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        
R10.0
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]9.0 3.83 4 16.9 9 1.87 8 2.64 7 16.1 11 1.33 8 3.02 3 10.7 3 1.33 15 2.79 17 18.9 23 1.11 17 4.82 1 6.85 1 1.73 2 4.13 4 14.6 3 2.27 2 0.52 19 5.08 49 0.00 1 0.28 3 1.04 3 0.04 2
OFLAF [77]9.5 3.84 5 17.2 11 1.99 13 2.48 5 14.1 5 1.41 9 2.96 2 10.1 2 1.17 11 2.36 9 14.7 8 0.82 10 5.15 3 7.90 7 2.15 4 6.43 32 18.2 12 4.98 18 0.27 2 2.42 4 0.07 15 0.79 10 1.88 8 1.81 24
MDP-Flow2 [68]11.2 3.86 7 17.2 11 1.90 10 2.06 1 12.6 1 1.04 2 3.22 5 11.0 4 1.16 10 3.27 28 21.7 33 1.19 21 6.35 16 8.86 13 3.12 10 5.40 14 15.7 4 5.11 20 0.38 11 3.75 24 0.02 3 0.49 6 1.80 7 0.13 7
NN-field [71]12.8 4.31 17 18.6 22 2.22 22 3.13 16 18.3 25 1.79 19 3.16 4 11.1 5 1.40 16 2.08 6 16.7 11 0.78 8 5.28 4 7.44 3 2.25 5 2.53 1 8.92 1 0.92 1 0.89 39 6.39 73 0.02 3 0.27 2 0.98 2 0.04 2
PMMST [114]13.9 4.02 10 16.5 7 1.46 1 3.86 32 16.9 17 3.33 47 3.91 10 12.6 9 2.82 40 2.18 8 9.47 2 1.30 27 5.68 9 7.88 6 2.78 7 5.25 12 13.7 2 4.29 10 0.53 21 5.11 50 0.02 3 0.26 1 0.94 1 0.04 2
nLayers [57]23.0 4.08 13 16.2 5 2.80 39 4.71 56 19.3 33 3.82 74 4.64 19 15.2 19 3.96 60 1.99 4 13.2 3 0.80 9 5.34 6 7.57 5 3.22 12 5.85 26 16.8 7 4.64 13 0.87 37 3.68 22 0.96 51 0.84 11 2.94 18 0.75 10
ComponentFusion [96]23.9 4.03 11 17.7 15 2.19 21 2.17 4 13.1 3 1.26 5 3.86 9 13.2 11 1.58 18 2.85 20 18.0 16 1.03 15 6.68 23 9.59 22 4.14 34 8.35 69 27.3 70 8.34 83 0.60 23 4.03 29 0.52 39 0.76 9 2.22 12 1.09 12
LME [70]24.1 3.70 3 16.1 4 1.69 2 2.13 2 13.0 2 1.19 4 5.91 46 15.4 20 7.43 86 3.23 24 22.4 37 1.19 21 6.60 22 9.12 16 4.39 43 6.11 28 20.8 21 6.60 51 0.52 19 4.96 47 0.07 15 1.09 15 3.28 25 1.86 26
SVFilterOh [111]24.9 4.36 19 15.9 3 2.01 16 3.04 14 16.3 13 1.78 18 3.31 6 11.3 6 1.20 12 2.02 5 13.6 5 0.57 2 5.94 12 8.69 12 2.12 3 6.61 34 19.3 14 6.32 47 5.10 100 12.9 113 10.0 111 0.75 8 2.20 11 1.32 14
FC-2Layers-FF [74]25.4 4.03 11 16.3 6 2.39 29 4.23 41 20.9 42 3.21 44 3.40 8 11.4 7 2.64 34 2.74 14 17.1 13 1.03 15 5.73 10 8.29 10 3.31 14 7.49 46 20.5 20 6.66 55 1.30 54 6.84 78 0.34 33 0.64 7 1.78 6 1.20 13
NNF-EAC [103]26.1 4.32 18 18.6 22 2.18 20 2.69 8 15.1 7 1.64 14 3.93 11 13.1 10 1.27 13 4.17 60 23.0 46 1.95 57 7.09 33 9.97 29 3.89 30 6.33 30 17.4 9 5.53 23 0.55 22 5.18 51 0.02 3 1.60 40 4.32 42 1.93 29
HAST [109]27.6 2.98 1 12.9 1 1.71 3 3.63 29 15.0 6 2.78 36 2.46 1 8.38 1 0.25 1 2.84 19 18.0 16 0.67 4 5.02 2 7.35 2 1.66 1 8.83 79 22.4 35 8.37 84 6.13 106 12.0 108 18.0 119 0.31 4 1.13 4 0.03 1
WLIF-Flow [93]28.8 3.97 9 17.0 10 2.12 18 3.53 23 18.5 27 2.37 29 4.60 18 15.1 17 2.34 30 3.40 31 20.3 29 1.50 32 7.69 56 11.4 65 4.79 57 6.67 35 17.8 11 5.53 23 0.40 14 3.68 22 0.07 15 1.59 39 3.82 35 2.63 46
RNLOD-Flow [121]30.0 3.58 2 15.7 2 1.83 6 3.60 27 19.9 36 2.06 23 5.53 40 18.1 42 2.42 32 2.75 15 17.7 14 1.01 14 6.01 13 9.09 15 3.98 31 7.21 40 20.0 16 6.87 64 2.59 77 9.67 90 1.95 68 1.06 14 2.66 15 1.79 23
3DFlow [135]30.0 4.65 26 19.4 26 1.86 7 3.01 13 18.5 27 1.32 7 4.17 12 14.5 13 0.62 2 1.38 1 7.93 1 0.72 6 6.90 26 10.3 41 3.76 27 11.3 97 30.0 84 10.5 98 1.63 66 4.03 29 5.22 97 0.35 5 1.27 5 0.06 5
FESL [72]30.1 3.91 8 16.6 8 2.13 19 5.68 78 23.5 59 4.23 79 5.17 30 16.8 26 2.99 42 2.41 11 15.8 9 0.89 13 5.76 11 8.62 11 4.05 32 5.81 23 17.6 10 5.32 22 1.09 47 5.68 64 1.21 58 1.35 24 2.89 17 1.72 21
Layers++ [37]30.2 4.39 20 17.8 16 3.14 47 3.70 30 18.0 22 2.84 37 3.37 7 11.5 8 2.65 35 2.38 10 14.1 7 0.82 10 5.33 5 7.52 4 3.78 28 7.58 49 22.0 31 6.13 41 1.81 71 7.08 80 0.54 40 1.45 31 2.46 14 4.56 83
ALD-Flow [66]31.4 4.22 14 18.2 19 1.93 12 3.20 19 16.8 16 1.59 13 5.21 31 17.4 33 1.13 9 3.70 39 22.9 44 1.26 23 6.54 21 9.31 18 3.14 11 5.25 12 21.5 26 4.98 18 0.88 38 4.67 39 4.48 93 2.69 62 6.66 60 4.79 84
