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]9.9 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 16 2.79 19 18.9 25 1.11 19 4.82 1 6.85 1 1.73 2 4.13 4 14.6 3 2.27 2 0.52 25 5.08 58 0.00 1 0.28 3 1.04 3 0.04 2
OFLAF [77]9.9 3.84 5 17.2 11 1.99 14 2.48 5 14.1 5 1.41 9 2.96 2 10.1 2 1.17 12 2.36 10 14.7 9 0.82 11 5.15 3 7.90 7 2.15 4 6.43 34 18.2 12 4.98 18 0.27 2 2.42 4 0.07 15 0.79 10 1.88 8 1.81 26
MDP-Flow2 [68]11.6 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 30 21.7 36 1.19 24 6.35 16 8.86 13 3.12 10 5.40 14 15.7 4 5.11 20 0.38 11 3.75 26 0.02 3 0.49 6 1.80 7 0.13 7
NN-field [71]14.0 4.31 17 18.6 23 2.22 23 3.13 16 18.3 25 1.79 19 3.16 4 11.1 5 1.40 17 2.08 7 16.7 13 0.78 9 5.28 4 7.44 3 2.25 5 2.53 1 8.92 1 0.92 1 0.89 50 6.39 83 0.02 3 0.27 2 0.98 2 0.04 2
PMMST [114]14.9 4.02 10 16.5 7 1.46 1 3.86 33 16.9 17 3.33 49 3.91 10 12.6 9 2.82 41 2.18 9 9.47 3 1.30 30 5.68 9 7.88 6 2.78 7 5.25 12 13.7 2 4.29 10 0.53 27 5.11 59 0.02 3 0.26 1 0.94 1 0.04 2
nLayers [57]24.8 4.08 13 16.2 5 2.80 42 4.71 58 19.3 33 3.82 78 4.64 20 15.2 20 3.96 63 1.99 5 13.2 4 0.80 10 5.34 6 7.57 5 3.22 12 5.85 27 16.8 7 4.64 13 0.87 48 3.68 24 0.96 62 0.84 11 2.94 18 0.75 12
LME [70]26.0 3.70 3 16.1 4 1.69 2 2.13 2 13.0 2 1.19 4 5.91 47 15.4 21 7.43 92 3.23 26 22.4 41 1.19 24 6.60 23 9.12 16 4.39 46 6.11 29 20.8 21 6.60 55 0.52 25 4.96 56 0.07 15 1.09 16 3.28 26 1.86 29
ComponentFusion [96]26.3 4.03 11 17.7 15 2.19 22 2.17 4 13.1 3 1.26 5 3.86 9 13.2 11 1.58 19 2.85 22 18.0 18 1.03 17 6.68 24 9.59 23 4.14 37 8.35 76 27.3 75 8.34 91 0.60 31 4.03 34 0.52 49 0.76 9 2.22 12 1.09 14
SVFilterOh [111]27.3 4.36 19 15.9 3 2.01 17 3.04 14 16.3 13 1.78 18 3.31 6 11.3 6 1.20 13 2.02 6 13.6 6 0.57 3 5.94 12 8.69 12 2.12 3 6.61 37 19.3 14 6.32 51 5.10 114 12.9 128 10.0 126 0.75 8 2.20 11 1.32 16
FC-2Layers-FF [74]27.8 4.03 11 16.3 6 2.39 31 4.23 42 20.9 43 3.21 45 3.40 8 11.4 7 2.64 35 2.74 16 17.1 15 1.03 17 5.73 10 8.29 10 3.31 14 7.49 52 20.5 20 6.66 59 1.30 66 6.84 89 0.34 42 0.64 7 1.78 6 1.20 15
NNF-EAC [103]28.1 4.32 18 18.6 23 2.18 21 2.69 8 15.1 7 1.64 14 3.93 11 13.1 10 1.27 14 4.17 64 23.0 50 1.95 60 7.09 37 9.97 31 3.89 32 6.33 32 17.4 9 5.53 23 0.55 28 5.18 60 0.02 3 1.60 42 4.32 45 1.93 32
HAST [109]30.4 2.98 1 12.9 1 1.71 3 3.63 29 15.0 6 2.78 37 2.46 1 8.38 1 0.25 1 2.84 21 18.0 18 0.67 5 5.02 2 7.35 2 1.66 1 8.83 86 22.4 36 8.37 92 6.13 120 12.0 123 18.0 134 0.31 4 1.13 4 0.03 1
WLIF-Flow [93]30.5 3.97 9 17.0 10 2.12 19 3.53 23 18.5 27 2.37 30 4.60 19 15.1 18 2.34 31 3.40 33 20.3 31 1.50 35 7.69 61 11.4 72 4.79 61 6.67 38 17.8 11 5.53 23 0.40 14 3.68 24 0.07 15 1.59 41 3.82 36 2.63 50
RNLOD-Flow [121]32.6 3.58 2 15.7 2 1.83 6 3.60 27 19.9 36 2.06 23 5.53 41 18.1 43 2.42 33 2.75 17 17.7 16 1.01 16 6.01 13 9.09 15 3.98 34 7.21 44 20.0 16 6.87 68 2.59 89 9.67 105 1.95 81 1.06 15 2.66 15 1.79 25
FESL [72]32.7 3.91 8 16.6 8 2.13 20 5.68 84 23.5 62 4.23 85 5.17 31 16.8 27 2.99 44 2.41 12 15.8 11 0.89 14 5.76 11 8.62 11 4.05 35 5.81 23 17.6 10 5.32 22 1.09 58 5.68 74 1.21 69 1.35 25 2.89 17 1.72 23
Layers++ [37]33.0 4.39 21 17.8 16 3.14 50 3.70 30 18.0 22 2.84 38 3.37 7 11.5 8 2.65 36 2.38 11 14.1 8 0.82 11 5.33 5 7.52 4 3.78 30 7.58 55 22.0 32 6.13 44 1.81 83 7.08 93 0.54 50 1.45 32 2.46 14 4.56 92
3DFlow [135]33.0 4.65 27 19.4 27 1.86 7 3.01 13 18.5 27 1.32 7 4.17 12 14.5 14 0.62 2 1.38 2 7.93 2 0.72 7 6.90 28 10.3 45 3.76 28 11.3 107 30.0 90 10.5 110 1.63 78 4.03 34 5.22 111 0.35 5 1.27 5 0.06 5
ALD-Flow [66]34.3 4.22 14 18.2 19 1.93 12 3.20 19 16.8 16 1.59 13 5.21 32 17.4 34 1.13 9 3.70 43 22.9 48 1.26 26 6.54 22 9.31 19 3.14 11 5.25 12 21.5 27 4.98 18 0.88 49 4.67 46 4.48 107 2.69 68 6.66 66 4.79 94
TC/T-Flow [76]34.9 4.57 25 20.6 32 2.00 15 3.45 22 18.7 29 1.52 11 4.30 14 14.3 13 0.67 4 3.97 59 23.1 51 1.80 51 6.35 16 9.50 22 3.36 17 4.48 6 15.7 4 4.78 15 1.30 66 6.94 90 5.07 110 2.08 56 5.10 54 2.83 56
PMF [73]35.6 4.65 27 18.3 22 2.34 26 3.37 20 18.2 24 1.92 21 4.20 13 14.6 16 1.01 7 3.24 28 18.6 22 1.11 19 5.50 7 8.09 8 2.43 6 6.99 41 24.8 56 6.27 49 6.87 123 17.3 139 8.77 125 0.91 12 2.06 9 2.06 35
AGIF+OF [85]36.3 4.39 21 18.0 18 2.80 42 5.10 70 23.7 66 3.70 72 5.06 27 16.8 27 3.11 45 3.29 31 20.1 29 1.45 34 6.45 19 9.31 19 4.62 52 6.77 40 19.7 15 5.86 33 0.37 10 3.60 20 0.25 35 1.79 48 3.68 32 3.12 67
