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]7.8 0.82 12 4.87 13 0.37 19 1.75 7 12.1 8 0.53 6 2.22 2 7.90 2 0.57 9 1.07 6 9.10 8 0.17 4 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 25 3.94 2
OFLAF [77]9.6 0.82 12 4.86 12 0.38 21 1.74 5 11.1 5 0.62 13 2.08 1 7.42 1 0.57 9 1.61 14 12.0 14 0.48 15 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 21
PMMST [114]10.0 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 16 1.29 8 6.70 4 0.42 13 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]12.9 0.89 25 5.29 27 0.40 28 2.06 13 14.1 21 0.62 13 2.49 4 8.79 5 0.68 12 0.99 4 8.66 7 0.09 3 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 26 2.84 1
MDP-Flow2 [68]14.4 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 21 2.48 51 17.7 58 0.70 50 14.1 23 23.0 22 8.20 27 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 12
Correlation Flow [75]18.2 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 7 8.36 6 0.28 9 16.6 42 26.1 42 10.8 48 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]18.4 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 33 2.23 37 14.4 28 0.55 22 13.1 14 21.6 14 7.54 20 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 27
NNF-EAC [103]25.0 0.81 9 4.82 11 0.39 26 1.95 9 12.0 7 0.83 24 3.16 11 10.6 11 1.00 23 2.60 55 18.5 63 0.77 56 13.9 20 22.8 21 7.86 22 6.67 21 19.3 9 5.14 31 0.10 62 0.02 40 0.00 1 7.08 21 19.2 19 10.5 28
ComponentFusion [96]25.9 0.98 48 5.81 56 0.37 19 1.59 4 10.7 4 0.53 6 2.84 9 9.86 9 0.85 19 1.94 21 13.3 17 0.54 20 15.3 36 24.9 36 10.5 47 6.83 24 26.2 51 5.50 36 0.03 52 0.00 1 0.32 64 6.69 12 18.5 14 9.59 17
TC/T-Flow [76]27.1 0.71 3 4.20 3 0.40 28 2.67 33 15.4 29 0.77 22 3.30 14 11.2 12 0.44 4 2.33 42 15.9 44 0.60 31 14.8 28 23.6 27 8.02 23 3.70 1 15.8 3 2.27 1 0.13 65 0.02 40 1.23 86 7.85 36 21.7 38 10.9 37
Layers++ [37]27.2 0.91 31 5.39 33 0.43 42 2.18 17 13.9 20 0.96 26 2.73 7 9.43 7 1.40 32 1.70 16 10.5 11 0.56 23 10.2 3 16.8 2 6.50 14 9.09 51 22.7 24 5.92 49 0.21 75 0.02 40 0.69 68 6.88 14 17.6 11 10.9 37
AGIF+OF [85]27.8 0.90 27 5.34 29 0.42 37 3.13 48 19.3 51 1.37 42 3.87 24 12.8 21 1.80 47 2.19 34 14.3 26 0.64 37 12.4 9 20.6 9 7.20 17 9.27 57 22.4 21 5.97 53 0.00 1 0.00 1 0.00 1 7.26 24 18.8 16 10.7 34
FC-2Layers-FF [74]28.0 0.87 22 5.16 23 0.42 37 2.70 35 17.8 41 1.20 33 2.59 5 8.73 4 1.39 31 1.88 19 13.3 17 0.50 16 11.1 5 18.0 5 6.07 11 9.16 55 21.3 17 5.89 47 0.04 57 0.02 40 0.22 60 7.48 28 19.4 22 11.1 42
IIOF-NLDP [131]29.3 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 4 7.36 5 0.24 8 15.0 31 24.3 31 6.98 15 9.70 68 24.0 37 6.32 68 0.01 44 0.02 40 0.00 1 7.22 23 19.9 28 7.14 9