TC/T-Flow [76]32.2 4.57 24 20.6 31 2.00 14 3.45 22 18.7 29 1.52 11 4.30 14 14.3 12 0.67 4 3.97 55 23.1 47 1.80 48 6.35 16 9.50 21 3.36 17 4.48 6 15.7 4 4.78 15 1.30 54 6.94 79 5.07 96 2.08 53 5.10 50 2.83 52
PMF [73]32.8 4.65 26 18.3 21 2.34 25 3.37 20 18.2 24 1.92 21 4.20 13 14.6 15 1.01 7 3.24 26 18.6 20 1.11 17 5.50 7 8.09 8 2.43 6 6.99 38 24.8 53 6.27 45 6.87 109 17.3 124 8.77 110 0.91 12 2.06 9 2.06 32
Correlation Flow [75]33.2 4.57 24 20.5 30 1.87 8 2.71 9 16.2 12 1.16 3 5.74 44 17.9 40 0.66 3 1.91 2 13.5 4 0.85 12 8.00 65 12.0 74 4.57 46 8.69 73 23.8 45 8.93 89 0.84 34 4.74 40 0.96 51 1.38 27 3.81 34 1.91 28
Efficient-NL [60]34.0 4.24 15 17.4 13 2.24 23 4.30 42 21.8 45 2.75 34 5.26 34 16.9 28 2.67 36 3.43 33 21.0 31 1.74 43 6.02 14 9.16 17 3.31 14 7.84 58 21.7 28 6.26 44 1.36 57 6.79 77 1.03 54 1.48 34 3.08 21 1.77 22
AGIF+OF [85]34.2 4.39 20 18.0 18 2.80 39 5.10 67 23.7 62 3.70 68 5.06 26 16.8 26 3.11 43 3.29 29 20.1 27 1.45 31 6.45 19 9.31 18 4.62 48 6.77 37 19.7 15 5.86 32 0.37 10 3.60 20 0.25 28 1.79 46 3.68 31 3.12 61
TC-Flow [46]35.7 4.27 16 19.0 25 1.91 11 2.85 10 16.6 15 1.45 10 5.05 25 16.9 28 0.80 6 4.05 56 23.9 55 1.74 43 6.73 24 9.68 24 2.93 9 5.83 24 22.9 40 5.68 29 1.39 59 4.87 45 7.32 106 2.46 59 6.13 57 4.49 80
OAR-Flow [125]37.3 5.41 46 21.6 42 2.61 33 4.96 63 22.3 48 2.88 38 7.90 61 23.8 60 4.19 64 4.45 67 22.7 43 1.90 52 7.03 31 10.1 32 3.39 18 5.10 10 22.3 33 4.56 12 0.29 4 2.64 8 0.17 24 1.58 38 4.89 49 1.68 19
Classic+CPF [83]37.5 4.77 31 19.7 28 2.99 42 4.59 48 23.3 57 3.08 42 5.24 32 17.2 31 2.81 39 3.32 30 21.3 32 1.57 37 6.51 20 9.49 20 4.24 39 7.39 43 21.5 26 6.27 45 1.02 42 5.33 55 1.40 60 1.47 33 3.19 23 2.47 44
COFM [59]40.3 4.75 30 20.2 29 2.63 35 3.40 21 18.3 25 2.14 25 6.19 50 19.3 48 4.00 61 3.04 22 18.8 21 1.11 17 7.45 46 10.1 32 7.01 87 8.80 77 20.9 22 6.68 56 1.41 60 3.66 21 2.76 80 1.22 18 2.28 13 3.72 71
PH-Flow [101]40.3 5.11 38 21.0 33 3.62 61 4.59 48 22.4 49 3.37 51 4.37 15 14.5 13 3.45 48 3.93 52 22.5 39 2.07 64 6.34 15 9.00 14 3.74 25 7.28 42 21.7 28 6.39 49 1.61 65 5.58 62 1.58 63 1.15 17 2.12 10 3.39 66
IROF++ [58]40.5 4.68 28 19.4 26 2.70 36 4.66 52 23.1 53 3.42 56 5.25 33 17.2 31 3.79 56 3.95 53 23.2 48 2.05 61 6.97 29 9.84 27 4.64 49 7.99 62 24.6 50 7.05 68 0.44 16 4.30 35 0.00 1 1.37 26 3.26 24 2.83 52
HBM-GC [105]40.6 5.82 53 18.2 19 2.00 14 4.47 46 18.7 29 3.80 73 4.39 16 15.1 17 1.73 22 2.42 12 13.8 6 0.72 6 6.77 25 9.60 23 4.08 33 7.61 51 19.0 13 5.76 30 4.61 96 12.6 110 2.83 82 2.39 57 5.72 53 5.01 88
ProbFlowFields [128]41.1 8.29 84 31.1 83 5.73 97 3.54 24 18.0 22 2.75 34 6.07 49 18.9 47 5.22 67 3.54 36 17.7 14 1.91 53 7.66 55 10.8 51 4.59 47 5.06 9 20.0 16 5.58 27 0.38 11 3.08 14 0.07 15 1.70 43 4.56 45 2.41 43
Sparse-NonSparse [56]42.2 4.98 34 20.8 32 4.09 70 4.63 51 22.9 50 3.41 55 5.02 24 16.7 25 3.47 51 3.89 48 22.6 42 1.91 53 7.17 36 10.2 36 4.30 41 7.66 53 22.3 33 6.80 60 0.69 29 3.53 19 0.89 48 1.52 36 3.56 30 2.97 57
CostFilter [40]42.3 5.29 44 22.0 44 2.85 41 3.54 24 17.7 20 2.16 26 4.64 19 16.0 21 1.75 23 3.68 38 22.5 39 1.27 25 5.67 8 8.14 9 2.85 8 7.76 55 25.9 60 6.80 60 6.98 112 24.2 129 12.9 114 1.43 28 4.11 38 2.02 31
MLDP_OF [89]43.0 6.35 61 26.0 62 3.41 52 2.97 12 16.4 14 1.76 17 5.47 38 17.8 38 1.30 14 2.79 17 19.7 25 1.12 20 7.13 35 10.0 30 3.75 26 7.49 46 21.4 25 9.75 94 5.04 98 6.22 70 17.0 118 1.79 46 4.28 41 2.14 34
Classic+NL [31]43.6 5.07 37 21.0 33 4.22 74 4.70 55 23.4 58 3.27 45 4.98 23 16.5 23 3.48 52 3.75 42 22.5 39 1.68 40 7.21 39 10.2 36 4.32 42 7.82 56 22.4 35 6.71 57 1.47 61 6.39 73 1.18 57 1.12 16 2.87 16 2.27 38