Correlation Flow [75]36.5 4.57 25 20.5 31 1.87 8 2.71 9 16.2 12 1.16 3 5.74 45 17.9 41 0.66 3 1.91 3 13.5 5 0.85 13 8.00 71 12.0 83 4.57 50 8.69 80 23.8 47 8.93 97 0.84 45 4.74 48 0.96 62 1.38 28 3.81 35 1.91 31
Efficient-NL [60]36.6 4.24 15 17.4 13 2.24 24 4.30 43 21.8 46 2.75 35 5.26 35 16.9 29 2.67 37 3.43 35 21.0 33 1.74 46 6.02 14 9.16 17 3.31 14 7.84 64 21.7 29 6.26 47 1.36 69 6.79 88 1.03 65 1.48 36 3.08 21 1.77 24
TC-Flow [46]38.6 4.27 16 19.0 26 1.91 11 2.85 10 16.6 15 1.45 10 5.05 26 16.9 29 0.80 6 4.05 60 23.9 60 1.74 46 6.73 25 9.68 25 2.93 9 5.83 24 22.9 41 5.68 30 1.39 71 4.87 53 7.32 121 2.46 64 6.13 61 4.49 88
ProFlow_ROB [147]38.8 5.24 45 22.0 46 2.36 29 3.71 32 20.5 40 2.17 27 6.59 54 21.5 58 2.88 43 3.48 36 22.0 38 1.14 23 6.88 27 9.84 28 3.61 21 5.84 25 23.0 42 6.06 40 0.50 24 4.91 54 0.15 25 2.29 59 6.62 65 2.50 49
OAR-Flow [125]39.4 5.41 48 21.6 43 2.61 36 4.96 66 22.3 49 2.88 39 7.90 65 23.8 63 4.19 67 4.45 71 22.7 47 1.90 55 7.03 34 10.1 35 3.39 18 5.10 10 22.3 34 4.56 12 0.29 4 2.64 8 0.17 27 1.58 40 4.89 53 1.68 21
Classic+CPF [83]40.5 4.77 32 19.7 29 2.99 45 4.59 49 23.3 60 3.08 43 5.24 33 17.2 32 2.81 40 3.32 32 21.3 34 1.57 40 6.51 21 9.49 21 4.24 42 7.39 49 21.5 27 6.27 49 1.02 53 5.33 64 1.40 72 1.47 35 3.19 24 2.47 47
IROF++ [58]43.1 4.68 29 19.4 27 2.70 39 4.66 53 23.1 55 3.42 59 5.25 34 17.2 32 3.79 59 3.95 57 23.2 53 2.05 65 6.97 31 9.84 28 4.64 53 7.99 68 24.6 53 7.05 72 0.44 17 4.30 41 0.00 1 1.37 27 3.26 25 2.83 56
ProbFlowFields [128]43.2 8.29 88 31.1 86 5.73 104 3.54 24 18.0 22 2.75 35 6.07 50 18.9 48 5.22 70 3.54 39 17.7 16 1.91 56 7.66 60 10.8 57 4.59 51 5.06 9 20.0 16 5.58 27 0.38 11 3.08 14 0.07 15 1.70 45 4.56 49 2.41 46
COFM [59]43.5 4.75 31 20.2 30 2.63 38 3.40 21 18.3 25 2.14 25 6.19 51 19.3 49 4.00 64 3.04 24 18.8 23 1.11 19 7.45 50 10.1 35 7.01 96 8.80 84 20.9 22 6.68 60 1.41 72 3.66 23 2.76 93 1.22 19 2.28 13 3.72 78
PH-Flow [101]43.5 5.11 39 21.0 34 3.62 64 4.59 49 22.4 50 3.37 53 4.37 15 14.5 14 3.45 51 3.93 56 22.5 43 2.07 68 6.34 15 9.00 14 3.74 26 7.28 47 21.7 29 6.39 53 1.61 77 5.58 72 1.58 75 1.15 18 2.12 10 3.39 73
HBM-GC [105]44.2 5.82 56 18.2 19 2.00 15 4.47 47 18.7 29 3.80 77 4.39 16 15.1 18 1.73 23 2.42 13 13.8 7 0.72 7 6.77 26 9.60 24 4.08 36 7.61 57 19.0 13 5.76 31 4.61 110 12.6 125 2.83 95 2.39 62 5.72 57 5.01 98
PWC-Net_ROB [148]44.8 9.12 96 32.2 92 4.81 90 4.68 55 22.6 51 3.66 69 7.60 62 25.0 73 5.34 71 2.47 14 15.4 10 0.97 15 7.07 35 9.98 32 3.95 33 6.32 31 25.4 62 6.26 47 0.47 21 4.66 45 0.17 27 0.98 13 3.17 23 0.31 9
Sparse-NonSparse [56]45.4 4.98 35 20.8 33 4.09 73 4.63 52 22.9 52 3.41 58 5.02 25 16.7 26 3.47 54 3.89 52 22.6 46 1.91 56 7.17 40 10.2 39 4.30 44 7.66 59 22.3 34 6.80 64 0.69 37 3.53 19 0.89 59 1.52 38 3.56 31 2.97 63
WRT [151]45.5 5.66 55 21.6 43 1.98 13 5.17 74 23.5 62 3.40 56 7.54 61 21.3 57 1.16 10 1.32 1 7.54 1 0.47 1 6.97 31 10.2 39 4.90 67 11.5 109 27.6 76 8.28 90 0.45 20 3.92 30 0.22 32 2.30 60 4.18 42 2.94 62
CostFilter [40]45.8 5.29 46 22.0 46 2.85 44 3.54 24 17.7 20 2.16 26 4.64 20 16.0 22 1.75 24 3.68 42 22.5 43 1.27 28 5.67 8 8.14 9 2.85 8 7.76 61 25.9 64 6.80 64 6.98 126 24.2 144 12.9 129 1.43 29 4.11 39 2.02 34
MLDP_OF [89]46.8 6.35 64 26.0 65 3.41 55 2.97 12 16.4 14 1.76 17 5.47 39 17.8 39 1.30 15 2.79 19 19.7 27 1.12 22 7.13 39 10.0 33 3.75 27 7.49 52 21.4 26 9.75 104 5.04 112 6.22 80 17.0 133 1.79 48 4.28 43 2.14 37
LSM [39]47.1 5.00 37 21.2 40 3.93 70 4.62 51 22.9 52 3.37 53 5.13 29 17.1 31 3.26 48 3.80 47 22.9 48 1.87 53 6.92 29 9.78 26 4.41 48 7.71 60 22.4 36 6.74 62 1.00 52 4.76 50 1.16 67 1.68 44 3.94 37 2.90 60
Classic+NL [31]47.2 5.07 38 21.0 34 4.22 77 4.70 57 23.4 61 3.27 47 4.98 24 16.5 24 3.48 55 3.75 46 22.5 43 1.68 43 7.21 43 10.2 39 4.32 45 7.82 62 22.4 36 6.71 61 1.47 73 6.39 83 1.18 68 1.12 17 2.87 16 2.27 41
FMOF [94]47.6 4.42 23 17.8 16 3.06 48 5.03 67 23.1 55 3.63 67 4.45 18 14.8 17 2.80 39 2.94 23 18.8 23 1.26 26 7.00 33 10.2 39 4.71 56 8.92 87 20.9 22 7.13 74 1.06 56 6.34 82 1.85 80 2.58 67 5.80 59 3.06 65
JOF [141]47.7 4.36 19 18.2 19 2.55 34 5.21 76 23.2 57 4.14 82 4.40 17 14.2 12 3.37 50 3.66 41 21.4 35 1.95 60 6.49 20 9.25 18 3.76 28 7.05 43 21.0 24 5.58 27 4.19 107 8.20 98 6.97 119 1.84 52 4.37 46 2.92 61