LME [70]30.7 0.95 44 5.67 49 0.38 21 1.45 1 9.68 2 0.43 3 5.19 53 13.3 29 6.57 99 2.44 48 18.3 61 0.68 44 15.2 34 24.4 32 10.2 44 6.17 17 21.9 18 5.18 32 0.00 1 0.02 40 0.00 1 7.05 18 19.3 20 10.2 25
ALD-Flow [66]31.9 0.79 7 4.72 9 0.38 21 2.44 29 13.5 16 0.80 23 4.33 39 14.7 43 0.88 20 2.92 71 19.4 69 0.82 60 17.5 45 28.1 46 10.0 42 5.61 10 24.7 42 3.10 4 0.00 1 0.00 1 0.00 1 9.09 51 26.3 57 11.9 58
nLayers [57]32.4 0.88 23 5.25 25 0.44 46 2.79 37 15.6 33 1.47 48 4.34 40 14.4 39 2.33 62 1.54 12 11.6 13 0.52 19 10.4 4 17.1 4 5.51 9 8.89 45 19.3 9 5.79 45 0.31 86 0.00 1 1.16 84 7.27 25 19.3 20 11.3 48
MLDP_OF [89]33.3 0.94 41 5.51 44 0.36 17 1.74 5 11.7 6 0.44 5 4.05 30 13.1 26 0.50 7 1.48 10 12.3 15 0.29 10 15.4 37 24.7 35 9.15 32 5.54 9 18.2 7 3.11 5 1.54 124 0.05 106 9.31 132 8.33 43 21.4 37 9.39 16
PH-Flow [101]34.1 0.93 39 5.49 41 0.42 37 2.87 39 17.6 40 1.33 41 2.99 10 10.1 10 1.76 46 2.27 39 14.6 33 0.68 44 12.5 10 20.8 11 6.28 12 7.79 29 20.9 15 5.39 33 0.39 94 0.02 40 1.63 97 6.88 14 19.0 18 10.3 26
3DFlow [135]34.2 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 17 22.2 18 7.25 18 12.2 107 27.4 61 7.12 93 2.77 135 0.02 40 10.0 133 5.36 3 15.8 4 4.88 4
HAST [109]34.5 0.92 37 5.41 35 0.35 14 3.21 51 13.6 18 1.99 75 2.45 3 8.47 3 0.29 1 2.24 38 14.5 31 0.40 12 11.7 7 19.4 8 3.63 3 11.0 93 24.2 38 6.87 86 2.75 134 0.00 1 11.6 136 4.05 1 13.1 1 4.43 3
RNLOD-Flow [121]34.7 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 37 2.01 24 14.3 26 0.60 31 14.2 25 23.1 24 8.72 30 8.21 36 19.9 12 5.90 48 0.35 90 0.03 102 1.48 95 6.51 11 17.2 8 9.80 23
ProbFlowFields [128]36.4 1.16 74 6.86 82 0.85 100 2.32 21 14.6 23 1.45 46 4.28 37 14.9 45 2.43 65 1.56 13 9.89 9 0.50 16 18.1 49 29.1 51 11.5 52 4.44 2 20.6 13 4.20 13 0.00 1 0.02 40 0.00 1 8.97 49 25.7 52 9.75 19
IROF++ [58]36.7 0.96 45 5.70 54 0.44 46 3.00 45 19.4 52 1.37 42 3.90 26 12.8 21 1.96 52 2.36 45 15.8 43 0.69 48 14.1 23 23.0 22 8.22 28 9.14 54 25.0 43 6.07 59 0.00 1 0.02 40 0.00 1 7.35 26 20.3 30 10.8 35
Efficient-NL [60]37.8 0.93 39 5.47 40 0.39 26 2.76 36 18.0 44 1.11 31 4.12 34 13.3 29 1.15 26 2.15 31 14.1 24 0.66 39 13.0 13 21.3 13 7.16 16 10.6 85 23.4 31 6.41 74 0.26 80 0.02 40 1.13 82 7.35 26 17.4 10 10.9 37
TC-Flow [46]38.0 0.75 5 4.45 5 0.38 21 2.04 12 12.6 10 0.70 17 4.23 36 14.4 39 0.77 14 2.56 53 17.5 56 0.63 35 17.1 44 27.8 45 9.45 35 5.73 12 25.6 47 3.12 6 0.22 77 0.02 40 2.41 108 10.1 59 25.9 54 15.4 81
SVFilterOh [111]38.0 1.07 61 6.27 67 0.44 46 2.07 14 13.1 13 0.72 18 3.24 12 11.2 12 1.05 24 1.99 23 13.8 21 0.56 23 12.6 12 21.1 12 3.80 4 10.5 83 22.4 21 5.97 53 2.31 130 0.39 126 6.95 125 4.87 2 14.8 2 6.01 7