FMOF [94]43.7 4.42 22 17.8 16 3.06 45 5.03 64 23.1 53 3.63 64 4.45 17 14.8 16 2.80 38 2.94 21 18.8 21 1.26 23 7.00 30 10.2 36 4.71 52 8.92 80 20.9 22 7.13 70 1.06 45 6.34 72 1.85 67 2.58 61 5.80 55 3.06 59
LSM [39]43.8 5.00 36 21.2 39 3.93 67 4.62 50 22.9 50 3.37 51 5.13 28 17.1 30 3.26 46 3.80 43 22.9 44 1.87 50 6.92 27 9.78 25 4.41 45 7.71 54 22.4 35 6.74 58 1.00 41 4.76 42 1.16 56 1.68 42 3.94 36 2.90 56
Ramp [62]44.2 5.12 39 21.1 37 3.82 66 4.68 54 23.2 55 3.47 59 4.89 22 16.3 22 3.46 49 3.83 45 22.3 36 1.93 56 7.23 40 10.2 36 4.80 58 7.61 51 22.1 32 6.80 60 1.20 50 5.04 48 1.43 61 1.36 25 2.98 19 2.31 42
IIOF-NLDP [131]44.8 6.16 57 25.7 60 2.54 31 4.55 47 23.7 62 2.40 30 5.35 37 17.6 36 1.06 8 2.78 16 17.0 12 1.54 33 8.90 84 13.4 99 4.73 53 8.04 63 22.8 38 7.69 79 0.64 27 4.61 37 0.25 28 1.81 49 4.16 40 2.72 48
Aniso-Texture [82]45.8 3.84 5 17.5 14 1.76 4 2.88 11 15.9 9 2.11 24 7.10 58 20.9 53 2.30 26 1.97 3 16.5 10 0.57 2 8.24 70 11.9 71 5.22 71 8.82 78 26.6 67 6.77 59 8.34 118 16.2 123 1.43 61 2.42 58 5.55 51 2.84 54
NL-TV-NCC [25]46.1 5.44 47 21.7 43 2.24 23 4.00 36 21.9 46 1.69 15 5.27 35 17.8 38 0.67 4 2.52 13 19.1 24 0.67 4 8.37 73 12.5 83 5.12 70 11.5 99 32.0 95 9.19 91 0.86 35 4.93 46 1.35 59 2.16 54 6.46 58 1.63 16
S2D-Matching [84]46.4 4.97 33 21.3 41 3.55 58 4.74 57 23.6 60 3.35 49 6.50 52 20.9 53 3.46 49 3.49 34 20.4 30 1.60 38 7.07 32 10.0 30 4.22 37 7.82 56 23.1 41 6.87 64 1.78 70 5.90 67 2.12 70 1.30 21 3.14 22 2.74 49
TV-L1-MCT [64]47.8 4.69 29 18.9 24 3.60 60 5.64 77 25.6 75 4.21 77 5.53 40 18.1 42 3.23 44 3.04 22 19.9 26 1.35 28 7.49 47 10.6 45 4.91 64 8.34 67 22.8 38 7.50 78 0.79 33 2.61 6 3.57 87 1.73 45 3.45 28 3.26 64
MDP-Flow [26]47.9 5.65 51 24.7 57 4.93 88 3.70 30 17.6 19 3.40 54 5.47 38 18.7 46 4.66 65 3.87 46 24.3 58 1.88 51 7.12 34 9.89 28 5.00 68 6.17 29 25.9 60 4.66 14 0.61 24 5.65 63 0.05 12 3.28 73 8.39 72 3.45 69
AggregFlow [97]48.1 6.17 58 23.3 51 2.58 32 7.01 87 28.0 92 5.29 88 8.46 66 24.2 62 7.66 88 3.73 40 20.2 28 1.73 42 7.25 41 10.6 45 3.52 19 4.43 5 16.4 6 4.80 17 0.75 32 5.43 58 0.25 28 1.92 50 4.46 44 4.12 75
IROF-TV [53]49.3 5.22 42 22.6 49 3.59 59 4.80 59 24.2 67 3.73 72 5.71 43 18.4 45 3.64 54 4.19 61 25.7 71 1.92 55 7.63 54 10.7 48 5.26 72 9.22 84 30.2 85 6.60 51 0.30 6 2.86 10 0.02 3 1.32 23 3.76 33 2.27 38
CombBMOF [113]51.1 6.51 63 28.6 72 2.61 33 3.98 35 18.7 29 2.29 28 5.29 36 17.4 33 2.33 29 5.12 77 26.1 78 3.28 82 6.35 16 9.81 26 3.34 16 12.0 101 28.4 75 15.1 113 3.73 89 12.8 112 0.76 45 0.98 13 3.00 20 0.09 6
OFH [38]51.7 6.38 62 25.7 60 4.69 83 3.90 33 20.6 40 2.24 27 7.85 60 24.2 62 2.27 25 4.11 59 25.1 62 1.72 41 7.44 45 10.4 42 4.69 50 8.13 64 28.9 77 8.44 87 0.44 16 4.25 32 0.12 20 2.80 64 8.82 81 2.74 49
Adaptive [20]52.0 5.12 39 22.0 44 2.34 25 4.82 61 23.2 55 3.50 60 8.67 71 24.5 67 3.56 53 4.19 61 25.3 68 1.83 49 7.40 44 10.6 45 3.63 21 5.84 25 23.2 43 3.75 8 3.25 85 8.86 87 0.89 48 2.87 66 6.69 61 3.14 63
Occlusion-TV-L1 [63]52.1 5.23 43 22.2 46 2.36 28 4.40 44 21.2 43 3.39 53 8.46 66 24.8 68 3.83 58 3.92 50 24.8 60 1.74 43 9.11 86 13.1 96 5.75 77 4.65 7 23.9 46 3.52 6 1.27 53 3.13 15 0.44 36 3.56 79 8.92 82 3.28 65
Sparse Occlusion [54]52.1 4.99 35 21.1 37 2.79 38 4.13 39 20.1 39 3.00 41 5.94 48 19.4 49 2.15 24 3.41 32 21.8 34 1.35 28 8.17 69 12.1 77 4.74 54 7.87 60 25.6 59 6.34 48 11.4 123 17.7 125 2.71 79 1.64 41 4.70 48 1.81 24
RFlow [90]53.0 5.85 54 24.8 59 4.44 80 3.18 17 17.9 21 1.88 20 7.81 59 24.4 66 2.32 28 3.25 27 23.4 51 1.55 34 7.94 59 11.6 67 4.86 60 8.23 65 28.0 74 6.64 54 1.16 49 2.13 2 1.13 55 4.10 89 9.22 88 6.81 95
