Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R1.0
endpoint
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]7.6 0.82 12 4.87 13 0.37 18 1.75 7 12.1 8 0.53 6 2.22 2 7.90 2 0.57 9 1.07 5 9.10 7 0.17 3 9.77 1 16.5 1 2.56 2 4.53 3 15.6 2 3.00 3 0.00 1 0.02 40 0.00 1 5.99 10 19.5 24 3.94 2
OFLAF [77]9.4 0.82 12 4.86 12 0.38 20 1.74 5 11.1 5 0.62 13 2.08 1 7.42 1 0.57 9 1.61 13 12.0 13 0.48 14 11.2 6 19.0 6 3.96 6 6.81 23 19.8 11 4.79 23 0.00 1 0.00 1 0.00 1 5.80 7 15.6 3 9.76 19
PMMST [114]9.8 0.65 2 3.86 2 0.05 1 2.23 18 13.5 16 1.21 35 2.81 8 9.66 8 0.83 15 1.29 7 6.70 3 0.42 12 11.7 7 19.1 7 5.55 10 5.50 8 17.8 6 4.52 15 0.00 1 0.02 40 0.00 1 5.44 4 15.8 4 5.70 6
NN-field [71]12.7 0.89 25 5.29 27 0.40 27 2.06 13 14.1 21 0.62 13 2.49 4 8.79 5 0.68 12 0.99 3 8.66 6 0.09 2 9.99 2 16.8 2 2.51 1 6.53 20 11.2 1 2.42 2 0.01 44 0.02 40 0.00 1 5.86 8 19.6 25 2.84 1
MDP-Flow2 [68]14.0 0.77 6 4.59 6 0.31 5 1.46 2 9.56 1 0.39 1 2.59 5 9.00 6 0.91 20 2.48 50 17.7 58 0.70 49 14.1 22 23.0 21 8.20 26 5.27 5 18.2 7 4.66 18 0.00 1 0.00 1 0.00 1 5.91 9 16.7 7 8.80 10
Correlation Flow [75]17.9 0.81 9 4.81 10 0.22 2 2.03 10 13.0 11 0.42 2 5.14 52 15.7 50 0.55 8 1.09 6 8.36 5 0.28 8 16.6 41 26.1 41 10.8 47 7.92 32 22.7 24 4.18 12 0.00 1 0.02 40 0.00 1 5.54 5 17.2 8 5.00 5
WLIF-Flow [93]18.2 0.84 17 4.97 18 0.34 11 2.03 10 13.3 14 0.76 21 3.64 20 12.0 18 1.41 32 2.23 36 14.4 28 0.55 21 13.1 14 21.6 14 7.54 19 8.23 38 20.9 15 5.39 33 0.00 1 0.00 1 0.00 1 6.94 17 18.0 12 10.4 25
NNF-EAC [103]24.5 0.81 9 4.82 11 0.39 25 1.95 9 12.0 7 0.83 24 3.16 11 10.6 11 1.00 22 2.60 54 18.5 62 0.77 55 13.9 19 22.8 20 7.86 21 6.67 21 19.3 9 5.14 31 0.10 61 0.02 40 0.00 1 7.08 21 19.2 18 10.5 26
ComponentFusion [96]25.4 0.98 48 5.81 56 0.37 18 1.59 4 10.7 4 0.53 6 2.84 9 9.86 9 0.85 18 1.94 20 13.3 16 0.54 19 15.3 35 24.9 35 10.5 46 6.83 24 26.2 50 5.50 36 0.03 52 0.00 1 0.32 63 6.69 12 18.5 14 9.59 15
TC/T-Flow [76]26.5 0.71 3 4.20 3 0.40 27 2.67 33 15.4 29 0.77 22 3.30 14 11.2 12 0.44 4 2.33 41 15.9 44 0.60 30 14.8 27 23.6 26 8.02 22 3.70 1 15.8 3 2.27 1 0.13 64 0.02 40 1.23 84 7.85 35 21.7 37 10.9 35
Layers++ [37]26.8 0.91 31 5.39 33 0.43 41 2.18 17 13.9 20 0.96 26 2.73 7 9.43 7 1.40 31 1.70 15 10.5 10 0.56 22 10.2 3 16.8 2 6.50 14 9.09 51 22.7 24 5.92 48 0.21 73 0.02 40 0.69 67 6.88 14 17.6 11 10.9 35
AGIF+OF [85]27.3 0.90 27 5.34 29 0.42 36 3.13 48 19.3 51 1.37 41 3.87 24 12.8 21 1.80 46 2.19 33 14.3 25 0.64 36 12.4 9 20.6 9 7.20 17 9.27 56 22.4 21 5.97 52 0.00 1 0.00 1 0.00 1 7.26 24 18.8 16 10.7 32
FC-2Layers-FF [74]27.5 0.87 22 5.16 23 0.42 36 2.70 35 17.8 41 1.20 33 2.59 5 8.73 4 1.39 30 1.88 18 13.3 16 0.50 15 11.1 5 18.0 5 6.07 11 9.16 54 21.3 17 5.89 46 0.04 56 0.02 40 0.22 60 7.48 28 19.4 21 11.1 40
IIOF-NLDP [131]29.0 1.01 54 5.97 60 0.24 4 2.82 38 17.3 38 0.66 16 4.36 41 14.3 38 0.43 3 0.99 3 7.36 4 0.24 7 15.0 30 24.3 30 6.98 15 9.70 67 24.0 36 6.32 67 0.01 44 0.02 40 0.00 1 7.22 23 19.9 27 7.14 9
LME [70]30.2 0.95 44 5.67 49 0.38 20 1.45 1 9.68 2 0.43 3 5.19 53 13.3 29 6.57 98 2.44 47 18.3 60 0.68 43 15.2 33 24.4 31 10.2 43 6.17 17 21.9 18 5.18 32 0.00 1 0.02 40 0.00 1 7.05 18 19.3 19 10.2 23
ALD-Flow [66]31.3 0.79 7 4.72 9 0.38 20 2.44 29 13.5 16 0.80 23 4.33 39 14.7 43 0.88 19 2.92 70 19.4 68 0.82 59 17.5 44 28.1 45 10.0 41 5.61 10 24.7 41 3.10 4 0.00 1 0.00 1 0.00 1 9.09 50 26.3 56 11.9 56
nLayers [57]31.8 0.88 23 5.25 25 0.44 45 2.79 37 15.6 33 1.47 47 4.34 40 14.4 39 2.33 61 1.54 11 11.6 12 0.52 18 10.4 4 17.1 4 5.51 9 8.89 45 19.3 9 5.79 45 0.31 84 0.00 1 1.16 82 7.27 25 19.3 19 11.3 46
MLDP_OF [89]32.6 0.94 41 5.51 44 0.36 16 1.74 5 11.7 6 0.44 5 4.05 30 13.1 26 0.50 7 1.48 9 12.3 14 0.29 9 15.4 36 24.7 34 9.15 31 5.54 9 18.2 7 3.11 5 1.54 122 0.05 104 9.31 130 8.33 42 21.4 36 9.39 14
PH-Flow [101]33.6 0.93 39 5.49 41 0.42 36 2.87 39 17.6 40 1.33 40 2.99 10 10.1 10 1.76 45 2.27 38 14.6 33 0.68 43 12.5 10 20.8 11 6.28 12 7.79 29 20.9 15 5.39 33 0.39 92 0.02 40 1.63 95 6.88 14 19.0 17 10.3 24
3DFlow [135]33.8 0.92 37 5.49 41 0.34 11 2.26 19 15.2 27 0.54 9 3.57 17 12.4 19 0.47 5 0.31 1 3.40 1 0.01 1 13.6 16 22.2 17 7.25 18 12.2 105 27.4 60 7.12 91 2.77 133 0.02 40 10.0 131 5.36 3 15.8 4 4.88 4