Ramp [62]47.8 5.12 40 21.1 38 3.82 69 4.68 55 23.2 57 3.47 62 4.89 23 16.3 23 3.46 52 3.83 49 22.3 40 1.93 59 7.23 44 10.2 39 4.80 62 7.61 57 22.1 33 6.80 64 1.20 62 5.04 57 1.43 73 1.36 26 2.98 19 2.31 45
IIOF-NLDP [131]48.5 6.16 60 25.7 63 2.54 33 4.55 48 23.7 66 2.40 31 5.35 38 17.6 37 1.06 8 2.78 18 17.0 14 1.54 36 8.90 93 13.4 112 4.73 57 8.04 69 22.8 39 7.69 84 0.64 35 4.61 43 0.25 35 1.81 51 4.16 41 2.72 52
Aniso-Texture [82]50.0 3.84 5 17.5 14 1.76 4 2.88 11 15.9 9 2.11 24 7.10 60 20.9 54 2.30 27 1.97 4 16.5 12 0.57 3 8.24 78 11.9 79 5.22 76 8.82 85 26.6 72 6.77 63 8.34 132 16.2 138 1.43 73 2.42 63 5.55 55 2.84 58
S2D-Matching [84]50.0 4.97 34 21.3 42 3.55 61 4.74 59 23.6 64 3.35 51 6.50 53 20.9 54 3.46 52 3.49 37 20.4 32 1.60 41 7.07 35 10.0 33 4.22 40 7.82 62 23.1 43 6.87 68 1.78 82 5.90 77 2.12 83 1.30 22 3.14 22 2.74 53
NL-TV-NCC [25]50.5 5.44 49 21.7 45 2.24 24 4.00 37 21.9 47 1.69 15 5.27 36 17.8 39 0.67 4 2.52 15 19.1 26 0.67 5 8.37 82 12.5 93 5.12 75 11.5 109 32.0 102 9.19 100 0.86 46 4.93 55 1.35 71 2.16 57 6.46 62 1.63 18
MDP-Flow [26]51.5 5.65 53 24.7 60 4.93 92 3.70 30 17.6 19 3.40 56 5.47 39 18.7 47 4.66 68 3.87 50 24.3 63 1.88 54 7.12 38 9.89 30 5.00 73 6.17 30 25.9 64 4.66 14 0.61 32 5.65 73 0.05 12 3.28 82 8.39 82 3.45 76
TV-L1-MCT [64]51.7 4.69 30 18.9 25 3.60 63 5.64 83 25.6 80 4.21 83 5.53 41 18.1 43 3.23 46 3.04 24 19.9 28 1.35 31 7.49 51 10.6 50 4.91 69 8.34 74 22.8 39 7.50 83 0.79 44 2.61 6 3.57 101 1.73 47 3.45 29 3.26 71
AggregFlow [97]52.3 6.17 61 23.3 54 2.58 35 7.01 94 28.0 99 5.29 95 8.46 70 24.2 65 7.66 95 3.73 44 20.2 30 1.73 45 7.25 45 10.6 50 3.52 19 4.43 5 16.4 6 4.80 17 0.75 41 5.43 68 0.25 35 1.92 53 4.46 48 4.12 82
IROF-TV [53]52.5 5.22 43 22.6 52 3.59 62 4.80 61 24.2 72 3.73 76 5.71 44 18.4 46 3.64 57 4.19 65 25.7 77 1.92 58 7.63 59 10.7 54 5.26 77 9.22 92 30.2 91 6.60 55 0.30 6 2.86 10 0.02 3 1.32 24 3.76 34 2.27 41
CombBMOF [113]55.3 6.51 66 28.6 75 2.61 36 3.98 36 18.7 29 2.29 29 5.29 37 17.4 34 2.33 30 5.12 81 26.1 84 3.28 87 6.35 16 9.81 27 3.34 16 12.0 114 28.4 81 15.1 126 3.73 101 12.8 127 0.76 56 0.98 13 3.00 20 0.09 6
OFH [38]55.7 6.38 65 25.7 63 4.69 86 3.90 34 20.6 41 2.24 28 7.85 64 24.2 65 2.27 26 4.11 63 25.1 68 1.72 44 7.44 49 10.4 46 4.69 54 8.13 70 28.9 83 8.44 95 0.44 17 4.25 38 0.12 22 2.80 70 8.82 92 2.74 53
Adaptive [20]56.3 5.12 40 22.0 46 2.34 26 4.82 63 23.2 57 3.50 63 8.67 75 24.5 70 3.56 56 4.19 65 25.3 74 1.83 52 7.40 48 10.6 50 3.63 22 5.84 25 23.2 45 3.75 8 3.25 97 8.86 101 0.89 59 2.87 73 6.69 67 3.14 69
Sparse Occlusion [54]56.4 4.99 36 21.1 38 2.79 41 4.13 40 20.1 39 3.00 42 5.94 49 19.4 50 2.15 25 3.41 34 21.8 37 1.35 31 8.17 76 12.1 86 4.74 58 7.87 66 25.6 63 6.34 52 11.4 138 17.7 140 2.71 92 1.64 43 4.70 52 1.81 26
Occlusion-TV-L1 [63]56.8 5.23 44 22.2 49 2.36 29 4.40 45 21.2 44 3.39 55 8.46 70 24.8 71 3.83 61 3.92 54 24.8 65 1.74 46 9.11 96 13.1 108 5.75 84 4.65 7 23.9 48 3.52 6 1.27 65 3.13 15 0.44 45 3.56 90 8.92 93 3.28 72
RFlow [90]58.0 5.85 57 24.8 62 4.44 83 3.18 17 17.9 21 1.88 20 7.81 63 24.4 69 2.32 29 3.25 29 23.4 56 1.55 37 7.94 65 11.6 75 4.86 64 8.23 71 28.0 80 6.64 58 1.16 61 2.13 2 1.13 66 4.10 101 9.22 100 6.81 107
2DHMM-SAS [92]58.3 5.14 42 21.0 34 3.79 68 5.26 77 25.2 77 3.45 60 6.97 59 20.2 51 4.18 66 4.06 61 23.3 55 2.10 69 7.18 41 10.2 39 4.92 70 8.29 72 23.7 46 7.16 75 1.26 63 5.41 67 1.63 76 1.71 46 3.75 33 2.74 53
SimpleFlow [49]58.9 5.65 53 22.4 51 4.93 92 5.47 82 24.5 75 4.28 86 6.88 58 21.0 56 3.95 62 4.74 74 25.2 70 3.02 80 7.19 42 10.1 35 4.70 55 8.34 74 23.1 43 7.16 75 1.02 53 4.61 43 0.89 59 1.29 21 3.44 27 2.47 47
ACK-Prior [27]60.0 5.49 51 24.0 57 1.81 5 2.55 6 15.7 8 0.83 1 5.07 28 17.7 38 1.52 18 2.14 8 18.1 20 0.50 2 8.64 85 11.6 75 7.10 99 14.6 126 30.7 93 11.7 115 8.46 133 11.5 119 19.5 136 3.68 94 7.25 71 2.64 51
S2F-IF [123]61.1 9.49 101 37.6 107 4.93 92 4.81 62 25.6 80 3.34 50 8.25 68 26.1 75 6.40 80 4.99 78 25.6 76 2.93 78 7.80 62 11.0 62 4.90 67 5.61 17 24.9 59 5.83 32 0.62 34 5.35 66 0.22 32 1.43 29 4.11 39 1.67 20
