
CBF [12]76.5 12.2 61 41.4 18 8.65 66 16.5 91 47.1 47 16.6 98 24.7 66 88.1 69 12.9 75 11.0 83 99.9 46 4.18 61 14.9 106 17.5 104 14.0 111 15.0 52 79.8 76 8.97 12 14.9 124 15.1 116 15.9 115 5.78 68 63.0 82 10.1 88
p-harmonic [29]77.0 15.1 80 48.5 68 14.1 104 10.4 71 53.1 62 9.31 83 41.9 95 99.9 83 15.1 85 19.4 97 99.9 46 10.6 103 12.7 52 14.9 32 11.8 88 18.0 82 85.6 88 18.4 98 7.85 76 10.4 59 5.46 42 6.98 83 99.9 98 9.28 73
Local-TV-L1 [65]77.4 16.5 87 52.3 83 11.7 98 27.7 105 96.9 110 22.5 104 68.8 114 99.9 83 47.5 105 34.6 108 99.9 46 7.04 95 12.6 48 15.0 35 9.25 45 17.7 79 84.7 86 13.7 59 5.09 17 7.36 4 5.03 33 20.7 109 88.8 92 29.4 113
CLG-TV [48]78.2 12.1 59 43.5 31 9.42 79 14.1 86 60.9 75 13.2 94 33.2 81 99.9 83 11.2 71 10.8 81 84.7 27 5.82 83 14.8 105 17.9 110 12.1 92 13.8 40 99.9 104 11.3 30 10.9 105 14.2 107 9.22 91 6.69 80 99.9 98 8.52 64
FlowNet2 [122]78.6 32.0 118 68.0 127 14.9 106 35.2 110 77.9 96 29.8 114 32.9 80 51.2 43 35.4 99 16.3 90 99.9 46 10.5 102 13.2 69 15.9 70 12.0 90 14.1 44 99.9 104 10.8 23 8.84 87 20.1 127 4.66 22 4.49 56 9.46 47 3.65 16
OFRF [134]79.1 13.1 64 58.6 111 9.77 86 49.6 120 99.9 114 43.7 121 49.2 105 99.9 83 32.0 97 16.3 90 96.4 42 10.0 101 12.1 27 14.7 23 7.87 17 14.9 51 43.6 26 13.3 52 8.66 84 12.0 85 11.8 107 21.9 111 19.7 66 36.6 115
TriFlow [95]79.1 16.1 84 57.1 105 7.97 50 13.3 84 65.2 80 12.3 93 48.8 104 99.9 83 61.8 114 7.03 61 91.4 38 5.33 77 13.4 77 15.3 50 11.4 86 14.3 46 76.1 72 13.3 52 22.7 130 14.3 109 26.7 123 5.93 70 11.8 52 7.86 59
DF-Auto [115]79.5 20.5 100 55.9 102 9.21 74 22.7 101 74.8 91 19.3 102 44.7 100 93.5 72 57.8 112 27.1 102 99.9 46 5.70 82 15.0 109 18.9 122 11.8 88 7.13 2 57.9 37 7.09 4 10.2 102 13.9 106 4.23 10 8.94 92 54.0 80 9.21 72
SegOF [10]79.6 22.8 110 54.8 95 15.4 108 27.9 106 56.0 71 27.4 109 39.3 88 87.9 68 33.2 98 37.5 109 75.4 15 22.3 109 14.4 100 16.3 93 14.7 114 21.7 96 99.9 104 24.5 108 4.09 3 7.28 2 2.18 2 6.79 81 48.3 78 6.93 43
EPMNet [133]80.0 29.4 116 62.1 118 16.4 110 36.2 111 95.3 109 29.0 113 30.2 76 47.4 40 30.9 96 18.3 94 99.9 46 11.1 104 13.2 69 15.9 70 12.0 90 14.1 44 99.9 104 10.8 23 8.19 79 16.9 123 4.18 9 6.63 79 19.4 64 6.18 34
Bartels [41]81.1 13.3 68 55.0 96 10.2 91 8.13 34 43.2 36 7.67 42 18.1 53 69.0 59 6.30 39 8.49 69 99.9 46 6.05 88 13.9 91 16.1 85 13.9 109 21.8 97 99.9 104 21.5 104 10.6 104 13.5 102 20.3 121 12.3 99 99.9 98 26.9 111