RNLOD-Flow [121]34.0 0.79 7 4.69 7 0.34 11 2.67 33 17.2 37 1.09 30 4.46 45 14.5 41 1.53 36 2.01 23 14.3 25 0.60 30 14.2 24 23.1 23 8.72 29 8.21 36 19.9 12 5.90 47 0.35 88 0.03 100 1.48 93 6.51 11 17.2 8 9.80 21
HAST [109]34.2 0.92 37 5.41 35 0.35 14 3.21 51 13.6 18 1.99 74 2.45 3 8.47 3 0.29 1 2.24 37 14.5 31 0.40 11 11.7 7 19.4 8 3.63 3 11.0 93 24.2 37 6.87 85 2.75 132 0.00 1 11.6 134 4.05 1 13.1 1 4.43 3
ProbFlowFields [128]35.8 1.16 73 6.86 81 0.85 99 2.32 21 14.6 23 1.45 45 4.28 37 14.9 45 2.43 64 1.56 12 9.89 8 0.50 15 18.1 48 29.1 50 11.5 51 4.44 2 20.6 13 4.20 13 0.00 1 0.02 40 0.00 1 8.97 48 25.7 51 9.75 17
IROF++ [58]36.1 0.96 45 5.70 54 0.44 45 3.00 45 19.4 52 1.37 41 3.90 26 12.8 21 1.96 51 2.36 44 15.8 43 0.69 47 14.1 22 23.0 21 8.22 27 9.14 53 25.0 42 6.07 58 0.00 1 0.02 40 0.00 1 7.35 26 20.3 29 10.8 33
Efficient-NL [60]37.2 0.93 39 5.47 40 0.39 25 2.76 36 18.0 44 1.11 31 4.12 34 13.3 29 1.15 25 2.15 30 14.1 23 0.66 38 13.0 13 21.3 13 7.16 16 10.6 85 23.4 30 6.41 73 0.26 78 0.02 40 1.13 80 7.35 26 17.4 10 10.9 35
TC-Flow [46]37.3 0.75 5 4.45 5 0.38 20 2.04 12 12.6 10 0.70 17 4.23 36 14.4 39 0.77 13 2.56 52 17.5 56 0.63 34 17.1 43 27.8 44 9.45 34 5.73 12 25.6 46 3.12 6 0.22 75 0.02 40 2.41 106 10.1 57 25.9 53 15.4 80
SVFilterOh [111]37.5 1.07 61 6.27 67 0.44 45 2.07 14 13.1 13 0.72 18 3.24 12 11.2 12 1.05 23 1.99 22 13.8 20 0.56 22 12.6 12 21.1 12 3.80 4 10.5 83 22.4 21 5.97 52 2.31 128 0.39 124 6.95 123 4.87 2 14.8 2 6.01 7
Classic+CPF [83]38.0 0.89 25 5.26 26 0.41 32 3.03 46 19.4 52 1.27 38 4.14 35 13.6 32 1.64 42 2.12 29 14.4 28 0.64 36 13.6 16 22.2 17 7.82 20 9.85 71 22.6 23 6.18 61 0.36 89 0.02 40 1.50 94 7.07 19 18.5 14 10.5 26
FESL [72]38.0 0.83 15 4.91 16 0.36 16 3.90 79 21.6 73 1.75 61 4.06 31 13.4 31 1.61 39 2.02 25 14.1 23 0.56 22 13.3 15 21.7 15 8.08 24 9.19 55 22.0 19 6.25 64 0.34 87 0.02 40 1.16 82 7.51 29 18.3 13 11.0 39
FMOF [94]39.2 0.83 15 4.92 17 0.43 41 3.35 59 20.0 57 1.57 54 3.37 16 11.4 15 1.46 34 1.98 21 13.8 20 0.56 22 14.2 24 23.2 24 8.08 24 9.98 76 22.7 24 6.19 62 0.42 95 0.02 40 1.87 100 8.11 41 21.0 33 10.5 26
HBM-GC [105]40.3 1.24 82 7.38 86 0.52 60 2.50 31 15.5 32 1.40 43 4.06 31 14.1 36 1.32 28 1.77 16 13.2 15 0.61 32 13.7 18 22.1 16 8.06 23 8.98 48 16.5 4 4.42 14 1.30 119 0.02 40 3.28 113 7.20 22 19.8 26 10.8 33
Sparse-NonSparse [56]40.8 0.88 23 5.21 24 0.40 27 3.16 50 19.8 56 1.53 52 3.90 26 12.9 23 2.00 53 2.18 32 15.2 39 0.66 38 15.6 37 25.4 38 10.1 42 9.38 58 23.7 34 5.97 52 0.31 84 0.00 1 1.28 85 7.74 31 20.9 31 11.2 44
Aniso-Texture [82]40.9 0.73 4 4.33 4 0.33 8 1.83 8 12.4 9 0.91 25 6.29 65 18.2 57 1.57 37 1.35 8 11.4 11 0.18 5 19.7 63 29.7 52 16.8 83 9.10 52 26.1 49 5.78 44 0.26 78 0.18 111 0.07 51 9.32 52 24.3 49 12.2 57
Ramp [62]41.0 0.90 27 5.36 30 0.41 32 3.14 49 20.0 57 1.52 49 3.86 23 12.9 23 1.93 49 2.01 23 14.5 31 0.59 28 15.1 32 24.4 31 9.67 38 9.44 59 22.9 27 5.95 50 0.29 82 0.02 40 1.38 89 7.83 34 20.9 31 11.5 49
PMF [73]41.2 1.08 62 6.23 65 0.35 14 2.33 22 14.8 24 0.60 11 3.87 24 13.6 32 0.62 11 2.29 39 14.4 28 0.44 13 14.0 21 23.3 25 3.86 5 9.55 60 28.3 71 6.63 78 0.89 113 0.79 134 3.74 117 5.66 6 15.8 4 8.92 11
ProFlow_ROB [147]41.5 1.18 75 7.01 84 0.57 75 2.87 39 17.8 41 1.32 39 5.44 54 18.3 59 1.71 44 2.83 65 17.9 59 0.70 49 18.5 49 30.3 59 9.32 32 6.29 18 25.3 45 3.36 8 0.00 1 0.00 1 0.00 1 7.96 36 24.6 50 8.97 13
JOF [141]41.7 0.98 48 5.69 51 0.45 49 3.43 62 20.4 61 1.74 60 3.59 19 11.7 17 2.20 56 2.30 40 15.3 40 0.67 41 12.5 10 20.7 10 6.41 13 8.98 48 22.2 20 5.76 42 1.88 125 0.00 1 4.61 118 7.07 19 19.4 21 10.6 30
CombBMOF [113]42.4 0.91 31 5.38 31 0.33 8 2.30 20 13.4 15 0.64 15 3.33 15 11.5 16 0.78 14 2.08 27 15.3 40 0.77 55 13.9 19 22.3 19 8.24 28 13.0 116 26.2 50 11.4 123 0.56 100 0.02 40 0.86 74 8.93 47 21.1 34 15.6 81
NL-TV-NCC [25]43.0 0.96 45 5.68 50 0.22 2 2.93 42 18.4 46 0.59 10 4.37 43 14.6 42 0.47 5 1.63 14 14.6 33 0.17 3 18.6 51 29.8 53 9.76 40 11.8 104 31.2 96 7.70 103 0.12 62 0.00 1 0.30 61 9.40 54 26.0 55 9.75 17
LSM [39]43.4 0.86 21 5.13 22 0.40 27 3.22 52 20.3 60 1.54 53 4.08 33 13.6 32 1.93 49 2.09 28 14.9 37 0.63 34 15.6 37 25.3 37 10.2 43 9.58 62 24.6 38 5.95 50 0.30 83 0.02 40 1.43 90 7.97 37 21.7 37 11.1 40