Complementary OF [21]62.6 7.27 75 30.0 80 4.31 78 3.18 17 18.9 32 1.52 11 5.91 47 20.2 51 2.31 28 4.22 68 24.8 65 2.05 65 7.50 54 10.4 46 4.99 72 12.3 117 31.7 101 8.87 96 0.61 32 2.69 9 1.72 78 3.33 83 9.22 100 4.88 97
ROF-ND [107]63.6 6.70 67 27.6 71 3.53 59 3.08 15 16.0 10 1.73 16 5.81 46 18.3 45 1.58 19 3.81 48 18.4 21 2.20 70 9.45 101 14.0 123 6.31 91 11.3 107 29.6 88 7.27 79 9.92 136 10.8 110 7.29 120 1.53 39 3.44 27 1.64 19
PGM-C [120]64.2 9.47 99 37.1 104 4.81 90 5.08 68 26.1 87 3.63 67 8.75 77 27.6 81 7.02 85 5.65 92 28.1 103 3.63 97 7.99 68 11.3 69 4.88 65 5.71 21 24.5 52 5.97 36 0.31 7 3.01 13 0.02 3 2.07 55 6.50 64 2.14 37
TCOF [69]64.3 7.04 73 26.9 68 3.54 60 4.93 64 23.7 66 3.45 60 9.94 90 27.8 83 7.40 91 3.74 45 23.7 59 1.55 37 10.0 115 14.3 124 4.40 47 4.91 8 17.0 8 5.53 23 5.08 113 9.68 106 4.19 105 1.43 29 4.44 47 1.69 22
TF+OM [100]66.0 6.03 59 23.7 56 2.78 40 4.39 44 19.9 36 3.57 64 8.73 76 23.0 62 11.2 101 3.57 40 23.2 53 1.36 33 7.98 67 11.1 66 5.89 86 8.95 88 25.3 61 7.06 73 1.68 80 11.2 115 0.20 29 3.56 90 8.35 81 4.18 83
FlowFields [110]66.0 9.65 103 37.6 107 5.13 97 5.09 69 25.9 84 3.72 74 8.92 79 28.3 87 7.07 87 5.45 85 26.0 82 3.82 98 7.95 66 11.2 68 5.01 74 5.75 22 26.1 68 6.01 37 0.40 14 3.29 17 0.12 22 1.92 53 5.99 60 1.89 30
DMF_ROB [140]66.9 8.16 86 33.3 95 4.93 92 4.95 65 23.7 66 3.23 46 9.38 83 28.5 89 5.85 79 5.64 91 27.3 93 3.41 92 7.49 51 10.6 50 4.44 49 6.49 35 25.9 64 6.07 41 0.40 14 3.65 21 0.07 15 3.81 97 9.06 98 4.63 93
Steered-L1 [118]67.1 4.54 24 21.2 40 2.09 18 2.13 2 13.9 4 1.31 6 4.80 22 16.5 24 1.64 21 3.87 50 25.1 68 1.60 41 8.62 84 11.5 74 7.01 96 11.1 104 28.7 82 10.4 109 12.0 142 12.3 124 34.9 144 5.90 113 9.03 97 11.6 121
FlowFields+ [130]67.5 9.76 105 38.1 111 5.31 100 5.14 71 26.2 89 3.72 74 8.99 80 28.6 90 7.15 90 5.09 80 25.9 81 3.29 88 7.82 63 11.0 62 4.94 71 5.22 11 24.7 55 5.18 21 0.70 39 5.85 76 0.30 40 1.79 48 5.77 58 1.45 17
DeepFlow2 [108]67.9 6.80 69 28.5 74 2.99 45 5.20 75 22.9 52 3.60 66 8.88 78 26.2 76 5.75 76 5.76 94 26.8 91 3.41 92 7.34 47 10.7 54 3.58 20 5.86 28 24.8 56 6.22 46 1.02 53 3.78 28 3.08 99 4.35 104 9.84 105 5.80 102
EPPM w/o HM [88]68.3 8.62 92 33.5 96 3.62 64 3.58 26 19.7 34 1.93 22 6.19 51 20.5 53 1.64 21 4.64 73 25.2 70 2.54 73 7.60 58 10.4 46 5.81 85 11.2 105 31.6 99 9.82 105 6.91 125 8.93 102 15.9 132 1.48 36 4.06 38 2.01 33
CPM-Flow [116]68.3 9.47 99 37.1 104 4.79 88 5.15 72 26.3 90 3.67 70 8.59 74 27.1 79 7.00 84 5.59 89 27.8 100 3.57 95 7.99 68 11.3 69 4.74 58 5.70 20 24.1 50 6.05 39 0.48 22 4.29 40 0.02 3 2.76 69 7.63 76 4.11 81
EpicFlow [102]69.1 9.44 98 37.1 104 4.80 89 5.15 72 26.4 91 3.70 72 9.58 85 30.0 93 7.07 87 5.38 84 27.8 100 3.29 88 8.01 72 11.3 69 4.88 65 5.67 19 24.6 53 6.12 43 0.32 9 3.13 15 0.02 3 3.10 80 7.52 74 4.79 94
ComplOF-FED-GPU [35]71.2 6.96 71 30.7 83 3.33 53 4.74 59 24.9 76 2.66 33 6.71 56 22.4 59 2.45 34 4.44 70 26.2 85 2.05 65 7.50 54 10.7 54 4.20 39 9.78 94 34.0 111 9.47 102 2.42 88 4.74 48 6.63 117 3.09 78 9.17 99 3.91 80
SRR-TVOF-NL [91]71.8 7.45 79 28.6 75 3.09 49 6.20 87 26.1 87 3.90 79 9.82 88 28.4 88 5.78 77 3.96 58 23.5 57 1.55 37 7.55 56 10.8 57 5.27 78 9.21 90 26.7 73 7.25 78 5.74 117 11.5 119 4.01 103 1.30 22 3.49 30 2.19 40
F-TV-L1 [15]72.3 8.70 93 31.4 88 8.47 113 7.61 98 27.3 96 5.86 96 11.0 93 28.0 84 5.73 75 5.75 93 28.7 106 3.32 91 7.28 46 10.8 57 3.72 23 6.59 36 26.4 69 4.38 11 1.26 63 5.30 63 0.44 45 3.04 76 7.76 77 2.29 44
SIOF [67]73.3 5.37 47 22.6 52 2.34 26 6.11 85 28.4 100 4.30 87 12.6 100 29.2 92 14.4 106 5.52 88 27.4 96 3.00 79 8.96 94 12.6 95 6.02 87 8.72 81 27.9 78 7.93 86 0.38 11 3.48 18 0.02 3 3.09 78 7.58 75 4.85 96
TV-L1-improved [17]73.5 5.52 52 23.4 55 3.42 56 4.13 40 20.8 42 2.96 40 8.29 69 24.2 65 3.64 57 4.06 61 24.4 64 1.77 49 8.34 81 12.1 86 4.15 38 13.7 121 38.4 123 14.9 123 4.40 109 10.1 108 2.14 84 3.33 83 8.42 83 3.40 74
DPOF [18]73.9 9.01 95 34.7 98 3.68 67 6.16 86 25.4 79 4.32 88 5.55 43 17.9 41 3.36 49 3.92 54 25.3 74 2.00 63 8.14 75 11.0 62 6.05 88 10.5 99 27.9 78 8.16 88 9.33 134 6.19 79 21.0 138 1.46 33 4.57 50 0.80 13
Aniso. Huber-L1 [22]74.1 5.98 58 24.2 58 3.23 52 8.53 102 27.3 96 7.91 101 9.64 86 25.6 74 5.52 73 5.00 79 25.7 77 2.75 76 8.66 86 12.8 101 4.74 58 7.60 56 24.8 56 3.51 5 3.65 100 7.24 94 3.00 98 2.57 66 6.69 67 2.86 59