Classic+CPF [83]38.6 0.89 25 5.26 26 0.41 33 3.03 46 19.4 52 1.27 38 4.14 35 13.6 32 1.64 43 2.12 30 14.4 28 0.64 37 13.6 17 22.2 18 7.82 21 9.85 72 22.6 23 6.18 62 0.36 91 0.02 40 1.50 96 7.07 19 18.5 14 10.5 28
FESL [72]38.8 0.83 15 4.91 16 0.36 17 3.90 80 21.6 74 1.75 62 4.06 31 13.4 31 1.61 40 2.02 26 14.1 24 0.56 23 13.3 15 21.7 15 8.08 25 9.19 56 22.0 19 6.25 65 0.34 89 0.02 40 1.16 84 7.51 29 18.3 13 11.0 41
WRT [151]39.9 1.11 67 6.61 74 0.35 14 3.70 73 21.1 68 1.28 39 7.27 82 19.2 61 0.68 12 0.35 2 3.88 2 0.01 1 13.5 16 22.1 16 7.40 19 11.2 99 22.9 27 6.52 75 0.03 52 0.02 40 0.25 61 7.71 31 18.8 16 7.93 11
FMOF [94]40.0 0.83 15 4.92 17 0.43 42 3.35 59 20.0 57 1.57 55 3.37 16 11.4 15 1.46 35 1.98 22 13.8 21 0.56 23 14.2 25 23.2 25 8.08 25 9.98 77 22.7 24 6.19 63 0.42 97 0.02 40 1.87 102 8.11 42 21.0 34 10.5 28
HBM-GC [105]41.0 1.24 83 7.38 87 0.52 61 2.50 31 15.5 32 1.40 44 4.06 31 14.1 36 1.32 29 1.77 17 13.2 16 0.61 33 13.7 19 22.1 16 8.06 24 8.98 48 16.5 4 4.42 14 1.30 121 0.02 40 3.28 115 7.20 22 19.8 27 10.8 35
Sparse-NonSparse [56]41.6 0.88 23 5.21 24 0.40 28 3.16 50 19.8 56 1.53 53 3.90 26 12.9 23 2.00 54 2.18 33 15.2 39 0.66 39 15.6 38 25.4 39 10.1 43 9.38 59 23.7 35 5.97 53 0.31 86 0.00 1 1.28 87 7.74 32 20.9 32 11.2 46
Aniso-Texture [82]41.6 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 38 1.35 9 11.4 12 0.18 6 19.7 64 29.7 53 16.8 85 9.10 52 26.1 50 5.78 44 0.26 80 0.18 113 0.07 51 9.32 53 24.3 50 12.2 59
Ramp [62]41.7 0.90 27 5.36 30 0.41 33 3.14 49 20.0 57 1.52 50 3.86 23 12.9 23 1.93 50 2.01 24 14.5 31 0.59 29 15.1 33 24.4 32 9.67 39 9.44 60 22.9 27 5.95 51 0.29 84 0.02 40 1.38 91 7.83 35 20.9 32 11.5 51
PMF [73]41.9 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 40 14.4 28 0.44 14 14.0 22 23.3 26 3.86 5 9.55 61 28.3 72 6.63 80 0.89 115 0.79 136 3.74 119 5.66 6 15.8 4 8.92 13
ProFlow_ROB [147]42.1 1.18 76 7.01 85 0.57 76 2.87 39 17.8 41 1.32 40 5.44 54 18.3 59 1.71 45 2.83 66 17.9 59 0.70 50 18.5 50 30.3 60 9.32 33 6.29 18 25.3 46 3.36 8 0.00 1 0.00 1 0.00 1 7.96 37 24.6 51 8.97 15
JOF [141]42.2 0.98 48 5.69 51 0.45 50 3.43 62 20.4 61 1.74 61 3.59 19 11.7 17 2.20 57 2.30 41 15.3 40 0.67 42 12.5 10 20.7 10 6.41 13 8.98 48 22.2 20 5.76 42 1.88 127 0.00 1 4.61 120 7.07 19 19.4 22 10.6 32
CombBMOF [113]43.1 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 15 2.08 28 15.3 40 0.77 56 13.9 20 22.3 20 8.24 29 13.0 118 26.2 51 11.4 125 0.56 102 0.02 40 0.86 75 8.93 48 21.1 35 15.6 82
NL-TV-NCC [25]43.7 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 15 14.6 33 0.17 4 18.6 52 29.8 54 9.76 41 11.8 106 31.2 97 7.70 105 0.12 63 0.00 1 0.30 62 9.40 55 26.0 56 9.75 19