OFH [38]44.2 0.81 9 4.70 8 0.31 5 2.96 44 17.3 38 1.20 33 6.37 67 19.7 64 1.51 35 2.92 70 20.6 76 0.91 61 20.7 72 32.4 75 14.2 64 6.39 19 31.5 97 3.74 10 0.00 1 0.00 1 0.00 1 11.0 65 33.0 84 12.8 61
PWC-Net_ROB [148]44.5 1.18 75 6.99 83 0.63 85 3.25 54 20.9 65 1.41 44 6.19 63 21.0 76 3.34 72 1.51 10 9.97 9 0.54 19 19.2 59 31.5 69 9.61 36 8.57 42 28.0 65 4.96 28 0.00 1 0.00 1 0.02 49 6.91 16 22.1 40 6.52 8
Sparse Occlusion [54]44.7 0.90 27 5.06 21 0.46 51 2.35 24 14.9 26 1.01 27 4.83 48 15.7 50 1.09 24 2.38 45 17.2 54 0.66 38 16.7 42 26.9 42 8.75 30 7.98 33 24.6 38 5.42 35 0.60 104 0.61 130 0.84 71 8.41 45 22.7 42 10.5 26
Classic+NL [31]45.2 0.91 31 5.38 31 0.45 49 3.22 52 20.4 61 1.49 48 3.97 28 13.1 26 1.97 52 2.33 41 15.0 38 0.68 43 14.9 28 24.0 28 10.2 43 9.83 68 23.9 35 6.24 63 0.33 86 0.02 40 1.28 85 7.80 33 21.2 35 11.1 40
MDP-Flow [26]45.5 0.84 17 5.01 19 0.47 52 2.37 25 13.0 11 1.76 62 4.04 29 14.0 35 2.72 69 2.70 58 21.0 77 0.98 66 18.0 47 28.5 47 13.1 60 8.58 43 26.6 54 5.71 40 0.00 1 0.02 40 0.00 1 12.4 81 31.9 74 16.2 85
EPPM w/o HM [88]45.9 1.16 73 5.61 47 0.33 8 2.33 22 15.4 29 0.60 11 4.28 37 14.7 43 0.32 2 2.20 34 14.7 35 0.59 28 14.3 26 23.6 26 5.47 8 12.2 105 29.9 85 7.04 87 2.28 127 0.03 100 6.80 122 6.72 13 19.4 21 8.96 12
OAR-Flow [125]48.5 1.00 51 5.81 56 0.55 69 3.94 81 18.5 47 1.99 74 6.44 69 20.5 68 2.66 68 2.84 67 18.5 62 0.71 52 18.9 55 30.1 57 11.2 48 5.95 15 26.2 50 3.42 9 0.00 1 0.00 1 0.00 1 9.00 49 26.4 57 12.2 57
CostFilter [40]48.9 1.14 69 6.62 74 0.40 27 2.38 26 14.8 24 0.53 6 3.58 18 12.5 20 0.84 16 2.62 55 17.3 55 0.51 17 14.9 28 24.9 35 4.14 7 9.99 77 29.2 80 6.06 57 1.38 120 0.81 135 6.01 121 8.00 38 23.2 46 9.84 22
Complementary OF [21]49.5 0.91 31 5.39 33 0.43 41 2.42 28 15.2 27 0.74 19 4.36 41 15.5 48 1.16 26 2.63 56 19.5 69 0.76 54 22.5 91 33.0 81 20.1 92 9.92 74 28.5 74 4.80 24 0.00 1 0.00 1 0.00 1 12.6 84 35.6 103 16.9 89
S2D-Matching [84]51.3 1.09 64 6.39 71 0.51 58 3.35 59 20.9 65 1.52 49 5.55 57 17.8 56 2.21 57 1.91 19 13.6 19 0.56 22 15.2 33 24.5 33 9.72 39 10.1 79 23.6 32 6.34 69 0.52 97 0.02 40 2.09 104 7.62 30 20.0 28 11.6 52
COFM [59]51.5 1.15 70 6.80 79 0.58 79 2.62 32 15.8 35 1.25 37 5.68 59 18.2 57 2.12 54 2.20 34 13.5 18 0.58 27 19.6 62 31.0 66 15.7 77 9.91 73 23.3 29 6.03 56 0.81 110 0.00 1 1.43 90 7.76 32 20.7 30 10.6 30
IROF-TV [53]52.2 1.10 66 6.24 66 0.57 75 3.29 58 21.5 71 1.72 59 4.40 44 14.2 37 1.87 48 3.04 75 21.7 83 1.11 70 16.2 39 26.0 39 11.3 50 9.60 64 32.4 103 5.72 41 0.00 1 0.02 40 0.00 1 8.00 38 22.4 41 11.2 44
SimpleFlow [49]52.4 0.94 41 5.57 46 0.44 45 3.52 64 21.7 74 1.79 65 5.82 60 17.6 55 2.36 62 2.55 51 16.5 48 0.81 58 16.3 40 26.0 39 11.8 52 10.3 81 23.1 28 6.33 68 0.24 76 0.00 1 0.81 70 8.33 42 22.7 42 11.5 49
2DHMM-SAS [92]53.0 0.91 31 5.42 36 0.41 32 3.67 71 21.9 76 1.52 49 5.62 58 16.1 52 2.28 60 2.44 47 15.9 44 0.72 53 15.0 30 24.2 29 9.48 35 11.1 96 25.1 44 6.36 71 0.38 91 0.02 40 1.67 97 8.04 40 21.7 37 11.7 53
ACK-Prior [27]53.6 0.82 12 4.87 13 0.32 7 2.12 16 13.7 19 0.43 3 3.68 21 12.9 23 0.92 21 1.77 16 14.0 22 0.19 6 19.5 61 28.2 46 16.7 82 12.3 109 29.1 79 7.52 100 2.44 130 0.30 119 8.47 129 13.9 91 30.2 68 18.0 94
ROF-ND [107]54.7 1.27 87 6.15 64 0.38 20 4.71 91 18.9 49 1.07 29 4.89 49 15.6 49 1.21 27 0.65 2 6.22 2 0.29 9 19.7 63 30.5 61 14.5 66 11.5 102 26.5 53 6.25 64 0.39 92 0.02 40 0.84 71 12.3 80 31.5 72 13.8 70
TV-L1-MCT [64]55.7 0.90 27 5.30 28 0.41 32 3.73 73 22.1 77 1.79 65 4.61 47 15.3 46 1.63 41 2.16 31 14.7 35 0.67 41 17.6 45 27.1 43 15.2 73 11.0 93 25.0 42 6.58 77 0.36 89 0.02 40 2.46 108 9.73 55 23.0 44 16.2 85
RFlow [90]57.6 0.91 31 5.43 37 0.47 52 2.46 30 15.6 33 1.13 32 6.42 68 19.3 63 1.66 43 2.77 61 21.4 81 1.16 73 20.7 72 31.7 71 18.0 89 9.69 66 30.4 88 6.14 59 0.01 44 0.02 40 0.15 55 10.9 64 30.0 67 13.1 64
S2F-IF [123]58.7 1.28 89 7.44 90 0.84 98 3.48 63 22.4 80 1.86 69 5.52 55 19.0 60 3.05 71 2.96 72 16.9 52 1.21 75 21.3 80 34.1 90 14.5 66 5.45 6 25.6 46 4.62 16 0.00 1 0.00 1 0.00 1 12.0 75 32.3 78 14.7 74