2DHMM-SAS [92]54.1 5.14 41 21.0 33 3.79 65 5.26 72 25.2 72 3.45 57 6.97 57 20.2 50 4.18 63 4.06 57 23.3 50 2.10 65 7.18 37 10.2 36 4.92 65 8.29 66 23.7 44 7.16 71 1.26 51 5.41 57 1.63 64 1.71 44 3.75 32 2.74 49
ACK-Prior [27]54.2 5.49 49 24.0 54 1.81 5 2.55 6 15.7 8 0.83 1 5.07 27 17.7 37 1.52 17 2.14 7 18.1 18 0.50 1 8.64 76 11.6 67 7.10 90 14.6 112 30.7 87 11.7 102 8.46 119 11.5 104 19.5 121 3.68 83 7.25 64 2.64 47
SimpleFlow [49]54.6 5.65 51 22.4 48 4.93 88 5.47 76 24.5 70 4.28 80 6.88 56 21.0 55 3.95 59 4.74 70 25.2 64 3.02 76 7.19 38 10.1 32 4.70 51 8.34 67 23.1 41 7.16 71 1.02 42 4.61 37 0.89 48 1.29 20 3.44 26 2.47 44
S2F-IF [123]57.0 9.49 96 37.6 102 4.93 88 4.81 60 25.6 75 3.34 48 8.25 64 26.1 71 6.40 75 4.99 74 25.6 70 2.93 74 7.80 57 11.0 56 4.90 63 5.61 17 24.9 56 5.83 31 0.62 26 5.35 56 0.22 26 1.43 28 4.11 38 1.67 18
Complementary OF [21]57.7 7.27 72 30.0 77 4.31 75 3.18 17 18.9 32 1.52 11 5.91 46 20.2 50 2.31 27 4.22 64 24.8 60 2.05 61 7.50 49 10.4 42 4.99 67 12.3 104 31.7 94 8.87 88 0.61 24 2.69 9 1.72 66 3.33 74 9.22 88 4.88 87
ROF-ND [107]58.5 6.70 64 27.6 68 3.53 56 3.08 15 16.0 10 1.73 16 5.81 45 18.3 44 1.58 18 3.81 44 18.4 19 2.20 66 9.45 91 14.0 109 6.31 84 11.3 97 29.6 82 7.27 75 9.92 121 10.8 95 7.29 105 1.53 37 3.44 26 1.64 17
TCOF [69]59.0 7.04 70 26.9 65 3.54 57 4.93 62 23.7 62 3.45 57 9.94 84 27.8 79 7.40 85 3.74 41 23.7 54 1.55 34 10.0 101 14.3 110 4.40 44 4.91 8 17.0 8 5.53 23 5.08 99 9.68 91 4.19 91 1.43 28 4.44 43 1.69 20
PGM-C [120]60.2 9.47 94 37.1 99 4.81 87 5.08 65 26.1 80 3.63 64 8.75 73 27.6 77 7.02 79 5.65 85 28.1 94 3.63 90 7.99 62 11.3 62 4.88 61 5.71 21 24.5 49 5.97 35 0.31 7 3.01 13 0.02 3 2.07 52 6.50 59 2.14 34
TF+OM [100]60.5 6.03 56 23.7 53 2.78 37 4.39 43 19.9 36 3.57 61 8.73 72 23.0 59 11.2 94 3.57 37 23.2 48 1.36 30 7.98 61 11.1 59 5.89 79 8.95 81 25.3 58 7.06 69 1.68 68 11.2 100 0.20 25 3.56 79 8.35 71 4.18 76
Steered-L1 [118]60.6 4.54 23 21.2 39 2.09 17 2.13 2 13.9 4 1.31 6 4.80 21 16.5 23 1.64 20 3.87 46 25.1 62 1.60 38 8.62 75 11.5 66 7.01 87 11.1 94 28.7 76 10.4 97 12.0 127 12.3 109 34.9 129 5.90 100 9.03 86 11.6 108
FlowFields [110]62.0 9.65 98 37.6 102 5.13 91 5.09 66 25.9 78 3.72 70 8.92 75 28.3 83 7.07 81 5.45 81 26.0 76 3.82 91 7.95 60 11.2 61 5.01 69 5.75 22 26.1 63 6.01 36 0.40 14 3.29 17 0.12 20 1.92 50 5.99 56 1.89 27
DeepFlow2 [108]62.5 6.80 66 28.5 71 2.99 42 5.20 71 22.9 50 3.60 63 8.88 74 26.2 72 5.75 72 5.76 87 26.8 83 3.41 87 7.34 43 10.7 48 3.58 20 5.86 27 24.8 53 6.22 43 1.02 42 3.78 26 3.08 85 4.35 92 9.84 93 5.80 91
FlowFields+ [130]62.8 9.76 100 38.1 106 5.31 93 5.14 68 26.2 82 3.72 70 8.99 76 28.6 85 7.15 84 5.09 76 25.9 75 3.29 83 7.82 58 11.0 56 4.94 66 5.22 11 24.7 52 5.18 21 0.70 31 5.85 66 0.30 32 1.79 46 5.77 54 1.45 15
EPPM w/o HM [88]63.2 8.62 88 33.5 91 3.62 61 3.58 26 19.7 34 1.93 22 6.19 50 20.5 52 1.64 20 4.64 69 25.2 64 2.54 69 7.60 53 10.4 42 5.81 78 11.2 95 31.6 92 9.82 95 6.91 111 8.93 88 15.9 117 1.48 34 4.06 37 2.01 30
CPM-Flow [116]63.5 9.47 94 37.1 99 4.79 85 5.15 69 26.3 83 3.67 66 8.59 70 27.1 75 7.00 78 5.59 83 27.8 91 3.57 88 7.99 62 11.3 62 4.74 54 5.70 20 24.1 48 6.05 38 0.48 18 4.29 34 0.02 3 2.76 63 7.63 67 4.11 74
EpicFlow [102]64.5 9.44 93 37.1 99 4.80 86 5.15 69 26.4 84 3.70 68 9.58 80 30.0 88 7.07 81 5.38 80 27.8 91 3.29 83 8.01 66 11.3 62 4.88 61 5.67 19 24.6 50 6.12 40 0.32 9 3.13 15 0.02 3 3.10 71 7.52 65 4.79 84
ComplOF-FED-GPU [35]65.2 6.96 68 30.7 80 3.33 50 4.74 57 24.9 71 2.66 32 6.71 54 22.4 56 2.45 33 4.44 66 26.2 79 2.05 61 7.50 49 10.7 48 4.20 36 9.78 85 34.0 100 9.47 93 2.42 76 4.74 40 6.63 103 3.09 69 9.17 87 3.91 73
SRR-TVOF-NL [91]66.3 7.45 76 28.6 72 3.09 46 6.20 81 26.1 80 3.90 75 9.82 82 28.4 84 5.78 73 3.96 54 23.5 52 1.55 34 7.55 51 10.8 51 5.27 73 9.21 83 26.7 68 7.25 74 5.74 103 11.5 104 4.01 89 1.30 21 3.49 29 2.19 37