LSM [39]44.2 0.86 21 5.13 22 0.40 28 3.22 52 20.3 60 1.54 54 4.08 33 13.6 32 1.93 50 2.09 29 14.9 37 0.63 35 15.6 38 25.3 38 10.2 44 9.58 63 24.6 39 5.95 51 0.30 85 0.02 40 1.43 92 7.97 38 21.7 38 11.1 42
OFH [38]44.8 0.81 9 4.70 8 0.31 5 2.96 44 17.3 38 1.20 33 6.37 67 19.7 65 1.51 36 2.92 71 20.6 77 0.91 62 20.7 73 32.4 76 14.2 65 6.39 19 31.5 99 3.74 10 0.00 1 0.00 1 0.00 1 11.0 67 33.0 85 12.8 63
PWC-Net_ROB [148]45.1 1.18 76 6.99 84 0.63 86 3.25 54 20.9 65 1.41 45 6.19 63 21.0 77 3.34 73 1.51 11 9.97 10 0.54 20 19.2 60 31.5 70 9.61 37 8.57 42 28.0 66 4.96 28 0.00 1 0.00 1 0.02 49 6.91 16 22.1 41 6.52 8
Sparse Occlusion [54]45.4 0.90 27 5.06 21 0.46 52 2.35 24 14.9 26 1.01 27 4.83 48 15.7 50 1.09 25 2.38 46 17.2 54 0.66 39 16.7 43 26.9 43 8.75 31 7.98 33 24.6 39 5.42 35 0.60 106 0.61 132 0.84 72 8.41 46 22.7 43 10.5 28
Classic+NL [31]46.0 0.91 31 5.38 31 0.45 50 3.22 52 20.4 61 1.49 49 3.97 28 13.1 26 1.97 53 2.33 42 15.0 38 0.68 44 14.9 29 24.0 29 10.2 44 9.83 69 23.9 36 6.24 64 0.33 88 0.02 40 1.28 87 7.80 34 21.2 36 11.1 42
MDP-Flow [26]46.1 0.84 17 5.01 19 0.47 53 2.37 25 13.0 11 1.76 63 4.04 29 14.0 35 2.72 70 2.70 59 21.0 78 0.98 67 18.0 48 28.5 48 13.1 61 8.58 43 26.6 55 5.71 40 0.00 1 0.02 40 0.00 1 12.4 82 31.9 76 16.2 86
EPPM w/o HM [88]46.7 1.16 74 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 35 14.7 35 0.59 29 14.3 27 23.6 27 5.47 8 12.2 107 29.9 86 7.04 89 2.28 129 0.03 102 6.80 124 6.72 13 19.4 22 8.96 14
OAR-Flow [125]49.2 1.00 51 5.81 56 0.55 70 3.94 82 18.5 47 1.99 75 6.44 69 20.5 69 2.66 69 2.84 68 18.5 63 0.71 53 18.9 56 30.1 58 11.2 49 5.95 15 26.2 51 3.42 9 0.00 1 0.00 1 0.00 1 9.00 50 26.4 58 12.2 59
CostFilter [40]49.8 1.14 70 6.62 75 0.40 28 2.38 26 14.8 24 0.53 6 3.58 18 12.5 20 0.84 17 2.62 56 17.3 55 0.51 18 14.9 29 24.9 36 4.14 7 9.99 78 29.2 81 6.06 58 1.38 122 0.81 137 6.01 123 8.00 39 23.2 47 9.84 24
Complementary OF [21]50.1 0.91 31 5.39 33 0.43 42 2.42 28 15.2 27 0.74 19 4.36 41 15.5 48 1.16 27 2.63 57 19.5 70 0.76 55 22.5 92 33.0 82 20.1 94 9.92 75 28.5 75 4.80 24 0.00 1 0.00 1 0.00 1 12.6 85 35.6 104 16.9 90
S2D-Matching [84]52.1 1.09 64 6.39 71 0.51 59 3.35 59 20.9 65 1.52 50 5.55 57 17.8 56 2.21 58 1.91 20 13.6 20 0.56 23 15.2 34 24.5 34 9.72 40 10.1 80 23.6 33 6.34 70 0.52 99 0.02 40 2.09 106 7.62 30 20.0 29 11.6 54
COFM [59]52.4 1.15 71 6.80 80 0.58 80 2.62 32 15.8 35 1.25 37 5.68 59 18.2 57 2.12 55 2.20 35 13.5 19 0.58 28 19.6 63 31.0 67 15.7 78 9.91 74 23.3 30 6.03 57 0.81 112 0.00 1 1.43 92 7.76 33 20.7 31 10.6 32
IROF-TV [53]52.9 1.10 66 6.24 66 0.57 76 3.29 58 21.5 72 1.72 60 4.40 44 14.2 37 1.87 49 3.04 76 21.7 84 1.11 71 16.2 40 26.0 40 11.3 51 9.60 65 32.4 105 5.72 41 0.00 1 0.02 40 0.00 1 8.00 39 22.4 42 11.2 46