TriangleFlow [30]81.1 13.2 65 46.8 62 9.41 78 10.8 76 73.2 89 7.30 40 26.1 67 99.9 83 5.70 31 7.23 62 99.9 46 4.46 67 17.0 122 21.3 127 15.2 115 23.0 101 69.8 61 22.9 105 9.71 96 16.1 119 9.40 92 6.89 82 23.8 67 11.5 94
Fusion [6]82.5 16.3 85 53.8 90 12.5 100 7.93 31 37.7 20 7.75 43 15.6 52 41.8 24 13.2 76 13.5 85 83.1 21 7.77 98 15.4 111 18.5 116 14.2 113 33.1 112 89.0 92 24.8 110 11.8 114 14.7 110 8.27 83 11.4 98 99.9 98 13.3 98
CNN-flow-warp+ref [117]83.8 21.3 106 57.3 106 15.1 107 16.8 93 54.4 65 15.9 97 41.0 92 99.9 83 28.8 93 28.6 104 99.9 46 7.45 97 14.0 94 15.9 70 14.0 111 16.5 64 84.8 87 10.9 26 5.30 23 8.23 15 8.13 81 99.9 127 99.9 98 99.9 126
StereoFlow [44]84.8 48.0 129 74.6 134 41.1 129 61.0 125 99.9 114 51.6 124 71.4 115 99.9 83 63.9 116 65.6 123 99.9 46 61.2 123 16.2 117 15.9 70 22.6 123 7.22 3 77.8 75 7.39 5 3.38 1 7.35 3 1.99 1 7.18 85 99.9 98 11.4 93
LDOF [28]85.8 17.9 95 53.5 89 8.72 68 18.7 96 92.6 108 11.8 90 29.5 73 67.1 58 20.9 91 29.0 105 99.9 46 8.92 100 14.2 97 16.4 96 13.7 106 18.9 87 97.5 101 15.0 70 6.26 48 10.3 56 10.1 96 10.4 96 99.9 98 10.3 90
StereoOF-V1MT [119]86.5 16.5 87 46.0 55 9.27 76 18.9 98 99.9 114 7.16 37 40.5 90 99.9 83 8.18 60 14.7 87 96.4 42 6.30 92 14.1 96 16.8 98 12.9 101 29.9 108 91.4 94 27.0 113 5.78 36 10.4 59 10.4 98 99.9 127 99.9 98 99.9 126
FlowNetS+ft+v [112]87.0 16.5 87 52.1 82 8.06 55 17.4 95 76.9 92 13.4 95 46.3 102 99.9 83 30.4 95 29.8 106 99.9 46 13.8 106 15.5 112 18.5 116 13.8 108 12.7 31 89.5 93 11.7 34 9.24 91 13.5 102 12.1 108 7.39 87 57.9 81 9.52 80
Learning Flow [11]87.5 13.7 71 52.8 85 7.67 42 12.9 81 87.1 107 10.0 85 40.5 90 95.0 75 13.4 78 38.1 110 99.9 46 4.74 71 17.1 124 21.7 128 12.5 98 24.2 103 99.9 104 13.5 57 7.95 77 12.7 92 6.98 61 23.9 114 99.9 98 14.9 102
Shiralkar [42]87.5 16.8 90 44.6 43 9.46 81 16.5 91 98.8 112 8.05 55 42.0 96 99.9 83 10.8 69 18.4 95 99.9 46 8.02 99 12.9 57 15.5 62 10.4 73 30.2 109 99.9 104 25.1 111 11.4 110 11.8 83 15.8 114 22.2 112 99.9 98 17.5 107
Ad-TV-NDC [36]88.2 31.0 117 53.3 88 33.1 126 70.2 126 99.9 114 49.0 123 93.2 127 99.9 83 54.0 109 38.9 111 95.0 40 29.4 112 13.8 90 17.3 103 8.71 27 14.7 48 77.1 74 13.0 50 6.24 46 9.84 40 5.19 38 46.4 119 76.4 86 54.0 119