F-TV-L1 [15]66.5 8.70 89 31.4 85 8.47 105 7.61 91 27.3 89 5.86 89 11.0 87 28.0 80 5.73 71 5.75 86 28.7 96 3.32 86 7.28 42 10.8 51 3.72 22 6.59 33 26.4 64 4.38 11 1.26 51 5.30 54 0.44 36 3.04 68 7.76 68 2.29 41
TV-L1-improved [17]66.7 5.52 50 23.4 52 3.42 53 4.13 39 20.8 41 2.96 39 8.29 65 24.2 62 3.64 54 4.06 57 24.4 59 1.77 46 8.34 72 12.1 77 4.15 35 13.7 108 38.4 109 14.9 110 4.40 95 10.1 93 2.14 71 3.33 74 8.42 73 3.40 67
SIOF [67]67.5 5.37 45 22.6 49 2.34 25 6.11 79 28.4 93 4.30 81 12.6 93 29.2 87 14.4 95 5.52 82 27.4 87 3.00 75 8.96 85 12.6 85 6.02 80 8.72 74 27.9 72 7.93 80 0.38 11 3.48 18 0.02 3 3.09 69 7.58 66 4.85 86
Aniso. Huber-L1 [22]68.1 5.98 55 24.2 55 3.23 49 8.53 95 27.3 89 7.91 94 9.64 81 25.6 70 5.52 69 5.00 75 25.7 71 2.75 72 8.66 77 12.8 91 4.74 54 7.60 50 24.8 53 3.51 5 3.65 88 7.24 81 3.00 84 2.57 60 6.69 61 2.86 55
DPOF [18]68.3 9.01 91 34.7 93 3.68 64 6.16 80 25.4 74 4.32 82 5.55 42 17.9 40 3.36 47 3.92 50 25.3 68 2.00 59 8.14 68 11.0 56 6.05 81 10.5 90 27.9 72 8.16 82 9.33 120 6.19 69 21.0 123 1.46 32 4.57 46 0.80 11
BriefMatch [124]69.9 4.78 32 21.0 33 2.40 30 4.00 36 19.8 35 2.68 33 5.13 28 17.5 35 2.41 31 3.23 24 22.1 35 1.28 26 9.81 98 12.0 74 13.1 119 17.2 114 33.8 99 17.8 116 7.84 114 12.7 111 22.3 124 8.01 112 10.5 99 16.1 119
Classic++ [32]70.0 5.46 48 22.2 46 4.35 77 4.66 52 22.1 47 3.57 61 8.00 62 24.3 65 5.06 66 4.21 63 25.2 64 2.01 60 8.77 80 12.7 89 5.47 74 9.03 82 30.2 85 7.29 76 2.92 83 7.73 83 3.10 86 3.83 86 8.53 74 3.87 72
LocallyOriented [52]70.1 8.05 82 30.6 79 3.63 63 8.09 93 30.8 100 6.17 91 12.3 92 32.3 94 7.04 80 4.88 73 25.2 64 2.88 73 8.80 82 12.7 89 4.27 40 5.41 15 20.4 18 6.07 39 1.35 56 6.03 68 0.99 53 3.73 85 8.62 77 4.18 76
DeepFlow [86]72.5 7.55 77 29.3 75 4.67 82 6.29 83 23.7 62 4.86 84 10.0 85 28.0 80 8.76 93 6.15 94 27.3 85 3.83 92 7.49 47 10.8 51 3.72 22 6.40 31 26.8 69 6.85 63 1.12 48 2.92 12 3.94 88 7.07 105 11.2 103 12.7 110
CRTflow [80]72.6 7.63 79 31.8 88 3.42 53 4.40 44 21.2 43 2.97 40 8.99 76 26.6 73 4.11 62 4.86 72 26.5 80 2.57 70 7.99 62 11.7 69 3.26 13 18.0 118 40.2 112 22.2 121 1.47 61 4.45 36 2.51 77 4.73 94 11.4 104 7.30 96
TriFlow [95]73.0 7.87 81 30.1 78 3.19 48 7.12 88 24.4 69 7.15 93 13.9 96 31.4 91 20.0 101 3.50 35 22.4 37 1.77 46 8.70 78 11.7 69 7.03 89 7.51 48 21.9 30 6.63 53 28.6 130 14.7 120 78.3 132 2.16 54 5.57 52 2.14 34
Rannacher [23]74.8 6.99 69 27.1 66 5.36 95 5.27 73 24.3 68 4.22 78 9.51 79 27.1 75 5.54 70 4.76 71 25.7 71 2.58 71 8.80 82 12.9 93 4.82 59 11.0 92 35.7 103 9.36 92 2.33 75 4.76 42 2.39 76 2.82 65 8.01 69 3.13 62
Brox et al. [5]75.0 8.32 85 32.6 89 6.95 100 6.23 82 26.9 88 5.23 86 9.13 78 27.6 77 6.55 77 5.85 89 28.2 95 3.26 80 10.2 103 12.9 93 11.0 114 5.43 16 29.3 81 4.79 16 0.86 35 4.00 28 0.12 20 4.32 90 10.2 96 4.54 82
Local-TV-L1 [65]75.4 9.60 97 30.8 81 7.89 104 12.7 101 30.2 99 13.3 101 15.9 103 32.3 94 17.3 98 6.19 95 28.0 93 3.84 93 7.55 51 10.9 55 4.22 37 7.48 45 26.4 64 6.02 37 0.28 3 1.87 1 0.15 23 9.10 114 10.8 101 20.5 120
Bartels [41]75.7 6.83 67 26.2 63 5.19 92 3.93 34 17.4 18 3.30 46 6.63 53 22.6 57 3.25 45 4.45 67 23.9 55 2.48 68 9.12 87 12.1 77 8.25 98 10.6 91 31.1 88 12.3 105 5.74 103 10.4 94 18.9 120 5.34 96 9.52 90 8.47 102
Dynamic MRF [7]76.2 7.74 80 31.6 87 4.44 80 4.12 38 23.6 60 2.47 31 8.49 68 28.0 80 2.83 41 4.25 65 27.4 87 2.41 67 8.61 74 12.0 74 6.08 82 14.5 111 43.2 116 14.9 110 0.64 27 2.35 3 4.51 94 9.85 117 15.6 120 15.3 117
SuperFlow [81]76.4 7.15 71 27.4 67 3.52 55 10.4 98 27.8 91 11.2 98 14.5 101 31.5 93 22.4 103 5.93 90 31.6 102 3.23 79 8.77 80 11.9 71 8.59 103 5.61 17 25.9 60 3.72 7 3.76 91 11.1 99 0.37 35 3.59 81 8.96 84 3.01 58