Occlusion-TV-L1 [63]58.7 0.98 48 5.50 43 0.48 54 3.25 54 19.5 54 1.82 68 7.36 83 21.2 77 2.44 65 2.73 59 20.4 74 0.93 64 20.5 69 32.1 72 15.5 75 8.22 37 28.1 67 6.69 80 0.00 1 0.00 1 0.00 1 13.1 88 33.5 91 15.9 84
DeepFlow2 [108]59.4 1.04 57 5.76 55 0.54 67 3.86 77 19.7 55 2.02 77 6.79 72 20.5 68 3.55 78 3.64 88 22.5 87 1.44 83 18.8 53 30.1 57 12.0 54 7.01 26 27.7 63 4.65 17 0.00 1 0.02 40 0.00 1 12.6 84 32.0 76 16.9 89
DPOF [18]59.7 1.11 67 6.56 73 0.53 62 4.51 89 21.0 67 2.42 87 3.25 13 11.3 14 0.84 16 2.03 26 15.3 40 0.70 49 17.8 46 28.8 48 9.36 33 11.4 101 26.9 55 6.26 66 4.21 137 0.02 40 10.5 133 10.2 58 26.7 58 11.8 54
FlowFields+ [130]61.5 1.31 91 7.52 92 0.92 107 3.61 67 23.0 84 1.98 73 6.08 61 20.6 70 3.39 75 2.82 64 16.4 47 1.23 76 21.4 83 34.3 93 14.1 62 5.45 6 27.5 62 4.68 20 0.00 1 0.02 40 0.00 1 11.3 67 33.1 87 11.4 47
TF+OM [100]62.7 1.11 67 6.49 72 0.69 90 2.94 43 16.8 36 1.78 63 7.92 88 20.7 72 9.65 102 2.85 68 20.5 75 1.05 69 22.0 88 32.2 73 20.3 93 8.74 44 28.3 71 4.67 19 0.00 1 0.02 40 0.00 1 12.1 77 30.5 70 15.8 83
FlowFields [110]63.9 1.32 92 7.63 94 0.93 109 3.61 67 22.9 82 2.00 76 6.11 62 20.6 70 3.58 79 2.85 68 16.6 50 1.24 77 21.9 87 35.0 102 15.1 72 5.70 11 28.0 65 4.72 21 0.00 1 0.02 40 0.00 1 11.7 70 33.4 89 11.5 49
CRTflow [80]64.3 1.02 56 5.69 51 0.58 79 3.12 47 18.1 45 1.46 46 6.89 75 20.9 74 2.40 63 3.38 83 22.2 84 1.42 82 19.7 63 31.3 68 12.3 55 11.0 93 35.9 118 10.1 117 0.00 1 0.00 1 0.00 1 12.0 75 33.6 92 14.7 74
AggregFlow [97]64.5 1.68 107 9.22 112 0.86 101 4.76 92 25.3 98 2.56 90 7.33 82 22.6 85 5.07 94 2.64 57 16.5 48 0.69 47 19.1 58 30.7 63 11.2 48 5.11 4 17.3 5 3.29 7 0.14 66 0.02 40 0.96 77 9.35 53 25.7 51 13.1 64
LiteFlowNet [143]64.9 1.49 96 8.56 103 0.62 84 4.27 85 23.7 91 1.92 71 6.82 73 22.9 87 3.44 76 2.47 49 16.3 46 0.62 33 25.7 108 39.8 120 17.5 86 9.55 60 30.2 87 4.00 11 0.00 1 0.00 1 0.00 1 10.7 61 30.5 70 12.2 57
Steered-L1 [118]65.0 0.63 1 3.72 1 0.42 36 1.53 3 10.4 3 0.75 20 3.84 22 13.2 28 1.32 28 2.80 62 21.1 79 0.98 66 21.2 79 31.2 67 20.3 93 10.7 89 29.3 82 7.45 99 4.27 138 0.34 121 19.6 140 16.5 103 33.3 88 24.6 111
TCOF [69]65.7 1.00 51 5.63 48 0.59 82 3.53 65 21.5 71 1.69 58 7.64 86 22.0 81 3.79 82 2.80 62 19.9 72 0.77 55 21.1 77 32.7 77 13.9 61 7.79 29 20.7 14 5.77 43 0.92 114 0.03 100 3.23 112 8.40 44 23.2 46 11.4 47
ComplOF-FED-GPU [35]66.0 0.85 19 5.04 20 0.42 36 3.90 79 21.4 69 1.78 63 4.90 50 16.8 53 1.41 32 3.18 78 21.1 79 1.03 68 21.6 85 33.8 88 15.4 74 10.8 90 34.7 114 5.93 49 0.12 62 0.02 40 1.43 90 11.9 72 34.2 95 15.3 78
Adaptive [20]67.4 1.05 58 6.01 61 0.48 54 3.27 56 20.1 59 1.79 65 7.11 79 20.1 65 1.62 40 3.29 81 22.4 85 1.15 72 18.8 53 29.8 53 12.6 57 10.6 85 28.4 73 6.72 83 0.57 103 0.71 133 0.96 77 8.64 46 23.1 45 10.9 35
SRR-TVOF-NL [91]68.7 1.15 70 6.13 63 0.60 83 5.04 94 23.3 86 2.68 92 8.17 89 22.9 87 4.22 91 2.76 60 16.9 52 0.68 43 19.8 66 29.0 49 17.7 88 8.07 34 27.0 57 6.17 60 0.16 68 0.02 40 0.86 74 11.8 71 25.9 53 15.3 78
DeepFlow [86]70.1 1.19 77 6.04 62 0.57 75 4.41 86 21.3 68 2.41 86 8.35 92 22.9 87 6.63 99 4.03 99 24.5 96 1.69 93 19.0 57 30.9 64 11.8 52 7.29 27 29.5 84 4.88 26 0.00 1 0.02 40 0.00 1 15.7 102 35.1 101 23.4 107
TV-L1-improved [17]70.2 0.94 41 5.45 38 0.52 60 2.91 41 17.8 41 1.58 55 7.00 77 20.2 67 2.24 59 3.00 73 21.5 82 1.16 73 20.6 70 32.3 74 15.0 70 12.2 105 34.2 111 7.87 104 0.19 71 0.30 119 0.49 65 10.7 61 29.7 66 12.8 61
PGM-C [120]71.3 1.52 99 8.68 105 0.99 115 3.66 69 23.0 84 2.03 78 6.30 66 21.2 77 3.90 84 3.82 94 22.9 91 1.68 92 21.3 80 34.3 93 14.1 62 6.89 25 28.8 76 5.60 38 0.00 1 0.02 40 0.00 1 11.9 72 34.3 96 14.2 73
Aniso. Huber-L1 [22]72.6 1.06 59 5.69 51 0.65 86 5.24 96 25.4 99 3.29 97 8.19 90 21.4 80 4.09 89 3.10 76 21.0 77 0.97 65 18.5 49 29.1 50 12.6 57 9.08 50 27.0 57 5.56 37 0.68 106 0.08 108 2.93 111 9.25 51 24.1 48 11.8 54
DMF_ROB [140]73.8 1.06 59 6.27 67 0.56 71 4.09 82 20.7 64 2.13 82 7.51 84 23.3 91 3.01 70 3.67 89 23.0 92 1.51 85 20.9 75 32.8 79 16.6 81 10.2 80 30.1 86 7.29 95 0.00 1 0.02 40 0.00 1 14.3 98 35.7 105 17.3 93
Classic++ [32]73.8 1.00 51 5.92 59 0.56 71 3.28 57 19.2 50 1.87 70 6.88 74 20.7 72 3.38 74 3.41 85 23.6 94 1.30 78 20.8 74 33.2 84 15.0 70 10.0 78 31.8 99 6.69 80 0.66 105 0.02 40 2.59 109 11.3 67 29.5 63 13.5 68