SimpleFlow [49]53.2 0.94 41 5.57 46 0.44 46 3.52 64 21.7 75 1.79 66 5.82 60 17.6 55 2.36 63 2.55 52 16.5 48 0.81 59 16.3 41 26.0 40 11.8 53 10.3 82 23.1 29 6.33 69 0.24 78 0.00 1 0.81 71 8.33 43 22.7 43 11.5 51
2DHMM-SAS [92]53.8 0.91 31 5.42 36 0.41 33 3.67 71 21.9 77 1.52 50 5.62 58 16.1 52 2.28 61 2.44 48 15.9 44 0.72 54 15.0 31 24.2 30 9.48 36 11.1 96 25.1 45 6.36 72 0.38 93 0.02 40 1.67 99 8.04 41 21.7 38 11.7 55
ACK-Prior [27]54.6 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 22 1.77 17 14.0 23 0.19 7 19.5 62 28.2 47 16.7 84 12.3 111 29.1 80 7.52 102 2.44 132 0.30 121 8.47 131 13.9 92 30.2 70 18.0 95
ROF-ND [107]55.6 1.27 88 6.15 64 0.38 21 4.71 92 18.9 49 1.07 29 4.89 49 15.6 49 1.21 28 0.65 3 6.22 3 0.29 10 19.7 64 30.5 62 14.5 67 11.5 104 26.5 54 6.25 65 0.39 94 0.02 40 0.84 72 12.3 81 31.5 74 13.8 72
TV-L1-MCT [64]56.6 0.90 27 5.30 28 0.41 33 3.73 74 22.1 78 1.79 66 4.61 47 15.3 46 1.63 42 2.16 32 14.7 35 0.67 42 17.6 46 27.1 44 15.2 74 11.0 93 25.0 43 6.58 79 0.36 91 0.02 40 2.46 110 9.73 57 23.0 45 16.2 86
RFlow [90]58.4 0.91 31 5.43 37 0.47 53 2.46 30 15.6 33 1.13 32 6.42 68 19.3 64 1.66 44 2.77 62 21.4 82 1.16 74 20.7 73 31.7 72 18.0 91 9.69 67 30.4 89 6.14 60 0.01 44 0.02 40 0.15 55 10.9 66 30.0 69 13.1 66
S2F-IF [123]59.4 1.28 90 7.44 91 0.84 99 3.48 63 22.4 81 1.86 70 5.52 55 19.0 60 3.05 72 2.96 73 16.9 52 1.21 76 21.3 81 34.1 91 14.5 67 5.45 6 25.6 47 4.62 16 0.00 1 0.00 1 0.00 1 12.0 77 32.3 80 14.7 75
Occlusion-TV-L1 [63]59.4 0.98 48 5.50 43 0.48 55 3.25 54 19.5 54 1.82 69 7.36 84 21.2 78 2.44 66 2.73 60 20.4 75 0.93 65 20.5 70 32.1 73 15.5 76 8.22 37 28.1 68 6.69 82 0.00 1 0.00 1 0.00 1 13.1 89 33.5 92 15.9 85
DeepFlow2 [108]60.0 1.04 57 5.76 55 0.54 68 3.86 78 19.7 55 2.02 78 6.79 72 20.5 69 3.55 79 3.64 89 22.5 88 1.44 84 18.8 54 30.1 58 12.0 55 7.01 26 27.7 64 4.65 17 0.00 1 0.02 40 0.00 1 12.6 85 32.0 78 16.9 90
DPOF [18]60.6 1.11 67 6.56 73 0.53 63 4.51 90 21.0 67 2.42 88 3.25 13 11.3 14 0.84 17 2.03 27 15.3 40 0.70 50 17.8 47 28.8 49 9.36 34 11.4 103 26.9 56 6.26 67 4.21 139 0.02 40 10.5 135 10.2 60 26.7 59 11.8 56
FlowFields+ [130]62.3 1.31 92 7.52 93 0.92 109 3.61 67 23.0 85 1.98 74 6.08 61 20.6 71 3.39 76 2.82 65 16.4 47 1.23 77 21.4 84 34.3 94 14.1 63 5.45 6 27.5 63 4.68 20 0.00 1 0.02 40 0.00 1 11.3 69 33.1 88 11.4 49
TF+OM [100]63.5 1.11 67 6.49 72 0.69 91 2.94 43 16.8 36 1.78 64 7.92 89 20.7 73 9.65 104 2.85 69 20.5 76 1.05 70 22.0 89 32.2 74 20.3 95 8.74 44 28.3 72 4.67 19 0.00 1 0.02 40 0.00 1 12.1 79 30.5 72 15.8 84
FlowFields [110]64.7 1.32 93 7.63 95 0.93 111 3.61 67 22.9 83 2.00 77 6.11 62 20.6 71 3.58 80 2.85 69 16.6 50 1.24 78 21.9 88 35.0 103 15.1 73 5.70 11 28.0 66 4.72 21 0.00 1 0.02 40 0.00 1 11.7 72 33.4 90 11.5 51