CBF [12]80.6 6.32 59 26.2 63 3.35 51 11.1 99 25.6 75 13.7 102 8.51 69 24.1 61 7.12 83 5.12 77 26.0 76 3.04 78 10.3 104 13.6 104 9.59 110 7.85 59 26.4 64 4.25 9 11.8 124 13.8 115 14.2 116 3.54 78 8.06 70 5.32 89
OFRF [134]81.0 7.28 73 24.5 56 4.75 84 14.7 105 29.6 97 15.2 103 14.3 98 29.0 86 15.9 97 6.64 97 25.7 71 5.02 101 6.95 28 10.1 32 3.72 22 8.44 70 23.9 46 7.17 73 3.30 86 6.51 75 10.8 112 9.99 118 9.82 92 24.2 122
CLG-TV [48]81.6 6.33 60 24.7 57 4.13 71 9.08 97 26.6 85 9.31 97 9.85 83 26.8 74 5.82 74 5.30 79 26.5 80 3.03 77 10.4 106 14.6 114 7.57 93 7.95 61 31.1 88 6.51 50 5.92 105 11.4 101 4.36 92 3.41 76 8.81 80 3.06 59
TriangleFlow [30]82.3 7.35 74 28.2 70 4.31 75 5.35 75 25.2 72 3.36 50 8.00 62 24.8 68 2.70 37 3.90 49 24.1 57 1.97 58 12.9 120 17.8 126 10.7 112 13.1 106 32.3 97 13.9 108 4.71 97 16.1 122 4.04 90 3.65 82 8.73 79 5.69 90
DF-Auto [115]83.3 9.74 99 34.1 92 4.36 78 14.1 104 31.9 103 15.4 105 15.6 102 33.1 100 23.6 105 5.94 91 27.3 85 3.59 89 10.4 106 14.8 117 6.97 86 3.80 3 21.1 24 2.46 3 5.25 102 11.4 101 0.49 38 4.33 91 10.4 97 4.33 78
p-harmonic [29]84.0 8.47 86 36.3 97 7.17 101 5.27 73 24.1 66 4.39 83 11.2 89 31.4 91 8.13 92 7.18 101 32.4 103 5.24 102 8.04 67 11.1 59 6.89 85 9.82 86 36.4 105 10.6 99 2.61 78 5.51 60 0.54 40 4.07 88 9.01 85 4.34 79
CNN-flow-warp+ref [117]84.2 9.81 102 35.7 95 7.67 103 8.14 94 26.0 79 8.55 95 14.3 98 35.8 103 15.7 96 6.69 98 30.3 99 4.31 97 9.17 89 12.2 80 8.71 105 7.03 39 29.6 82 5.55 26 0.69 29 3.77 25 2.00 69 7.79 110 12.1 108 8.13 101
FlowNet2 [122]86.2 21.7 117 43.8 110 13.5 109 24.6 118 42.3 116 27.3 119 19.8 107 40.5 107 29.9 112 8.21 105 23.6 53 5.39 104 9.85 99 12.6 85 8.54 100 8.76 75 28.9 77 5.89 33 2.77 80 15.5 121 0.81 47 1.28 19 4.68 47 0.26 8
FlowNetS+ft+v [112]87.5 7.57 78 29.4 76 3.96 68 7.50 90 26.6 85 6.48 92 14.3 98 32.7 98 17.5 99 7.55 102 31.3 100 5.28 103 10.5 108 14.7 115 7.49 92 6.75 36 27.8 71 6.97 67 4.01 93 8.84 86 6.77 104 3.52 77 9.71 91 3.61 70
SegOF [10]88.5 12.6 105 34.9 94 7.20 102 21.3 113 36.9 111 25.3 117 21.6 110 40.5 107 31.8 116 14.1 114 37.7 111 10.8 109 10.3 104 12.5 83 12.6 118 10.2 88 40.2 112 11.2 101 0.29 4 2.91 11 0.07 15 2.90 67 8.68 78 2.07 33
LDOF [28]88.8 8.22 83 31.4 85 4.08 69 7.64 92 29.4 95 5.87 90 10.7 86 30.3 89 7.99 91 7.80 103 36.8 109 4.86 100 9.14 88 12.4 82 8.24 97 8.58 71 32.0 95 8.38 85 1.75 69 5.26 53 5.02 95 5.52 98 12.9 112 6.04 93
Fusion [6]89.1 8.51 87 37.6 102 6.69 99 3.62 28 20.0 38 3.08 42 6.82 55 22.6 57 6.47 76 5.78 88 31.3 100 4.29 96 11.2 116 14.7 115 10.6 111 14.0 109 35.2 101 15.0 112 7.88 115 14.3 118 2.22 72 5.35 97 11.0 102 8.56 103
EPMNet [133]89.2 21.3 116 48.9 118 14.5 110 23.2 116 44.2 118 25.1 116 18.8 106 37.9 105 28.4 109 8.92 107 27.5 90 5.90 105 9.85 99 12.6 85 8.54 100 8.76 75 28.9 77 5.89 33 1.98 72 11.4 101 0.59 42 2.36 56 8.59 76 0.63 9
Learning Flow [11]91.4 6.74 65 28.1 69 3.03 44 6.37 84 28.7 94 5.02 85 11.8 90 32.6 97 7.93 90 6.87 100 33.2 106 4.32 98 12.5 119 17.4 124 7.78 94 9.98 87 35.2 101 8.41 86 2.66 79 10.9 97 2.24 73 6.76 104 13.7 114 6.41 94
StereoFlow [44]92.3 58.0 132 76.4 132 63.7 129 51.8 131 66.9 132 48.3 127 51.0 132 73.0 132 41.6 126 63.5 132 83.4 132 56.7 130 13.3 122 13.7 105 19.1 125 3.63 2 20.4 18 2.73 4 0.26 1 2.49 5 0.05 12 4.06 87 8.57 75 5.81 92
Ad-TV-NDC [36]93.3 21.2 115 36.8 98 34.1 124 25.9 120 38.5 113 29.9 120 23.5 114 41.0 109 27.1 106 13.3 111 32.4 103 13.3 114 8.75 79 13.2 97 3.82 29 7.43 44 25.1 57 6.92 66 1.50 63 4.84 44 0.34 33 17.1 127 15.9 124 37.2 130
Second-order prior [8]93.7 7.35 74 31.2 84 4.16 72 6.80 86 29.5 96 5.27 87 11.8 90 33.3 101 7.78 89 6.05 92 27.2 84 3.90 94 9.67 96 13.8 107 5.74 76 14.0 109 41.8 115 11.7 102 6.86 108 9.72 92 7.61 108 4.72 93 10.1 95 7.78 99