CPM-Flow [116]73.8 1.53 100 8.72 107 0.98 112 3.74 74 23.5 87 2.08 80 6.22 64 20.9 74 3.88 83 3.78 92 22.5 87 1.64 90 21.3 80 34.4 95 14.2 64 7.87 31 28.8 76 6.40 72 0.00 1 0.02 40 0.00 1 12.5 83 35.6 103 14.9 76
Bartels [41]74.8 1.28 89 7.59 93 0.50 56 2.39 27 15.4 29 1.04 28 5.52 55 19.2 61 2.54 67 2.83 65 19.9 72 1.30 78 22.7 94 34.1 90 20.4 95 9.92 74 30.5 90 6.93 86 1.88 125 0.02 40 12.3 135 12.7 86 31.9 74 16.4 87
CBF [12]75.4 0.85 19 4.89 15 0.43 41 4.99 93 22.3 79 4.63 105 6.60 70 19.2 61 4.08 88 3.61 87 24.5 96 1.49 84 20.0 67 30.9 64 16.2 79 9.67 65 27.4 60 5.64 39 2.65 131 0.37 122 6.97 124 11.5 69 28.4 62 16.9 89
FF++_ROB [146]76.0 1.67 106 9.54 114 0.97 110 3.68 72 22.9 82 2.07 79 6.93 76 22.8 86 3.99 87 3.03 74 17.5 56 1.31 80 22.1 89 35.6 107 14.8 68 6.77 22 25.9 48 4.87 25 0.17 69 0.22 112 0.79 69 10.5 59 30.3 69 13.1 64
EpicFlow [102]76.3 1.51 97 8.63 104 0.98 112 3.76 75 23.5 87 2.11 81 7.14 80 23.6 93 3.97 86 3.79 93 22.6 89 1.64 90 21.5 84 34.4 95 14.8 68 8.97 47 29.2 80 6.53 74 0.00 1 0.02 40 0.00 1 12.4 81 34.5 97 15.2 77
LocallyOriented [52]77.4 1.78 114 9.64 116 0.77 95 6.11 105 28.2 106 3.79 102 10.9 102 28.0 107 5.52 96 3.28 80 19.5 69 1.55 86 22.8 96 33.9 89 17.6 87 9.84 70 24.6 38 6.63 78 0.00 1 0.00 1 0.00 1 11.9 72 29.6 65 15.7 82
CLG-TV [48]78.4 1.01 54 5.46 39 0.50 56 4.16 84 23.5 87 2.40 85 7.52 85 21.2 77 2.51 66 3.33 82 22.8 90 1.14 71 20.9 75 32.4 75 15.6 76 8.94 46 31.7 98 6.35 70 1.27 118 1.18 138 3.55 115 11.1 66 28.2 61 13.5 68
TriangleFlow [30]79.7 1.19 77 6.73 78 0.53 62 3.88 78 21.8 75 1.64 57 6.61 71 20.1 65 1.59 38 2.35 43 19.3 67 0.89 60 25.6 107 37.3 112 23.5 109 13.4 118 30.5 90 8.48 112 0.81 110 0.17 110 1.33 88 10.7 61 28.1 60 13.1 64
Fusion [6]80.1 1.15 70 6.83 80 0.71 92 2.10 15 14.5 22 1.23 36 4.58 46 15.4 47 3.60 80 3.73 91 27.2 107 2.38 102 23.9 100 33.7 86 26.4 114 8.36 39 27.3 59 7.11 90 1.00 115 0.64 132 2.66 110 14.5 99 34.0 94 18.7 96
Rannacher [23]80.5 1.09 64 6.27 67 0.54 67 3.77 76 22.1 77 2.27 83 7.89 87 22.4 83 3.34 72 3.67 89 23.5 93 1.61 88 21.1 77 33.1 82 15.8 78 12.9 114 35.4 117 7.98 105 0.43 96 0.02 40 1.63 95 10.5 59 29.5 63 12.8 61
SIOF [67]80.9 1.24 82 6.63 75 0.51 58 5.26 97 26.2 100 3.22 96 11.5 103 26.1 97 12.3 106 4.49 102 27.4 110 2.29 100 22.8 96 33.3 85 23.4 108 8.56 41 28.8 76 7.15 92 0.00 1 0.02 40 0.00 1 13.6 90 32.1 77 23.6 109
F-TV-L1 [15]82.2 1.22 79 6.63 75 0.53 62 5.86 102 24.8 96 3.51 101 9.25 96 23.4 92 3.44 76 3.91 95 24.9 98 1.61 88 20.3 68 31.5 69 16.2 79 11.3 99 30.9 94 7.40 98 0.15 67 0.47 127 0.17 56 9.88 56 27.6 59 11.1 40
ResPWCR_ROB [145]83.0 1.22 79 7.22 85 0.68 89 5.04 94 24.6 94 2.77 94 9.17 95 26.7 100 6.63 99 3.22 79 22.4 85 1.31 80 22.7 94 35.5 106 18.0 89 10.9 91 32.3 101 7.99 106 0.00 1 0.02 40 0.00 1 14.2 95 37.2 107 16.5 88
Local-TV-L1 [65]83.8 1.57 101 7.45 91 0.67 88 7.93 109 28.0 104 5.97 110 12.9 110 26.6 99 12.2 105 6.04 118 31.1 117 3.55 117 18.7 52 29.9 56 12.9 59 9.33 57 28.1 67 5.97 52 0.00 1 0.02 40 0.00 1 21.0 121 37.7 110 37.5 126
p-harmonic [29]84.1 1.08 62 6.28 70 0.55 69 3.66 69 20.5 63 2.48 89 8.22 91 23.0 90 3.92 85 5.04 106 28.4 113 3.51 115 24.8 104 34.1 90 30.1 119 7.78 28 32.3 101 6.54 75 0.19 71 0.44 126 0.00 1 14.2 95 33.0 84 21.8 103
BriefMatch [124]84.7 0.96 45 5.52 45 0.53 62 3.55 66 18.6 48 1.97 72 4.95 51 16.9 54 1.82 47 2.57 53 19.7 71 0.92 63 21.8 86 32.7 77 20.8 98 16.2 127 33.7 109 13.5 129 3.95 136 0.97 137 15.8 136 17.3 109 34.7 99 25.4 113
OFRF [134]85.5 1.68 107 8.84 109 0.73 93 12.5 121 28.4 108 11.9 122 12.8 109 24.7 94 13.6 108 4.30 101 18.9 65 2.52 103 18.9 55 30.4 60 9.65 37 11.5 102 27.9 64 5.03 30 0.13 64 0.00 1 0.71 68 20.9 120 32.7 83 40.3 129
TriFlow [95]87.0 1.51 97 8.71 106 0.78 96 4.56 90 22.8 81 3.37 99 12.5 107 28.2 108 17.8 111 2.41 46 18.3 60 0.91 61 24.8 104 34.4 95 25.7 112 5.97 16 23.5 31 4.74 22 19.3 144 0.27 117 59.0 144 13.2 89 32.5 80 14.1 72
Dynamic MRF [7]87.9 1.26 85 7.42 88 0.57 75 3.39 61 21.4 69 1.58 55 7.00 77 22.5 84 2.22 58 3.40 84 24.1 95 1.69 93 25.9 113 37.6 113 24.8 111 14.4 122 41.5 128 9.85 116 0.09 59 0.00 1 0.96 77 19.2 116 39.4 116 25.5 114