CRTflow [80]65.0 1.02 56 5.69 51 0.58 80 3.12 47 18.1 45 1.46 47 6.89 75 20.9 75 2.40 64 3.38 84 22.2 85 1.42 83 19.7 64 31.3 69 12.3 56 11.0 93 35.9 120 10.1 119 0.00 1 0.00 1 0.00 1 12.0 77 33.6 93 14.7 75
AggregFlow [97]65.4 1.68 108 9.22 113 0.86 102 4.76 93 25.3 99 2.56 91 7.33 83 22.6 86 5.07 95 2.64 58 16.5 48 0.69 48 19.1 59 30.7 64 11.2 49 5.11 4 17.3 5 3.29 7 0.14 67 0.02 40 0.96 78 9.35 54 25.7 52 13.1 66
LiteFlowNet [143]65.8 1.49 97 8.56 104 0.62 85 4.27 86 23.7 92 1.92 72 6.82 73 22.9 88 3.44 77 2.47 50 16.3 46 0.62 34 25.7 109 39.8 121 17.5 88 9.55 61 30.2 88 4.00 11 0.00 1 0.00 1 0.00 1 10.7 63 30.5 72 12.2 59
Steered-L1 [118]65.9 0.63 1 3.72 1 0.42 37 1.53 3 10.4 3 0.75 20 3.84 22 13.2 28 1.32 29 2.80 63 21.1 80 0.98 67 21.2 80 31.2 68 20.3 95 10.7 89 29.3 83 7.45 101 4.27 140 0.34 123 19.6 142 16.5 105 33.3 89 24.6 113
TCOF [69]66.6 1.00 51 5.63 48 0.59 83 3.53 65 21.5 72 1.69 59 7.64 87 22.0 82 3.79 83 2.80 63 19.9 73 0.77 56 21.1 78 32.7 78 13.9 62 7.79 29 20.7 14 5.77 43 0.92 116 0.03 102 3.23 114 8.40 45 23.2 47 11.4 49
ComplOF-FED-GPU [35]66.9 0.85 19 5.04 20 0.42 37 3.90 80 21.4 70 1.78 64 4.90 50 16.8 53 1.41 33 3.18 79 21.1 80 1.03 69 21.6 86 33.8 89 15.4 75 10.8 90 34.7 117 5.93 50 0.12 63 0.02 40 1.43 92 11.9 74 34.2 96 15.3 79
Adaptive [20]68.3 1.05 58 6.01 61 0.48 55 3.27 56 20.1 59 1.79 66 7.11 79 20.1 66 1.62 41 3.29 82 22.4 86 1.15 73 18.8 54 29.8 54 12.6 58 10.6 85 28.4 74 6.72 84 0.57 105 0.71 135 0.96 78 8.64 47 23.1 46 10.9 37
SRR-TVOF-NL [91]69.6 1.15 71 6.13 63 0.60 84 5.04 95 23.3 87 2.68 93 8.17 90 22.9 88 4.22 92 2.76 61 16.9 52 0.68 44 19.8 67 29.0 50 17.7 90 8.07 34 27.0 58 6.17 61 0.16 69 0.02 40 0.86 75 11.8 73 25.9 54 15.3 79
DeepFlow [86]71.0 1.19 78 6.04 62 0.57 76 4.41 87 21.3 69 2.41 87 8.35 93 22.9 88 6.63 100 4.03 100 24.5 98 1.69 94 19.0 58 30.9 65 11.8 53 7.29 27 29.5 85 4.88 26 0.00 1 0.02 40 0.00 1 15.7 104 35.1 102 23.4 109
TV-L1-improved [17]71.3 0.94 41 5.45 38 0.52 61 2.91 41 17.8 41 1.58 56 7.00 77 20.2 68 2.24 60 3.00 74 21.5 83 1.16 74 20.6 71 32.3 75 15.0 71 12.2 107 34.2 113 7.87 106 0.19 73 0.30 121 0.49 66 10.7 63 29.7 68 12.8 63
PGM-C [120]72.1 1.52 100 8.68 106 0.99 117 3.66 69 23.0 85 2.03 79 6.30 66 21.2 78 3.90 85 3.82 95 22.9 92 1.68 93 21.3 81 34.3 94 14.1 63 6.89 25 28.8 77 5.60 38 0.00 1 0.02 40 0.00 1 11.9 74 34.3 97 14.2 74
Aniso. Huber-L1 [22]73.6 1.06 59 5.69 51 0.65 87 5.24 97 25.4 100 3.29 98 8.19 91 21.4 81 4.09 90 3.10 77 21.0 78 0.97 66 18.5 50 29.1 51 12.6 58 9.08 50 27.0 58 5.56 37 0.68 108 0.08 110 2.93 113 9.25 52 24.1 49 11.8 56