Classic++ [32]76.1 5.46 50 22.2 49 4.35 80 4.66 53 22.1 48 3.57 64 8.00 66 24.3 68 5.06 69 4.21 67 25.2 70 2.01 64 8.77 89 12.7 99 5.47 79 9.03 89 30.2 91 7.29 80 2.92 95 7.73 96 3.10 100 3.83 98 8.53 84 3.87 79
LocallyOriented [52]76.3 8.05 85 30.6 82 3.63 66 8.09 100 30.8 108 6.17 98 12.3 99 32.3 100 7.04 86 4.88 77 25.2 70 2.88 77 8.80 91 12.7 99 4.27 43 5.41 15 20.4 18 6.07 41 1.35 68 6.03 78 0.99 64 3.73 96 8.62 87 4.18 83
BriefMatch [124]77.0 4.78 33 21.0 34 2.40 32 4.00 37 19.8 35 2.68 34 5.13 29 17.5 36 2.41 32 3.23 26 22.1 39 1.28 29 9.81 109 12.0 83 13.1 133 17.2 128 33.8 107 17.8 130 7.84 128 12.7 126 22.3 139 8.01 125 10.5 111 16.1 132
DeepFlow [86]78.8 7.55 80 29.3 78 4.67 85 6.29 89 23.7 66 4.86 90 10.0 91 28.0 84 8.76 100 6.15 101 27.3 93 3.83 99 7.49 51 10.8 57 3.72 23 6.40 33 26.8 74 6.85 67 1.12 59 2.92 12 3.94 102 7.07 118 11.2 116 12.7 123
FF++_ROB [146]78.9 9.90 108 38.2 112 5.12 96 5.32 80 26.0 85 4.01 80 9.76 87 30.0 93 7.58 93 5.48 86 26.2 85 3.88 101 7.83 64 11.0 62 5.63 82 7.26 45 24.3 51 7.33 81 0.78 43 3.65 21 2.88 96 2.92 75 6.46 62 6.17 105
CRTflow [80]79.4 7.63 82 31.8 91 3.42 56 4.40 45 21.2 44 2.97 41 8.99 80 26.6 77 4.11 65 4.86 76 26.5 88 2.57 74 7.99 68 11.7 77 3.26 13 18.0 132 40.2 126 22.2 135 1.47 73 4.45 42 2.51 90 4.73 106 11.4 117 7.30 108
TriFlow [95]79.5 7.87 84 30.1 81 3.19 51 7.12 95 24.4 74 7.15 100 13.9 104 31.4 97 20.0 112 3.50 38 22.4 41 1.77 49 8.70 87 11.7 77 7.03 98 7.51 54 21.9 31 6.63 57 28.6 145 14.7 135 78.3 147 2.16 57 5.57 56 2.14 37
Rannacher [23]81.8 6.99 72 27.1 69 5.36 102 5.27 78 24.3 73 4.22 84 9.51 84 27.1 79 5.54 74 4.76 75 25.7 77 2.58 75 8.80 91 12.9 104 4.82 63 11.0 102 35.7 115 9.36 101 2.33 87 4.76 50 2.39 89 2.82 72 8.01 78 3.13 68
Brox et al. [5]81.8 8.32 89 32.6 93 6.95 107 6.23 88 26.9 95 5.23 93 9.13 82 27.6 81 6.55 82 5.85 96 28.2 104 3.26 85 10.2 117 12.9 104 11.0 128 5.43 16 29.3 87 4.79 16 0.86 46 4.00 32 0.12 22 4.32 102 10.2 108 4.54 91
Local-TV-L1 [65]82.1 9.60 102 30.8 84 7.89 112 12.7 112 30.2 107 13.3 112 15.9 112 32.3 100 17.3 109 6.19 102 28.0 102 3.84 100 7.55 56 10.9 61 4.22 40 7.48 51 26.4 69 6.02 38 0.28 3 1.87 1 0.15 25 9.10 127 10.8 113 20.5 133
Bartels [41]83.0 6.83 70 26.2 66 5.19 99 3.93 35 17.4 18 3.30 48 6.63 55 22.6 60 3.25 47 4.45 71 23.9 60 2.48 72 9.12 97 12.1 86 8.25 111 10.6 100 31.1 95 12.3 118 5.74 117 10.4 109 18.9 135 5.34 108 9.52 102 8.47 114
Dynamic MRF [7]83.2 7.74 83 31.6 90 4.44 83 4.12 39 23.6 64 2.47 32 8.49 72 28.0 84 2.83 42 4.25 69 27.4 96 2.41 71 8.61 83 12.0 83 6.08 89 14.5 125 43.2 130 14.9 123 0.64 35 2.35 3 4.51 108 9.85 130 15.6 133 15.3 130
SuperFlow [81]84.1 7.15 74 27.4 70 3.52 58 10.4 107 27.8 98 11.2 109 14.5 110 31.5 99 22.4 114 5.93 97 31.6 113 3.23 84 8.77 89 11.9 79 8.59 116 5.61 17 25.9 64 3.72 7 3.76 104 11.1 114 0.37 44 3.59 92 8.96 95 3.01 64
LiteFlowNet [143]85.4 15.0 116 50.3 129 7.15 108 6.37 90 25.8 83 4.98 91 11.5 96 36.2 111 6.96 83 5.48 86 23.1 51 3.06 83 9.02 95 12.3 91 7.10 99 11.7 113 33.8 107 9.65 103 0.44 17 4.00 32 0.20 29 3.07 77 6.97 70 4.52 90
CBF [12]88.5 6.32 62 26.2 66 3.35 54 11.1 109 25.6 80 13.7 113 8.51 73 24.1 64 7.12 89 5.12 81 26.0 82 3.04 82 10.3 118 13.6 117 9.59 124 7.85 65 26.4 69 4.25 9 11.8 139 13.8 130 14.2 131 3.54 89 8.06 79 5.32 100
OFRF [134]88.5 7.28 76 24.5 59 4.75 87 14.7 116 29.6 105 15.2 114 14.3 106 29.0 91 15.9 108 6.64 105 25.7 77 5.02 110 6.95 30 10.1 35 3.72 23 8.44 77 23.9 48 7.17 77 3.30 98 6.51 85 10.8 127 9.99 131 9.82 104 24.2 136
CLG-TV [48]89.5 6.33 63 24.7 60 4.13 74 9.08 105 26.6 92 9.31 107 9.85 89 26.8 78 5.82 78 5.30 83 26.5 88 3.03 81 10.4 120 14.6 128 7.57 104 7.95 67 31.1 95 6.51 54 5.92 119 11.4 116 4.36 106 3.41 86 8.81 91 3.06 65
TriangleFlow [30]90.4 7.35 77 28.2 73 4.31 78 5.35 81 25.2 77 3.36 52 8.00 66 24.8 71 2.70 38 3.90 53 24.1 62 1.97 62 12.9 134 17.8 140 10.7 126 13.1 119 32.3 104 13.9 121 4.71 111 16.1 137 4.04 104 3.65 93 8.73 89 5.69 101
DF-Auto [115]91.6 9.74 104 34.1 97 4.36 81 14.1 115 31.9 112 15.4 116 15.6 111 33.1 106 23.6 116 5.94 98 27.3 93 3.59 96 10.4 120 14.8 131 6.97 95 3.80 3 21.1 25 2.46 3 5.25 116 11.4 116 0.49 47 4.33 103 10.4 109 4.33 85