Second-order prior [8]89.8 14.3 74 46.7 60 8.79 69 15.2 89 72.5 87 10.5 87 39.2 87 99.9 83 16.6 89 17.5 92 99.9 46 6.01 87 14.4 100 17.5 104 10.8 79 38.6 121 99.9 104 24.7 109 11.3 108 12.2 86 11.2 102 9.13 93 89.5 95 15.6 104
Filter Flow [19]89.8 21.6 108 57.7 108 14.4 105 24.6 103 77.5 95 18.1 100 54.3 109 80.8 62 66.3 120 52.8 116 91.0 37 46.5 117 13.6 85 16.0 81 12.3 95 17.0 72 69.6 60 14.2 63 12.0 118 16.1 119 7.39 68 6.58 78 37.5 74 8.36 63
2D-CLG [1]92.1 46.1 127 67.5 126 28.2 122 39.5 115 77.3 94 38.9 117 93.9 129 99.9 83 74.9 125 53.6 117 99.9 46 51.0 119 13.9 91 15.9 70 13.5 105 24.0 102 99.9 104 21.2 102 4.28 4 7.24 1 4.50 18 12.7 100 99.9 98 11.6 95
GraphCuts [14]92.1 21.7 109 52.8 85 10.4 94 39.2 114 99.9 114 23.1 105 39.7 89 58.0 51 49.6 108 25.6 101 74.6 14 7.31 96 13.6 85 15.9 70 13.2 104 37.8 118 97.6 102 16.2 81 9.36 93 11.4 77 11.7 105 10.3 95 99.9 98 15.0 103
HBpMotionGpu [43]93.0 19.5 96 63.6 120 13.5 103 31.0 107 99.9 114 27.4 109 99.9 132 99.9 83 59.3 113 18.2 93 99.9 46 6.69 93 13.6 85 16.0 81 12.4 97 16.2 58 91.5 95 11.1 29 11.1 106 13.0 97 6.73 57 21.3 110 99.9 98 21.6 109
SPSA-learn [13]93.5 23.6 111 55.7 100 20.1 114 32.9 109 99.9 114 25.2 106 91.2 126 99.9 83 64.5 118 49.6 114 99.9 46 31.2 113 14.0 94 16.0 81 13.0 103 19.9 92 99.9 104 23.3 107 6.53 53 9.13 28 4.40 16 15.8 107 99.9 98 16.5 106
IAOF2 [51]93.7 16.8 90 59.5 114 10.5 95 20.1 100 69.0 85 18.1 100 53.3 108 99.9 83 56.8 111 55.3 120 95.0 40 54.7 121 14.2 97 17.2 102 11.0 82 19.2 90 81.1 78 14.3 65 11.8 114 13.2 98 13.0 111 13.5 101 45.0 76 9.00 68
Modified CLG [34]95.0 27.9 114 58.6 111 23.4 117 26.5 104 71.1 86 26.2 108 93.4 128 99.9 83 73.1 123 49.2 113 99.9 46 22.6 110 15.2 110 18.1 113 13.7 106 16.3 60 99.9 104 12.8 49 6.43 51 10.2 53 11.7 105 11.3 97 99.9 98 11.3 92
UnFlow [129]96.4 49.8 130 69.9 131 23.3 116 32.8 108 57.8 72 33.0 115 49.4 106 98.6 80 39.8 100 53.6 117 99.9 46 52.1 120 16.2 117 18.5 116 20.6 120 35.3 115 99.9 104 38.4 121 8.81 86 11.4 77 3.08 5 6.46 75 99.9 98 6.47 39
IAOF [50]96.7 20.6 101 55.0 96 17.4 111 36.6 112 99.9 114 27.6 111 99.9 132 99.9 83 75.5 126 32.7 107 93.3 39 25.5 111 13.9 91 16.6 97 12.1 92 36.5 116 92.3 96 12.3 42 9.40 94 11.7 81 7.13 64 26.2 115 47.4 77 28.8 112