DF-Auto [115]88.7 1.84 115 8.87 110 0.90 102 8.40 110 30.1 110 6.82 111 13.3 111 27.9 106 19.6 113 5.29 109 26.6 103 3.01 107 22.2 90 32.9 80 21.0 99 5.80 13 23.6 32 5.02 29 0.18 70 0.61 130 0.00 1 14.8 100 32.4 79 19.9 98
LFNet_ROB [151]89.4 1.98 118 11.1 120 0.90 102 5.93 103 28.1 105 3.47 100 10.5 101 32.4 114 6.86 101 3.11 77 19.2 66 1.60 87 30.0 126 44.1 129 28.0 117 9.85 71 35.2 116 7.05 89 0.00 1 0.00 1 0.00 1 14.2 95 39.1 114 17.0 92
Brox et al. [5]91.1 1.22 79 6.66 77 0.70 91 4.15 83 24.3 93 2.39 84 7.21 81 22.1 82 4.18 90 4.91 104 26.3 102 2.65 104 26.2 116 35.7 108 31.4 122 10.5 83 33.4 108 7.34 97 0.01 44 0.13 109 0.00 1 17.1 108 39.1 114 23.0 106
ContFlow_ROB [150]91.7 3.63 129 17.1 133 1.92 131 10.2 113 34.0 116 8.28 114 14.6 114 34.3 120 18.7 112 3.41 85 14.3 25 2.16 96 30.8 128 46.9 135 21.9 103 10.4 82 35.1 115 6.69 80 0.00 1 0.02 40 0.00 1 12.1 77 32.5 80 14.0 71
FlowNet2 [122]92.9 2.63 123 12.9 125 1.14 120 17.9 126 43.1 128 16.1 128 17.0 117 32.9 115 25.3 126 3.92 96 16.7 51 2.16 96 25.8 111 40.2 123 17.0 84 10.6 85 28.2 69 8.09 107 0.02 49 0.00 1 0.20 58 12.2 79 34.5 97 9.71 16
SuperFlow [81]94.1 1.26 85 5.91 58 0.66 87 6.58 107 24.8 96 5.70 109 12.7 108 26.7 100 20.1 114 5.60 113 28.6 114 3.33 112 24.6 103 33.7 86 31.7 125 8.09 35 30.8 93 7.19 93 0.02 49 0.07 106 0.02 49 16.6 104 37.3 108 22.5 104
EPMNet [133]96.5 2.58 122 13.6 126 1.08 117 17.2 125 45.9 130 14.3 124 15.3 116 31.5 113 21.6 117 4.71 103 24.9 98 2.35 101 25.8 111 40.2 123 17.0 84 10.6 85 28.2 69 8.09 107 0.01 44 0.00 1 0.10 53 15.0 101 44.1 125 9.78 20
Second-order prior [8]98.0 1.24 82 6.93 82 0.58 79 5.26 97 27.0 102 3.34 98 9.68 98 26.8 102 5.39 95 4.25 100 26.1 101 2.25 98 22.5 91 34.4 95 19.0 91 12.9 114 41.2 127 8.26 111 1.14 117 0.07 106 2.41 106 12.7 86 32.5 80 18.2 95
AugFNG_ROB [144]100.1 3.78 132 18.3 135 1.78 128 15.9 124 39.3 124 15.3 127 17.3 118 37.8 124 24.2 123 3.99 97 18.6 64 2.27 99 29.6 123 45.3 131 21.5 102 11.1 96 34.5 113 7.60 101 0.00 1 0.00 1 0.00 1 18.5 114 46.2 128 18.8 97
SegOF [10]100.6 1.62 104 9.24 113 1.14 120 14.8 123 38.8 123 14.3 124 17.8 120 33.2 116 22.3 119 6.57 119 27.5 111 4.43 120 32.5 131 41.8 127 43.4 135 14.1 121 38.0 122 10.5 119 0.00 1 0.00 1 0.00 1 14.0 92 33.7 93 12.6 60
StereoOF-V1MT [119]101.7 1.42 95 8.08 99 0.56 71 6.56 106 34.1 117 2.73 93 10.0 100 29.8 110 2.19 55 4.91 104 34.6 122 2.66 105 31.4 130 44.5 130 31.4 122 15.8 126 48.0 134 11.6 124 0.05 57 0.00 1 0.52 66 24.0 124 48.7 132 28.5 117
WOLF_ROB [149]101.9 2.17 119 11.1 120 0.90 102 11.0 115 38.1 122 6.99 112 14.3 112 33.5 117 10.3 103 5.21 108 25.8 100 3.01 107 26.8 119 38.9 118 26.6 115 12.4 110 30.4 88 7.26 94 0.09 59 0.00 1 0.84 71 16.8 106 39.6 118 24.5 110
Shiralkar [42]102.0 1.27 87 7.43 89 0.53 62 5.83 101 30.1 110 2.93 95 9.62 97 26.2 98 3.70 81 5.11 107 30.7 116 3.08 109 25.7 108 39.1 119 22.5 106 17.9 128 45.5 130 9.73 115 1.80 123 0.00 1 8.23 128 18.4 113 44.9 126 19.9 98
FlowNetS+ft+v [112]102.7 1.40 94 7.39 87 0.80 97 5.75 100 23.6 90 4.35 104 11.7 105 27.3 104 12.4 107 5.33 110 27.2 107 3.18 111 25.7 108 35.4 105 26.9 116 8.52 40 32.0 100 6.85 84 2.34 129 1.61 141 10.1 132 14.0 92 34.9 100 20.1 101
CNN-flow-warp+ref [117]104.1 1.63 105 9.14 111 0.91 106 5.41 99 24.0 92 4.66 106 11.6 104 29.8 110 10.7 104 5.59 112 27.1 106 3.43 113 26.6 118 36.0 109 31.5 124 11.3 99 33.1 106 7.62 102 0.03 52 0.25 115 0.07 51 20.4 118 40.5 120 28.3 116
2bit-BM-tele [98]104.5 1.75 110 9.59 115 0.85 99 4.44 87 24.7 95 2.62 91 8.64 93 25.8 96 4.56 92 3.99 97 27.8 112 1.98 95 22.6 93 33.1 82 20.5 96 14.6 123 32.7 105 10.7 120 5.96 141 1.68 142 21.9 142 14.1 94 33.4 89 19.9 98
Ad-TV-NDC [36]104.7 3.59 128 8.26 100 6.67 141 21.3 130 38.0 120 22.4 133 19.7 123 33.6 118 21.8 118 13.5 125 33.9 121 15.0 126 19.4 60 30.6 62 12.5 56 9.58 62 28.6 75 6.54 75 0.21 73 0.37 122 0.17 56 28.1 130 43.2 123 47.4 136
Learning Flow [11]104.8 1.35 93 7.83 96 0.56 71 4.48 88 26.8 101 2.43 88 9.85 99 27.1 103 5.06 93 6.65 120 33.5 120 4.13 118 29.9 125 40.0 122 34.1 129 12.8 112 38.5 124 8.86 114 0.28 81 0.29 118 1.13 80 17.0 107 37.6 109 22.8 105