HBpMotionGpu [43]94.9 11.7 103 32.8 90 6.34 98 18.9 110 35.4 109 22.0 113 22.3 111 42.7 112 31.1 115 5.62 84 26.7 82 3.31 85 9.47 92 13.0 95 8.55 102 8.68 72 31.2 90 5.58 27 6.88 110 11.9 106 0.64 43 7.67 109 11.4 104 15.2 115
StereoOF-V1MT [119]96.6 9.29 92 44.8 112 4.17 73 7.22 89 34.5 106 3.68 67 13.7 95 42.6 111 3.80 57 6.06 93 38.5 113 3.27 81 11.0 113 15.1 119 9.55 109 15.1 113 49.9 122 14.0 109 1.08 46 5.51 60 5.44 98 9.33 116 15.5 119 9.73 106
Shiralkar [42]96.9 9.76 100 46.6 114 4.40 79 6.53 85 31.3 102 4.04 76 12.7 94 37.5 104 5.34 68 6.47 96 32.9 105 4.34 99 8.33 71 11.9 71 5.58 75 17.4 117 43.3 118 15.5 114 6.82 107 8.77 85 14.0 115 7.36 107 15.7 123 7.83 100
SPSA-learn [13]97.1 15.7 110 48.8 116 16.5 112 16.6 107 35.0 108 17.5 108 21.4 109 42.3 110 29.7 111 12.6 109 37.4 110 12.3 112 9.64 94 12.8 91 9.16 106 11.0 92 37.9 108 12.2 104 0.98 40 3.88 27 0.05 12 8.38 113 11.6 106 15.2 115
Filter Flow [19]99.4 14.6 107 38.2 107 8.96 107 12.4 100 34.6 107 11.3 99 20.2 108 38.3 106 30.1 113 19.2 116 43.4 117 18.6 117 10.0 101 13.4 99 9.43 108 10.3 89 31.4 91 9.08 90 8.21 117 19.6 126 0.79 46 3.72 84 6.85 63 3.41 68
Modified CLG [34]99.5 15.7 110 43.7 109 12.2 108 19.1 111 33.3 105 23.7 114 25.1 115 47.4 115 35.6 121 13.2 110 35.5 108 11.1 110 10.7 110 14.4 112 9.36 107 7.26 41 35.8 104 6.19 42 1.66 67 5.21 52 6.43 101 5.94 101 13.8 116 7.73 98
2D-CLG [1]100.8 24.4 119 51.8 120 19.4 116 27.4 121 38.7 114 33.8 123 34.6 122 57.7 121 42.2 128 33.4 126 57.1 127 32.9 125 9.64 94 12.2 80 11.0 114 11.2 95 40.2 112 12.8 106 0.31 7 2.62 7 0.25 28 6.33 102 13.7 114 7.33 97
GraphCuts [14]100.8 12.6 105 36.1 96 5.46 96 14.7 105 39.4 115 12.5 100 17.8 105 35.6 102 29.1 110 6.86 99 33.7 107 4.15 95 9.33 90 12.6 85 8.69 104 23.0 123 31.6 92 15.5 114 3.52 87 7.38 82 11.7 113 5.33 95 9.87 94 8.75 104
IAOF2 [51]101.0 8.72 90 30.9 82 5.32 94 13.9 103 31.1 101 15.4 105 14.1 97 33.0 99 18.2 100 30.8 124 42.2 116 36.4 126 9.74 97 13.8 107 6.09 83 12.0 101 33.4 98 7.96 81 7.92 116 13.9 116 7.49 107 5.69 99 10.6 100 4.51 81
BlockOverlap [61]103.8 12.3 104 29.2 74 8.49 106 13.7 102 29.6 97 15.3 104 16.2 104 32.5 96 20.0 101 8.87 106 27.4 87 7.62 107 10.9 112 13.4 99 12.5 117 13.3 107 29.1 80 10.3 96 11.8 124 14.4 119 23.8 125 10.6 119 8.92 82 24.8 123
IAOF [50]105.5 14.7 108 37.8 105 14.8 111 17.3 109 33.2 104 18.7 109 22.7 112 44.3 113 23.3 104 20.9 118 38.7 114 24.5 121 9.60 93 13.3 98 8.28 99 13.0 105 38.8 110 7.37 77 4.20 94 7.90 84 2.59 78 14.5 124 13.4 113 32.0 128
Black & Anandan [4]106.6 15.1 109 45.4 113 18.1 115 16.6 107 36.3 110 16.9 107 23.3 113 44.9 114 27.8 107 13.5 112 38.1 112 13.1 113 11.1 115 15.7 120 7.97 95 11.6 100 39.6 111 11.0 100 5.17 101 9.06 89 2.27 74 7.28 106 12.3 109 10.2 107
2bit-BM-tele [98]107.3 20.3 114 39.1 108 26.1 120 8.84 96 26.8 87 9.29 96 11.1 88 30.7 90 7.60 87 8.06 104 29.9 98 5.91 106 11.0 113 13.7 105 11.8 116 18.0 118 37.1 106 19.8 120 17.1 128 20.4 128 30.8 128 6.54 103 11.7 107 11.8 109
UnFlow [129]107.6 45.7 129 58.8 121 25.7 119 28.2 122 44.0 117 31.2 122 38.6 128 68.3 130 37.0 123 19.4 117 46.0 118 16.6 116 13.8 124 14.9 118 18.2 124 20.9 121 49.2 121 23.5 122 2.86 81 6.76 76 0.22 26 3.12 72 10.4 97 2.27 38
GroupFlow [9]108.2 22.9 118 47.1 115 26.7 122 28.4 123 50.0 124 30.8 121 25.4 116 52.4 117 30.6 114 9.32 108 29.6 97 8.14 108 10.7 110 13.4 99 7.16 91 23.0 123 46.3 119 27.8 126 1.56 64 5.72 65 2.76 80 8.00 111 12.5 110 15.3 117
Nguyen [33]108.5 20.0 113 44.7 111 17.4 114 39.5 127 37.5 112 52.5 128 34.0 121 56.0 120 38.8 124 35.6 127 47.9 120 41.1 127 12.1 117 14.3 110 16.5 122 12.0 101 37.8 107 13.8 107 1.37 58 4.27 33 0.71 44 11.6 122 14.5 118 20.8 121