GroupFlow [9]98.8 27.3 113 66.8 124 21.6 115 41.1 116 99.9 114 35.1 116 71.4 115 99.9 83 61.8 114 25.1 100 99.9 46 14.4 107 14.7 103 17.9 110 11.7 87 40.6 122 97.2 100 40.6 123 5.72 33 11.7 81 6.48 53 16.4 108 53.8 79 23.0 110
Black & Anandan [4]99.2 21.5 107 51.7 80 19.8 113 38.6 113 99.9 114 25.8 107 81.3 118 99.9 83 65.5 119 50.4 115 99.9 46 31.6 114 15.5 112 19.1 123 12.8 100 22.4 99 96.8 99 18.2 97 10.1 99 12.4 89 5.16 37 13.9 103 99.9 98 12.9 97
Nguyen [33]99.6 27.2 112 56.2 103 18.7 112 46.7 119 99.9 114 44.1 122 97.7 131 99.9 83 74.1 124 45.7 112 99.9 46 38.0 115 16.4 120 17.7 109 21.8 122 20.8 95 99.9 104 21.2 102 7.21 66 9.42 34 5.61 43 14.6 105 99.9 98 14.2 100
2bit-BM-tele [98]103.5 20.8 105 59.0 113 16.3 109 16.4 90 68.5 84 15.3 96 43.9 99 99.9 83 15.4 87 14.6 86 99.9 46 11.2 105 15.6 114 17.5 104 16.8 118 34.9 114 99.9 104 31.1 116 18.8 128 20.4 129 30.8 124 23.7 113 99.9 98 61.9 120
BlockOverlap [61]105.0 17.6 94 56.5 104 13.1 101 24.0 102 66.9 82 21.5 103 67.6 113 99.9 83 49.0 106 28.2 103 99.9 46 15.2 108 17.6 126 18.3 114 32.7 127 38.1 119 81.6 79 26.6 112 14.5 123 15.5 117 67.6 130 39.8 117 82.5 88 84.7 122
Heeger++ [104]105.6 33.0 119 58.3 110 23.6 118 60.7 123 99.9 114 39.4 118 59.1 110 99.9 83 30.1 94 86.5 133 99.9 46 70.5 125 14.9 106 17.1 100 12.9 101 76.5 130 99.9 104 79.8 130 7.49 71 12.9 94 6.59 54 99.9 127 99.9 98 99.9 126
SILK [79]107.8 33.3 120 64.6 121 29.2 124 46.3 118 99.9 114 39.4 118 95.0 130 99.9 83 66.5 121 56.7 121 99.9 46 50.2 118 16.1 116 18.7 120 17.2 119 48.7 125 99.9 104 37.3 120 7.26 68 9.22 30 14.5 113 70.9 122 99.9 98 51.7 118
Horn & Schunck [3]108.0 28.8 115 57.7 108 25.3 119 41.1 116 99.9 114 28.2 112 80.0 117 99.9 83 75.9 127 75.5 124 99.9 46 66.3 124 15.7 115 18.5 116 13.9 109 41.9 124 99.9 104 41.4 124 11.6 111 13.6 104 6.16 49 45.4 118 99.9 98 39.5 116
TI-DOFE [24]109.6 40.2 123 61.2 117 38.6 128 60.2 122 99.9 114 53.7 125 90.4 125 99.9 83 78.2 129 83.9 131 99.9 46 82.8 132 16.6 121 19.4 125 16.4 117 38.1 119 99.9 104 38.7 122 8.51 83 10.3 56 7.75 74 56.3 120 99.9 98 49.7 117
HCIC-L [99]112.0 44.4 126 66.7 123 29.1 123 99.9 133 99.9 114 99.9 133 47.8 103 99.9 83 44.6 103 58.5 122 99.9 46 55.7 122 20.3 128 20.6 126 24.0 125 33.9 113 86.5 90 33.6 117 38.0 132 49.5 132 36.0 125 13.7 102 25.8 68 13.7 99