StereoFlow [44]104.9 7.67 141 21.8 138 3.86 137 51.5 144 74.0 145 46.2 141 43.7 145 63.5 145 36.8 136 51.6 143 79.4 145 47.5 142 26.1 114 38.0 115 21.1 100 5.83 14 26.9 55 4.93 27 0.00 1 0.02 40 0.00 1 20.7 119 38.1 112 29.7 118
LDOF [28]105.3 1.59 103 8.06 97 0.97 110 6.08 104 27.9 103 3.79 102 8.98 94 25.2 95 6.05 97 5.90 116 33.2 119 3.14 110 23.5 98 34.5 99 22.7 107 9.83 68 34.0 110 7.30 96 0.86 112 1.28 139 3.67 116 16.7 105 39.7 119 23.5 108
SPSA-learn [13]105.8 1.77 112 7.72 95 0.90 102 11.0 115 33.2 113 9.40 118 17.3 118 34.2 119 22.7 121 11.0 122 32.2 118 10.9 122 26.1 114 34.9 101 31.8 127 12.8 112 34.2 111 11.9 125 0.00 1 0.03 100 0.00 1 25.5 128 39.4 116 39.6 128
BlockOverlap [61]107.1 1.73 109 8.32 101 1.07 116 8.43 111 28.3 107 7.39 113 14.3 112 29.4 109 16.3 110 6.01 117 26.7 105 4.24 119 20.6 70 29.8 53 20.6 97 12.4 110 29.4 83 8.20 110 3.91 135 0.92 136 16.5 138 19.1 115 31.7 73 36.0 122
Filter Flow [19]108.4 1.97 117 10.2 118 1.14 120 8.79 112 33.9 115 5.66 107 18.8 121 35.7 121 26.2 127 21.9 129 42.4 126 22.0 129 27.9 122 36.8 111 35.0 130 13.2 117 32.6 104 8.11 109 0.05 57 0.02 40 0.37 64 17.5 110 33.0 84 25.2 112
HBpMotionGpu [43]109.0 2.47 121 11.8 122 1.09 118 11.4 118 35.3 118 10.0 120 20.3 126 38.5 126 26.3 128 5.67 114 26.6 103 3.51 115 24.1 101 34.8 100 26.1 113 10.9 91 30.7 92 7.04 87 0.27 80 0.05 104 0.89 76 19.3 117 37.1 106 32.8 120
TVL1_ROB [139]112.2 3.70 130 15.6 129 1.80 129 28.3 135 41.8 127 32.9 137 26.2 132 42.0 128 37.7 139 27.9 133 54.9 134 33.1 135 27.0 120 37.8 114 30.2 120 12.2 105 36.9 119 10.2 118 0.00 1 0.00 1 0.00 1 32.6 136 48.2 131 49.8 138
GraphCuts [14]112.3 1.57 101 8.32 101 0.92 107 12.3 120 39.3 124 8.40 115 15.2 115 31.3 112 23.1 122 5.40 111 28.8 115 2.88 106 25.4 106 38.0 115 21.1 100 24.5 138 31.1 95 14.4 131 1.86 124 0.02 40 7.91 127 23.9 123 41.6 122 37.4 125
IAOF [50]113.0 1.77 112 8.80 108 0.98 112 11.2 117 32.5 112 9.32 117 19.8 124 35.7 121 20.2 115 17.5 127 37.6 123 19.8 127 23.7 99 35.0 102 22.3 105 18.1 131 40.2 125 10.9 121 0.56 100 0.02 40 2.17 105 24.8 126 37.8 111 43.9 131
UnFlow [129]113.4 7.34 138 24.6 143 3.32 134 21.7 131 50.1 133 19.1 129 26.8 134 53.1 140 25.0 124 13.7 126 42.5 127 12.5 125 42.2 139 53.7 140 45.6 138 15.1 125 46.2 131 12.1 126 0.00 1 0.00 1 0.00 1 17.5 110 43.7 124 21.5 102
IAOF2 [51]114.7 1.85 116 9.64 116 1.13 119 7.56 108 29.4 109 5.66 107 12.2 106 27.5 105 15.7 109 32.6 136 43.3 129 38.7 139 24.3 102 35.0 102 23.9 110 17.9 128 33.1 106 13.0 127 1.11 116 0.25 115 4.83 119 17.8 112 35.5 102 25.9 115
Black & Anandan [4]116.1 1.75 110 8.07 98 0.73 93 11.6 119 36.6 119 8.94 116 18.9 122 36.4 123 20.3 116 12.4 124 40.5 125 12.0 124 26.3 117 36.2 110 30.5 121 13.4 118 37.3 120 11.0 122 0.75 108 0.42 125 1.90 102 21.4 122 38.6 113 32.5 119
Nguyen [33]118.8 2.73 124 11.0 119 1.16 124 33.4 138 38.0 120 43.1 140 24.6 130 41.9 127 32.1 133 28.7 134 46.5 130 32.2 134 29.8 124 39.8 120 35.5 131 13.9 120 40.4 126 13.0 127 0.03 52 0.02 40 0.20 58 31.6 131 46.3 129 50.5 139
Modified CLG [34]119.6 2.46 120 12.2 123 1.37 125 10.5 114 33.6 114 9.99 119 20.2 125 37.9 125 27.9 130 9.52 121 38.0 124 7.95 121 27.6 121 38.6 117 31.7 125 11.2 98 37.6 121 8.53 113 0.70 107 0.24 114 3.33 114 24.7 125 45.8 127 38.5 127
2D-CLG [1]121.5 6.98 137 23.0 140 3.54 135 20.1 129 40.7 126 21.4 131 26.6 133 44.0 129 36.7 134 34.7 137 55.1 135 39.7 140 31.1 129 41.5 126 38.2 132 15.0 124 42.0 129 13.6 130 0.02 49 0.02 40 0.12 54 31.7 132 51.0 134 44.9 132
GroupFlow [9]124.2 3.39 126 16.8 132 1.37 125 23.0 132 51.6 135 21.5 132 20.7 127 45.1 132 22.3 119 5.67 114 27.3 109 3.50 114 34.6 133 51.5 138 22.0 104 22.4 135 47.9 133 25.4 139 0.55 99 0.47 127 1.70 98 25.2 127 47.9 130 33.5 121
SILK [79]124.3 3.45 127 15.8 130 2.61 132 19.0 127 44.9 129 19.5 130 23.5 129 44.1 130 26.6 129 12.0 123 42.7 128 11.1 123 35.3 134 46.3 134 44.8 136 18.0 130 49.4 135 14.5 132 1.53 121 0.00 1 5.00 120 32.1 135 50.8 133 47.1 135
Horn & Schunck [3]126.5 3.02 125 12.7 124 1.15 123 14.5 122 45.9 130 11.1 121 22.6 128 44.4 131 25.2 125 21.6 128 47.3 131 22.5 130 34.0 132 43.8 128 43.1 134 19.6 132 51.5 137 18.6 135 0.56 100 0.22 112 1.77 99 34.9 138 55.9 138 46.4 134