CPM-Flow [116]74.7 1.53 101 8.72 108 0.98 114 3.74 75 23.5 88 2.08 81 6.22 64 20.9 75 3.88 84 3.78 93 22.5 88 1.64 91 21.3 81 34.4 96 14.2 65 7.87 31 28.8 77 6.40 73 0.00 1 0.02 40 0.00 1 12.5 84 35.6 104 14.9 77
DMF_ROB [140]74.7 1.06 59 6.27 67 0.56 72 4.09 83 20.7 64 2.13 83 7.51 85 23.3 92 3.01 71 3.67 90 23.0 94 1.51 86 20.9 76 32.8 80 16.6 83 10.2 81 30.1 87 7.29 97 0.00 1 0.02 40 0.00 1 14.3 100 35.7 106 17.3 94
Classic++ [32]74.9 1.00 51 5.92 59 0.56 72 3.28 57 19.2 50 1.87 71 6.88 74 20.7 73 3.38 75 3.41 86 23.6 96 1.30 79 20.8 75 33.2 85 15.0 71 10.0 79 31.8 101 6.69 82 0.66 107 0.02 40 2.59 111 11.3 69 29.5 65 13.5 70
Bartels [41]75.8 1.28 90 7.59 94 0.50 57 2.39 27 15.4 29 1.04 28 5.52 55 19.2 61 2.54 68 2.83 66 19.9 73 1.30 79 22.7 95 34.1 91 20.4 97 9.92 75 30.5 91 6.93 87 1.88 127 0.02 40 12.3 137 12.7 87 31.9 76 16.4 88
CBF [12]76.4 0.85 19 4.89 15 0.43 42 4.99 94 22.3 80 4.63 106 6.60 70 19.2 61 4.08 89 3.61 88 24.5 98 1.49 85 20.0 68 30.9 65 16.2 81 9.67 66 27.4 61 5.64 39 2.65 133 0.37 124 6.97 126 11.5 71 28.4 63 16.9 90
FF++_ROB [146]77.0 1.67 107 9.54 115 0.97 112 3.68 72 22.9 83 2.07 80 6.93 76 22.8 87 3.99 88 3.03 75 17.5 56 1.31 81 22.1 90 35.6 108 14.8 69 6.77 22 25.9 49 4.87 25 0.17 70 0.22 114 0.79 70 10.5 61 30.3 71 13.1 66
EpicFlow [102]77.2 1.51 98 8.63 105 0.98 114 3.76 76 23.5 88 2.11 82 7.14 80 23.6 94 3.97 87 3.79 94 22.6 90 1.64 91 21.5 85 34.4 96 14.8 69 8.97 47 29.2 81 6.53 76 0.00 1 0.02 40 0.00 1 12.4 82 34.5 98 15.2 78
LocallyOriented [52]78.5 1.78 115 9.64 117 0.77 96 6.11 106 28.2 107 3.79 103 10.9 104 28.0 108 5.52 97 3.28 81 19.5 70 1.55 87 22.8 97 33.9 90 17.6 89 9.84 71 24.6 39 6.63 80 0.00 1 0.00 1 0.00 1 11.9 74 29.6 67 15.7 83
CLG-TV [48]79.5 1.01 54 5.46 39 0.50 57 4.16 85 23.5 88 2.40 86 7.52 86 21.2 78 2.51 67 3.33 83 22.8 91 1.14 72 20.9 76 32.4 76 15.6 77 8.94 46 31.7 100 6.35 71 1.27 120 1.18 140 3.55 117 11.1 68 28.2 62 13.5 70
TriangleFlow [30]81.0 1.19 78 6.73 79 0.53 63 3.88 79 21.8 76 1.64 58 6.61 71 20.1 66 1.59 39 2.35 44 19.3 68 0.89 61 25.6 108 37.3 113 23.5 111 13.4 120 30.5 91 8.48 114 0.81 112 0.17 112 1.33 90 10.7 63 28.1 61 13.1 66
Fusion [6]81.1 1.15 71 6.83 81 0.71 93 2.10 15 14.5 22 1.23 36 4.58 46 15.4 47 3.60 81 3.73 92 27.2 109 2.38 103 23.9 101 33.7 87 26.4 116 8.36 39 27.3 60 7.11 92 1.00 117 0.64 134 2.66 112 14.5 101 34.0 95 18.7 97
Rannacher [23]81.8 1.09 64 6.27 67 0.54 68 3.77 77 22.1 78 2.27 84 7.89 88 22.4 84 3.34 73 3.67 90 23.5 95 1.61 89 21.1 78 33.1 83 15.8 79 12.9 116 35.4 119 7.98 107 0.43 98 0.02 40 1.63 97 10.5 61 29.5 65 12.8 63
SIOF [67]82.0 1.24 83 6.63 76 0.51 59 5.26 98 26.2 101 3.22 97 11.5 105 26.1 98 12.3 108 4.49 103 27.4 112 2.29 101 22.8 97 33.3 86 23.4 110 8.56 41 28.8 77 7.15 94 0.00 1 0.02 40 0.00 1 13.6 91 32.1 79 23.6 111