FFV1MT [106]113.9 36.4 122 71.0 132 25.8 120 50.3 121 99.9 114 39.7 120 65.6 112 99.1 81 41.6 102 99.9 134 99.9 46 97.4 135 20.2 127 19.3 124 33.1 129 62.5 127 99.9 104 71.1 129 9.04 89 14.8 112 11.2 102 99.9 127 99.9 98 99.9 126
SLK [47]114.2 53.1 131 66.3 122 59.5 135 60.9 124 98.1 111 58.6 126 89.7 123 99.9 83 67.7 122 99.9 134 99.9 46 95.1 134 17.0 122 18.8 121 23.5 124 56.6 126 99.9 104 51.2 126 8.43 82 11.9 84 12.2 109 99.9 127 99.9 98 99.9 126
PGAM+LK [55]115.7 43.6 124 67.1 125 43.7 130 73.8 127 99.9 114 77.5 127 61.9 111 82.9 66 63.9 116 76.6 125 99.9 46 72.5 126 17.1 124 17.1 100 31.6 126 66.2 128 99.9 104 64.8 128 18.9 129 20.3 128 22.1 122 99.9 127 99.9 98 99.9 126
Adaptive flow [45]115.9 34.4 121 59.7 115 29.7 125 84.5 131 99.9 114 77.7 128 87.6 122 99.9 83 92.8 134 54.9 119 99.9 46 39.3 116 20.6 129 23.8 130 20.9 121 37.5 117 96.7 97 29.2 114 35.2 131 30.1 131 58.6 129 38.1 116 99.9 98 33.0 114
AdaConv-v1 [126]117.1 66.7 133 69.5 128 54.6 131 80.0 128 82.0 99 79.5 129 81.7 119 82.0 63 80.9 130 82.3 127 83.1 21 82.6 129 85.8 131 85.9 131 85.2 131 88.2 132 83.0 81 82.9 132 75.7 133 67.1 133 77.8 133 85.1 124 86.4 89 84.8 123
SepConv-v1 [127]117.1 66.7 133 69.5 128 54.6 131 80.0 128 82.0 99 79.5 129 81.7 119 82.0 63 80.9 130 82.3 127 83.1 21 82.6 129 85.8 131 85.9 131 85.2 131 88.2 132 83.0 81 82.9 132 75.7 133 67.1 133 77.8 133 85.1 124 86.4 89 84.8 123
SuperSlomo [132]117.1 66.7 133 69.5 128 54.6 131 80.0 128 82.0 99 79.5 129 81.7 119 82.0 63 80.9 130 82.3 127 83.1 21 82.6 129 85.8 131 85.9 131 85.2 131 88.2 132 83.0 81 82.9 132 75.7 133 67.1 133 77.8 133 85.1 124 86.4 89 84.8 123
Periodicity [78]118.0 54.4 132 84.3 135 26.5 121 99.9 133 99.9 114 99.9 133 99.9 132 99.9 83 99.9 135 81.4 126 99.9 46 76.3 127 99.9 135 99.9 134 99.9 135 99.9 135 99.9 104 99.9 135 6.06 43 14.8 112 70.6 132 99.9 127 99.9 98 99.9 126
FOLKI [16]120.1 43.8 125 74.4 133 38.0 127 99.9 133 99.9 114 99.9 133 89.7 123 99.9 83 76.2 128 85.0 132 99.9 46 81.0 128 23.2 130 22.5 129 38.8 130 66.2 128 99.9 104 62.7 127 17.0 127 17.6 124 42.6 127 99.9 127 99.9 98 99.9 126
Pyramid LK [2]121.1 47.7 128 60.7 116 56.1 134 88.6 132 99.9 114 91.9 132 99.9 132 99.9 83 89.4 133 83.0 130 99.9 46 83.2 133 98.4 134 99.9 134 87.9 134 87.4 131 99.9 104 81.4 131 16.9 126 16.6 121 57.0 128 99.9 127 99.9 98 99.9 126
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.