CNN-flow-warp+ref [117]92.2 9.81 107 35.7 100 7.67 111 8.14 101 26.0 85 8.55 103 14.3 106 35.8 109 15.7 107 6.69 106 30.3 109 4.31 105 9.17 99 12.2 89 8.71 118 7.03 42 29.6 88 5.55 26 0.69 37 3.77 27 2.00 82 7.79 123 12.1 121 8.13 113
p-harmonic [29]92.3 8.47 90 36.3 102 7.17 109 5.27 78 24.1 71 4.39 89 11.2 95 31.4 97 8.13 99 7.18 110 32.4 115 5.24 112 8.04 73 11.1 66 6.89 93 9.82 95 36.4 118 10.6 111 2.61 90 5.51 70 0.54 50 4.07 100 9.01 96 4.34 86
ContinualFlow_ROB [153]93.1 15.9 120 42.0 115 9.15 116 15.5 118 32.1 113 16.9 118 19.1 117 43.0 122 24.3 117 6.50 104 26.2 85 3.53 94 9.84 111 13.0 106 6.92 94 13.8 122 33.9 110 17.4 129 0.57 30 5.33 64 0.32 41 1.46 33 4.29 44 0.68 11
FlowNet2 [122]95.5 21.7 130 43.8 118 13.5 121 24.6 131 42.3 130 27.3 131 19.8 118 40.5 116 29.9 125 8.21 117 23.6 58 5.39 114 9.85 112 12.6 95 8.54 113 8.76 82 28.9 83 5.89 34 2.77 92 15.5 136 0.81 58 1.28 20 4.68 51 0.26 8
FlowNetS+ft+v [112]96.1 7.57 81 29.4 79 3.96 71 7.50 97 26.6 92 6.48 99 14.3 106 32.7 104 17.5 110 7.55 111 31.3 111 5.28 113 10.5 122 14.7 129 7.49 103 6.75 39 27.8 77 6.97 71 4.01 106 8.84 100 6.77 118 3.52 88 9.71 103 3.61 77
EAI-Flow [152]97.1 18.4 122 42.5 116 11.6 118 10.8 108 32.2 114 9.62 108 14.3 106 38.9 115 14.0 104 7.07 109 28.6 105 5.13 111 8.20 77 11.9 79 5.47 79 9.21 90 30.7 93 9.05 98 9.33 134 6.96 91 0.49 47 2.48 65 7.31 72 3.20 70
LDOF [28]97.5 8.22 87 31.4 88 4.08 72 7.64 99 29.4 102 5.87 97 10.7 92 30.3 95 7.99 98 7.80 114 36.8 122 4.86 109 9.14 98 12.4 92 8.24 110 8.58 78 32.0 102 8.38 93 1.75 81 5.26 62 5.02 109 5.52 110 12.9 125 6.04 104
SegOF [10]97.7 12.6 112 34.9 99 7.20 110 21.3 125 36.9 122 25.3 129 21.6 122 40.5 116 31.8 129 14.1 127 37.7 124 10.8 122 10.3 118 12.5 93 12.6 132 10.2 97 40.2 126 11.2 113 0.29 4 2.91 11 0.07 15 2.90 74 8.68 88 2.07 36
Fusion [6]98.0 8.51 91 37.6 107 6.69 106 3.62 28 20.0 38 3.08 43 6.82 57 22.6 60 6.47 81 5.78 95 31.3 111 4.29 104 11.2 130 14.7 129 10.6 125 14.0 123 35.2 113 15.0 125 7.88 129 14.3 133 2.22 85 5.35 109 11.0 114 8.56 115
AugFNG_ROB [144]98.2 18.1 121 47.6 124 10.8 117 23.9 129 39.8 128 28.6 132 22.8 125 49.1 127 29.3 123 7.57 112 25.0 67 4.54 108 9.90 114 12.8 101 8.92 119 8.31 73 33.8 107 8.19 89 0.76 42 7.01 92 0.25 35 2.80 70 7.45 73 1.85 28
EPMNet [133]99.2 21.3 129 48.9 128 14.5 123 23.2 128 44.2 132 25.1 128 18.8 116 37.9 113 28.4 121 8.92 119 27.5 99 5.90 116 9.85 112 12.6 95 8.54 113 8.76 82 28.9 83 5.89 34 1.98 84 11.4 116 0.59 52 2.36 61 8.59 86 0.63 10
ResPWCR_ROB [145]100.5 18.8 123 53.9 132 13.5 121 8.80 103 29.4 102 8.15 102 12.6 100 36.0 110 12.1 102 7.61 113 32.2 114 5.71 115 8.07 74 10.4 46 8.08 107 9.68 93 34.5 112 10.3 107 3.74 103 9.01 103 1.82 79 3.35 85 8.20 80 4.45 87
WOLF_ROB [149]100.5 11.7 109 48.4 125 5.18 98 12.5 111 38.6 125 8.94 104 18.0 115 43.3 123 13.5 103 7.96 115 30.5 110 5.97 118 8.25 79 11.4 72 6.75 92 10.9 101 36.1 117 10.2 106 0.72 40 4.15 36 1.28 70 5.67 111 11.0 114 10.2 119
Learning Flow [11]100.8 6.74 68 28.1 72 3.03 47 6.37 90 28.7 101 5.02 92 11.8 97 32.6 103 7.93 97 6.87 108 33.2 119 4.32 106 12.5 133 17.4 138 7.78 105 9.98 96 35.2 113 8.41 94 2.66 91 10.9 112 2.24 86 6.76 117 13.7 127 6.41 106
StereoFlow [44]102.7 58.0 147 76.4 147 63.7 144 51.8 146 66.9 147 48.3 142 51.0 147 73.0 146 41.6 139 63.5 146 83.4 147 56.7 144 13.3 136 13.7 118 19.1 139 3.63 2 20.4 18 2.73 4 0.26 1 2.49 5 0.05 12 4.06 99 8.57 85 5.81 103
Second-order prior [8]103.1 7.35 77 31.2 87 4.16 75 6.80 93 29.5 104 5.27 94 11.8 97 33.3 107 7.78 96 6.05 99 27.2 92 3.90 102 9.67 106 13.8 121 5.74 83 14.0 123 41.8 129 11.7 115 6.86 122 9.72 107 7.61 123 4.72 105 10.1 107 7.78 111
Ad-TV-NDC [36]103.7 21.2 128 36.8 103 34.1 138 25.9 133 38.5 124 29.9 133 23.5 127 41.0 118 27.1 118 13.3 124 32.4 115 13.3 127 8.75 88 13.2 109 3.82 31 7.43 50 25.1 60 6.92 70 1.50 75 4.84 52 0.34 42 17.1 141 15.9 137 37.2 145
HBpMotionGpu [43]104.5 11.7 109 32.8 94 6.34 105 18.9 122 35.4 120 22.0 125 22.3 123 42.7 121 31.1 128 5.62 90 26.7 90 3.31 90 9.47 102 13.0 106 8.55 115 8.68 79 31.2 97 5.58 27 6.88 124 11.9 121 0.64 53 7.67 122 11.4 117 15.2 128
Shiralkar [42]106.4 9.76 105 46.6 122 4.40 82 6.53 92 31.3 110 4.04 81 12.7 102 37.5 112 5.34 71 6.47 103 32.9 118 4.34 107 8.33 80 11.9 79 5.58 81 17.4 131 43.3 132 15.5 127 6.82 121 8.77 99 14.0 130 7.36 120 15.7 136 7.83 112