Heeger++ [104]127.9 3.74 131 16.1 131 1.49 127 23.6 133 64.4 144 14.1 123 36.0 141 49.4 138 37.3 138 38.6 141 67.3 141 38.6 138 46.7 142 58.2 143 50.9 141 36.6 143 68.1 145 34.5 143 0.41 94 0.00 1 1.87 100 31.8 133 51.3 135 37.0 123
TI-DOFE [24]128.5 7.50 139 18.0 134 10.6 142 41.8 142 54.1 138 49.7 142 31.9 138 54.7 143 39.7 141 41.8 142 61.8 138 48.6 143 35.5 136 45.7 133 45.0 137 21.9 134 52.6 138 21.7 137 0.25 77 0.00 1 1.31 87 43.7 141 61.4 141 58.6 141
FFV1MT [106]130.9 4.51 134 19.1 136 2.74 133 19.4 128 58.6 142 14.7 126 40.8 143 53.4 142 50.0 144 38.5 140 73.8 144 37.7 136 46.4 141 56.0 142 56.7 144 33.1 141 66.2 143 31.1 141 0.75 108 0.02 40 2.04 103 31.8 133 51.3 135 37.0 123
H+S_ROB [138]131.0 9.19 145 27.8 149 4.80 140 31.3 137 62.4 143 29.2 135 34.2 140 55.9 144 37.2 137 53.5 145 70.4 143 59.5 144 47.3 143 54.7 141 66.6 145 34.7 142 64.3 142 38.0 144 0.03 52 0.02 40 0.30 61 57.6 145 67.9 144 63.1 144
Periodicity [78]132.5 6.73 136 29.6 150 3.88 138 24.0 134 52.2 136 25.5 134 36.6 142 47.1 135 40.1 142 23.0 130 60.3 137 20.8 128 53.1 145 69.7 145 49.1 140 36.9 144 67.0 144 33.4 142 0.54 98 0.02 40 7.78 126 34.7 137 64.9 143 46.1 133
Adaptive flow [45]132.7 4.48 133 15.3 128 1.90 130 37.1 140 47.9 132 40.5 138 28.1 135 45.1 132 37.9 140 23.3 131 53.8 133 24.8 131 30.1 127 41.4 125 28.5 118 22.6 136 46.3 132 15.6 133 17.3 143 5.51 144 58.1 143 26.0 129 41.5 121 40.5 130
SLK [47]133.9 8.22 144 24.0 142 12.3 143 41.4 141 57.7 141 50.8 143 29.7 137 53.3 141 36.7 134 52.4 144 57.7 136 61.8 145 42.6 140 52.1 139 54.9 142 23.9 137 54.4 140 24.4 138 3.11 134 0.00 1 7.07 125 45.8 143 61.9 142 61.9 142
PGAM+LK [55]137.4 7.83 142 22.3 139 13.7 144 29.1 136 54.2 139 31.3 136 25.6 131 48.1 137 29.9 132 29.7 135 68.4 142 28.3 133 38.2 137 50.8 137 43.0 133 25.1 139 56.4 141 21.4 136 6.54 142 0.57 129 19.1 139 38.5 139 60.8 140 51.7 140
FOLKI [16]137.9 5.65 135 23.4 141 4.60 139 35.1 139 52.9 137 42.6 139 28.3 136 52.7 139 29.6 131 24.1 132 53.7 132 27.7 132 38.9 138 49.3 136 47.8 139 25.3 140 54.3 139 27.7 140 5.73 140 1.38 140 20.1 141 43.9 142 60.5 139 62.2 143
HCIC-L [99]138.2 8.04 143 19.9 137 3.64 136 56.4 145 56.0 140 70.0 145 40.9 144 45.5 134 62.3 145 38.3 139 62.5 139 38.2 137 35.3 134 45.3 131 32.0 128 20.7 133 38.1 123 18.5 134 26.5 145 13.0 145 59.2 145 40.6 140 51.8 137 48.7 137
Pyramid LK [2]140.8 7.59 140 14.5 127 15.4 145 47.0 143 50.5 134 58.8 144 32.1 139 47.7 136 42.4 143 36.1 138 62.9 140 41.1 141 48.9 144 61.1 144 55.0 143 41.7 145 50.3 136 40.3 145 4.64 139 2.07 143 16.3 137 56.9 144 71.9 145 77.2 145
AdaConv-v1 [126]146.2 25.9 146 27.4 144 29.8 146 96.8 146 97.6 146 95.4 146 93.0 146 90.8 146 99.0 146 88.2 146 85.6 146 91.5 146 97.0 146 98.5 147 88.6 146 86.2 146 81.3 146 83.9 146 64.9 147 56.4 147 97.3 147 100.0 147 99.9 147 99.9 147
SepConv-v1 [127]146.2 25.9 146 27.4 144 29.8 146 96.8 146 97.6 146 95.4 146 93.0 146 90.8 146 99.0 146 88.2 146 85.6 146 91.5 146 97.0 146 98.5 147 88.6 146 86.2 146 81.3 146 83.9 146 64.9 147 56.4 147 97.3 147 100.0 147 99.9 147 99.9 147
SuperSlomo [132]146.2 25.9 146 27.4 144 29.8 146 96.8 146 97.6 146 95.4 146 93.0 146 90.8 146 99.0 146 88.2 146 85.6 146 91.5 146 97.0 146 98.5 147 88.6 146 86.2 146 81.3 146 83.9 146 64.9 147 56.4 147 97.3 147 100.0 147 99.9 147 99.9 147
FGIK [136]146.2 25.9 146 27.4 144 29.8 146 96.8 146 97.6 146 95.4 146 93.0 146 90.8 146 99.0 146 88.2 146 85.6 146 91.5 146 97.0 146 98.5 147 88.6 146 86.2 146 81.3 146 83.9 146 64.9 147 56.4 147 97.3 147 100.0 147 99.9 147 99.9 147
CtxSyn [137]146.2 25.9 146 27.4 144 29.8 146 96.8 146 97.6 146 95.4 146 93.0 146 90.8 146 99.0 146 88.2 146 85.6 146 91.5 146 97.0 146 98.5 147 88.6 146 86.2 146 81.3 146 83.9 146 64.9 147 56.4 147 97.3 147 100.0 147 99.9 147 99.9 147
AVG_FLOW_ROB [142]149.3 73.2 151 62.5 151 69.7 151 98.2 151 97.8 151 97.4 151 99.9 151 99.9 151 99.8 151 92.1 151 87.3 151 92.8 151 98.1 151 97.7 146 97.7 151 87.7 151 86.5 151 83.9 146 58.7 146 25.5 146 95.7 146 98.8 146 99.4 146 99.7 146
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] ContFlow_ROB 0.45 all color Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
* 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.