SILK [79]113.5 26.9 120 51.7 119 36.6 126 22.3 115 45.5 120 24.5 115 28.8 117 54.7 119 34.2 117 18.4 115 41.6 115 15.8 115 13.1 121 16.5 121 16.1 121 19.1 120 47.8 120 19.3 119 2.87 82 4.22 31 6.53 102 15.9 125 19.1 125 25.8 124
Heeger++ [104]114.4 42.8 127 66.4 131 26.2 121 25.0 119 60.7 131 19.8 112 38.4 127 66.9 127 28.0 108 23.5 120 49.3 121 19.7 118 10.6 109 13.4 99 8.12 96 40.8 130 67.2 132 45.1 130 2.04 74 10.9 97 1.70 65 11.2 120 15.6 120 12.8 111
Horn & Schunck [3]115.9 19.9 112 61.0 125 23.3 117 19.4 112 44.3 119 19.1 110 29.5 118 58.8 123 34.9 119 21.0 119 49.9 122 21.2 119 12.3 118 16.5 121 10.8 113 17.3 116 50.6 124 18.0 117 7.23 113 11.9 106 2.34 75 13.4 123 22.2 127 14.9 114
Periodicity [78]119.6 30.6 123 48.8 116 16.7 113 24.1 117 49.8 122 26.2 118 39.1 129 54.5 118 39.5 125 13.6 113 47.1 119 12.0 111 37.5 132 48.2 132 33.6 131 38.5 129 66.9 131 36.0 129 2.02 73 10.8 95 8.18 109 20.8 128 35.9 131 30.1 126
TI-DOFE [24]120.3 44.7 128 66.3 130 66.5 131 44.2 129 50.5 125 54.8 130 43.5 131 72.0 131 44.7 130 48.6 129 63.3 128 54.0 129 13.6 123 17.7 125 15.1 120 17.2 114 50.3 123 19.0 118 3.07 84 5.50 59 2.93 83 21.5 129 24.7 129 33.9 129
FFV1MT [106]120.4 39.5 125 59.3 122 25.4 118 21.8 114 56.3 130 19.1 110 38.0 126 67.0 128 34.9 119 24.3 121 55.7 126 22.2 120 17.7 128 18.9 128 25.5 129 41.8 131 66.3 130 45.5 131 3.73 89 12.9 113 6.35 100 11.2 120 15.6 120 12.8 111
SLK [47]121.9 28.9 122 63.3 128 36.4 125 42.3 128 54.0 129 52.8 129 36.6 124 67.7 129 42.5 129 51.4 130 54.3 125 60.0 131 14.5 126 16.7 123 20.8 127 21.5 122 53.4 128 24.1 123 3.92 92 6.27 71 5.91 99 21.7 130 23.7 128 31.5 127
Adaptive flow [45]124.7 49.6 130 62.1 126 66.8 132 37.4 125 46.5 121 43.1 125 34.9 123 58.6 122 41.7 127 27.3 123 53.5 124 28.7 122 16.1 127 18.2 127 17.6 123 25.3 127 52.9 126 25.1 125 45.4 131 38.1 131 74.4 130 9.25 115 14.4 117 13.9 113
PGAM+LK [55]125.1 35.2 124 65.7 129 44.1 128 31.5 124 51.1 126 36.1 124 30.9 119 60.0 125 36.8 122 33.0 125 72.3 131 32.7 124 13.8 124 14.4 112 22.6 128 24.6 125 53.2 127 24.6 124 27.1 129 32.6 130 26.2 126 17.0 126 20.4 126 28.4 125
FOLKI [16]125.3 27.4 121 59.9 123 40.6 127 37.4 125 51.5 127 46.6 126 32.4 120 61.6 126 34.2 117 26.3 122 50.6 123 30.2 123 18.2 130 19.7 129 26.3 130 24.6 125 56.6 129 28.8 127 10.3 122 13.9 116 26.7 127 27.1 131 26.9 130 45.3 131
HCIC-L [99]125.7 51.6 131 60.9 124 30.9 123 58.4 132 53.4 128 73.0 132 39.8 130 50.8 116 52.8 132 63.4 131 71.0 130 69.9 132 18.1 129 20.6 130 20.5 126 29.9 128 43.2 116 34.1 128 73.0 132 62.0 132 76.4 131 7.45 108 12.5 110 8.87 105
Pyramid LK [2]128.5 41.0 126 62.5 127 66.4 130 47.2 130 49.9 123 59.7 131 37.5 125 59.5 124 45.5 131 43.8 128 65.1 129 49.5 128 36.5 131 43.8 131 42.6 132 43.3 132 52.8 125 45.9 132 11.8 124 20.2 127 20.7 122 40.0 132 46.5 132 59.5 132
AdaConv-v1 [126]133.0 99.3 133 97.8 133 99.8 133 99.9 133 100.0 133 99.8 133 99.9 133 99.9 133 99.9 133 99.5 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.1 133 98.9 133 99.7 133 98.5 133 93.0 133 100.0 133 99.9 133 99.9 133 99.9 133
SepConv-v1 [127]133.0 99.3 133 97.8 133 99.8 133 99.9 133 100.0 133 99.8 133 99.9 133 99.9 133 99.9 133 99.5 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.1 133 98.9 133 99.7 133 98.5 133 93.0 133 100.0 133 99.9 133 99.9 133 99.9 133
SuperSlomo [132]133.0 99.3 133 97.8 133 99.8 133 99.9 133 100.0 133 99.8 133 99.9 133 99.9 133 99.9 133 99.5 133 99.9 133 99.9 133 99.9 133 99.9 133 99.9 133 99.1 133 98.9 133 99.7 133 98.5 133 93.0 133 100.0 133 99.9 133 99.9 133 99.9 133
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.