StereoOF-V1MT [119]106.6 9.29 97 44.8 120 4.17 76 7.22 96 34.5 117 3.68 71 13.7 103 42.6 120 3.80 60 6.06 100 38.5 126 3.27 86 11.0 127 15.1 133 9.55 123 15.1 127 49.9 136 14.0 122 1.08 57 5.51 70 5.44 112 9.33 129 15.5 132 9.73 118
LFNet_ROB [150]106.8 20.5 127 60.8 137 12.8 120 10.1 106 31.7 111 9.00 105 20.6 120 53.4 130 14.0 104 9.26 120 32.6 117 7.53 119 9.83 110 13.2 109 8.22 109 11.5 109 37.7 120 11.3 114 1.13 60 6.72 86 0.74 55 3.50 87 8.77 90 5.19 99
SPSA-learn [13]108.0 15.7 118 48.8 126 16.5 125 16.6 119 35.0 119 17.5 120 21.4 121 42.3 119 29.7 124 12.6 122 37.4 123 12.3 125 9.64 104 12.8 101 9.16 120 11.0 102 37.9 122 12.2 117 0.98 51 3.88 29 0.05 12 8.38 126 11.6 119 15.2 128
Filter Flow [19]110.0 14.6 114 38.2 112 8.96 115 12.4 110 34.6 118 11.3 110 20.2 119 38.3 114 30.1 126 19.2 129 43.4 130 18.6 130 10.0 115 13.4 112 9.43 122 10.3 98 31.4 98 9.08 99 8.21 131 19.6 141 0.79 57 3.72 95 6.85 69 3.41 75
Modified CLG [34]110.8 15.7 118 43.7 117 12.2 119 19.1 123 33.3 116 23.7 126 25.1 128 47.4 126 35.6 134 13.2 123 35.5 121 11.1 123 10.7 124 14.4 126 9.36 121 7.26 45 35.8 116 6.19 45 1.66 79 5.21 61 6.43 115 5.94 114 13.8 129 7.73 110
IAOF2 [51]111.2 8.72 94 30.9 85 5.32 101 13.9 114 31.1 109 15.4 116 14.1 105 33.0 105 18.2 111 30.8 138 42.2 129 36.4 140 9.74 108 13.8 121 6.09 90 12.0 114 33.4 105 7.96 87 7.92 130 13.9 131 7.49 122 5.69 112 10.6 112 4.51 89
GraphCuts [14]111.2 12.6 112 36.1 101 5.46 103 14.7 116 39.4 127 12.5 111 17.8 114 35.6 108 29.1 122 6.86 107 33.7 120 4.15 103 9.33 100 12.6 95 8.69 117 23.0 137 31.6 99 15.5 127 3.52 99 7.38 95 11.7 128 5.33 107 9.87 106 8.75 116
2D-CLG [1]112.0 24.4 132 51.8 131 19.4 129 27.4 134 38.7 126 33.8 136 34.6 135 57.7 134 42.2 141 33.4 140 57.1 141 32.9 139 9.64 104 12.2 89 11.0 128 11.2 105 40.2 126 12.8 119 0.31 7 2.62 7 0.25 35 6.33 115 13.7 127 7.33 109
TVL1_ROB [139]113.0 36.9 139 55.3 133 54.3 143 36.5 138 40.3 129 46.0 140 36.6 137 59.4 137 43.5 144 30.0 137 49.3 134 31.8 137 9.70 107 13.7 118 7.19 102 7.34 48 33.4 105 7.88 85 0.56 29 3.98 31 0.10 21 15.1 138 15.9 137 33.3 143
BlockOverlap [61]114.7 12.3 111 29.2 77 8.49 114 13.7 113 29.6 105 15.3 115 16.2 113 32.5 102 20.0 112 8.87 118 27.4 96 7.62 120 10.9 126 13.4 112 12.5 131 13.3 120 29.1 86 10.3 107 11.8 139 14.4 134 23.8 140 10.6 132 8.92 93 24.8 137
IAOF [50]117.2 14.7 115 37.8 110 14.8 124 17.3 121 33.2 115 18.7 121 22.7 124 44.3 124 23.3 115 20.9 131 38.7 127 24.5 134 9.60 103 13.3 111 8.28 112 13.0 118 38.8 124 7.37 82 4.20 108 7.90 97 2.59 91 14.5 137 13.4 126 32.0 142
2bit-BM-tele [98]118.7 20.3 126 39.1 114 26.1 133 8.84 104 26.8 94 9.29 106 11.1 94 30.7 96 7.60 94 8.06 116 29.9 108 5.91 117 11.0 127 13.7 118 11.8 130 18.0 132 37.1 119 19.8 134 17.1 143 20.4 143 30.8 143 6.54 116 11.7 120 11.8 122
Black & Anandan [4]118.9 15.1 117 45.4 121 18.1 128 16.6 119 36.3 121 16.9 118 23.3 126 44.9 125 27.8 119 13.5 125 38.1 125 13.1 126 11.1 129 15.7 134 7.97 106 11.6 112 39.6 125 11.0 112 5.17 115 9.06 104 2.27 87 7.28 119 12.3 122 10.2 119
UnFlow [129]120.0 45.7 144 58.8 134 25.7 132 28.2 135 44.0 131 31.2 135 38.6 142 68.3 144 37.0 136 19.4 130 46.0 131 16.6 129 13.8 138 14.9 132 18.2 138 20.9 135 49.2 135 23.5 136 2.86 93 6.76 87 0.22 32 3.12 81 10.4 109 2.27 41
GroupFlow [9]120.8 22.9 131 47.1 123 26.7 136 28.4 136 50.0 138 30.8 134 25.4 129 52.4 129 30.6 127 9.32 121 29.6 107 8.14 121 10.7 124 13.4 112 7.16 101 23.0 137 46.3 133 27.8 140 1.56 76 5.72 75 2.76 93 8.00 124 12.5 123 15.3 130
Nguyen [33]121.1 20.0 125 44.7 119 17.4 127 39.5 142 37.5 123 52.5 143 34.0 134 56.0 133 38.8 137 35.6 141 47.9 133 41.1 141 12.1 131 14.3 124 16.5 136 12.0 114 37.8 121 13.8 120 1.37 70 4.27 39 0.71 54 11.6 135 14.5 131 20.8 134
SILK [79]126.5 26.9 133 51.7 130 36.6 140 22.3 127 45.5 134 24.5 127 28.8 130 54.7 132 34.2 130 18.4 128 41.6 128 15.8 128 13.1 135 16.5 135 16.1 135 19.1 134 47.8 134 19.3 133 2.87 94 4.22 37 6.53 116 15.9 139 19.1 139 25.8 138
Heeger++ [104]127.9 42.8 142 66.4 146 26.2 134 25.0 132 60.7 146 19.8 124 38.4 141 66.9 141 28.0 120 23.5 133 49.3 134 19.7 131 10.6 123 13.4 112 8.12 108 40.8 145 67.2 147 45.1 145 2.04 86 10.9 112 1.70 77 11.2 133 15.6 133 12.8 124
H+S_ROB [138]128.9 35.2 137 65.0 143 26.4 135 38.8 141 57.8 145 44.7 139 46.2 146 74.1 147 43.1 143 64.3 147 66.9 144 69.3 146 17.9 143 19.2 143 29.2 145 30.3 143 59.6 144 34.1 142 0.49 23 4.67 46 0.20 29 22.3 145 23.4 142 21.4 135
Horn & Schunck [3]129.3 19.9 124 61.0 139 23.3 130 19.4 124 44.3 133 19.1 122 29.5 131 58.8 136 34.9 132 21.0 132 49.9 136 21.2 132 12.3 132 16.5 135 10.8 127 17.3 130 50.6 138 18.0 131 7.23 127 11.9 121 2.34 88 13.4 136 22.2 141 14.9 127
Periodicity [78]133.3 30.6 136 48.8 126 16.7 126 24.1 130 49.8 136 26.2 130 39.1 143 54.5 131 39.5 138 13.6 126 47.1 132 12.0 124 37.5 147 48.2 147 33.6 146 38.5 144 66.9 146 36.0 144 2.02 85 10.8 110 8.18 124 20.8 142 35.9 146 30.1 140
FFV1MT [106]134.0 39.5 140 59.3 135 25.4 131 21.8 126 56.3 144 19.1 122 38.0 140 67.0 142 34.9 132 24.3 134 55.7 140 22.2 133 17.7 142 18.9 142 25.5 143 41.8 146 66.3 145 45.5 146 3.73 101 12.9 128 6.35 114 11.2 133 15.6 133 12.8 124
TI-DOFE [24]134.4 44.7 143 66.3 145 66.5 146 44.2 144 50.5 139 54.8 145 43.5 145 72.0 145 44.7 145 48.6 143 63.3 142 54.0 143 13.6 137 17.7 139 15.1 134 17.2 128 50.3 137 19.0 132 3.07 96 5.50 69 2.93 97 21.5 143 24.7 144 33.9 144
SLK [47]135.7 28.9 135 63.3 142 36.4 139 42.3 143 54.0 143 52.8 144 36.6 137 67.7 143 42.5 142 51.4 144 54.3 139 60.0 145 14.5 140 16.7 137 20.8 141 21.5 136 53.4 142 24.1 137 3.92 105 6.27 81 5.91 113 21.7 144 23.7 143 31.5 141
Adaptive flow [45]138.5 49.6 145 62.1 140 66.8 147 37.4 139 46.5 135 43.1 138 34.9 136 58.6 135 41.7 140 27.3 136 53.5 138 28.7 135 16.1 141 18.2 141 17.6 137 25.3 141 52.9 140 25.1 139 45.4 146 38.1 146 74.4 145 9.25 128 14.4 130 13.9 126
PGAM+LK [55]139.1 35.2 137 65.7 144 44.1 142 31.5 137 51.1 140 36.1 137 30.9 132 60.0 139 36.8 135 33.0 139 72.3 146 32.7 138 13.8 138 14.4 126 22.6 142 24.6 139 53.2 141 24.6 138 27.1 144 32.6 145 26.2 141 17.0 140 20.4 140 28.4 139
FOLKI [16]139.4 27.4 134 59.9 136 40.6 141 37.4 139 51.5 141 46.6 141 32.4 133 61.6 140 34.2 130 26.3 135 50.6 137 30.2 136 18.2 145 19.7 144 26.3 144 24.6 139 56.6 143 28.8 141 10.3 137 13.9 131 26.7 142 27.1 146 26.9 145 45.3 146
HCIC-L [99]139.9 51.6 146 60.9 138 30.9 137 58.4 147 53.4 142 73.0 147 39.8 144 50.8 128 52.8 147 63.4 145 71.0 145 69.9 147 18.1 144 20.6 145 20.5 140 29.9 142 43.2 130 34.1 142 73.0 147 62.0 147 76.4 146 7.45 121 12.5 123 8.87 117
Pyramid LK [2]143.2 41.0 141 62.5 141 66.4 145 47.2 145 49.9 137 59.7 146 37.5 139 59.5 138 45.5 146 43.8 142 65.1 143 49.5 142 36.5 146 43.8 146 42.6 147 43.3 147 52.8 139 45.9 147 11.8 139 20.2 142 20.7 137 40.0 147 46.5 147 59.5 147
AVG_FLOW_ROB [142]148.2 99.3 148 98.3 154 99.2 148 99.8 148 100.0 148 99.7 148 99.9 148 99.9 148 99.9 148 98.3 148 96.8 148 98.0 148 96.2 148 96.6 148 93.9 148 87.7 148 86.6 148 88.2 148 96.9 148 84.2 148 98.7 148 93.0 148 98.4 148 95.3 148
AdaConv-v1 [126]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
SepConv-v1 [127]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
SuperSlomo [132]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
FGIK [136]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
CtxSyn [137]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
CyclicGen [154]148.8 99.3 148 97.8 148 99.8 149 99.9 149 100.0 148 99.8 149 99.9 148 99.9 148 99.9 148 99.5 149 99.9 149 99.9 149 99.9 149 99.9 149 99.9 149 99.1 149 98.9 149 99.7 149 98.5 149 93.0 149 100.0 149 99.9 149 99.9 149 99.9 149
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. IEEE TIP 26(8):4055-4067, 2017.
[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.
[136] FGIK 0.18 2 color Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[139] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[140] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[141] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[142] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[143] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[151] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[152] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[153] ContinualFlow_ROB 0.5 all color Anonymous. Continual Flow. ACCV 2018 submission 273.
[154] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
* 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.