F-TV-L1 [15]83.4 1.22 80 6.63 76 0.53 63 5.86 103 24.8 97 3.51 102 9.25 97 23.4 93 3.44 77 3.91 96 24.9 100 1.61 89 20.3 69 31.5 70 16.2 81 11.3 101 30.9 95 7.40 100 0.15 68 0.47 129 0.17 56 9.88 58 27.6 60 11.1 42
ResPWCR_ROB [145]84.0 1.22 80 7.22 86 0.68 90 5.04 95 24.6 95 2.77 95 9.17 96 26.7 101 6.63 100 3.22 80 22.4 86 1.31 81 22.7 95 35.5 107 18.0 91 10.9 91 32.3 103 7.99 108 0.00 1 0.02 40 0.00 1 14.2 97 37.2 109 16.5 89
Local-TV-L1 [65]85.1 1.57 102 7.45 92 0.67 89 7.93 111 28.0 105 5.97 112 12.9 112 26.6 100 12.2 107 6.04 120 31.1 119 3.55 119 18.7 53 29.9 57 12.9 60 9.33 58 28.1 68 5.97 53 0.00 1 0.02 40 0.00 1 21.0 123 37.7 112 37.5 128
p-harmonic [29]85.3 1.08 62 6.28 70 0.55 70 3.66 69 20.5 63 2.48 90 8.22 92 23.0 91 3.92 86 5.04 108 28.4 115 3.51 117 24.8 105 34.1 91 30.1 121 7.78 28 32.3 103 6.54 77 0.19 73 0.44 128 0.00 1 14.2 97 33.0 85 21.8 105
BriefMatch [124]85.9 0.96 45 5.52 45 0.53 63 3.55 66 18.6 48 1.97 73 4.95 51 16.9 54 1.82 48 2.57 54 19.7 72 0.92 64 21.8 87 32.7 78 20.8 101 16.2 129 33.7 111 13.5 131 3.95 138 0.97 139 15.8 138 17.3 111 34.7 100 25.4 115
OFRF [134]86.8 1.68 108 8.84 110 0.73 94 12.5 123 28.4 109 11.9 124 12.8 111 24.7 95 13.6 110 4.30 102 18.9 66 2.52 104 18.9 56 30.4 61 9.65 38 11.5 104 27.9 65 5.03 30 0.13 65 0.00 1 0.71 69 20.9 122 32.7 84 40.3 131
TriFlow [95]88.2 1.51 98 8.71 107 0.78 97 4.56 91 22.8 82 3.37 100 12.5 109 28.2 109 17.8 113 2.41 47 18.3 61 0.91 62 24.8 105 34.4 96 25.7 114 5.97 16 23.5 32 4.74 22 19.3 146 0.27 119 59.0 146 13.2 90 32.5 82 14.1 73
ContinualFlow_ROB [153]88.4 2.51 124 13.8 129 1.37 127 9.26 115 34.0 118 7.16 115 13.6 114 32.9 117 18.7 114 3.59 87 18.0 60 2.00 97 27.7 124 44.1 131 16.1 80 11.1 96 34.2 113 7.02 88 0.00 1 0.02 40 0.00 1 9.54 56 28.7 64 7.73 10
Dynamic MRF [7]89.1 1.26 86 7.42 89 0.57 76 3.39 61 21.4 70 1.58 56 7.00 77 22.5 85 2.22 59 3.40 85 24.1 97 1.69 94 25.9 114 37.6 114 24.8 113 14.4 124 41.5 130 9.85 118 0.09 60 0.00 1 0.96 78 19.2 118 39.4 118 25.5 116
DF-Auto [115]90.2 1.84 116 8.87 111 0.90 104 8.40 112 30.1 112 6.82 113 13.3 113 27.9 107 19.6 115 5.29 111 26.6 105 3.01 109 22.2 91 32.9 81 21.0 102 5.80 13 23.6 33 5.02 29 0.18 72 0.61 132 0.00 1 14.8 102 32.4 81 19.9 100
LFNet_ROB [150]90.8 1.98 120 11.1 122 0.90 104 5.93 104 28.1 106 3.47 101 10.5 102 32.4 116 6.86 102 3.11 78 19.2 67 1.60 88 30.0 129 44.1 131 28.0 119 9.85 72 35.2 118 7.05 91 0.00 1 0.00 1 0.00 1 14.2 97 39.1 116 17.0 93
Brox et al. [5]92.3 1.22 80 6.66 78 0.70 92 4.15 84 24.3 94 2.39 85 7.21 81 22.1 83 4.18 91 4.91 106 26.3 104 2.65 105 26.2 117 35.7 109 31.4 124 10.5 83 33.4 110 7.34 99 0.01 44 0.13 111 0.00 1 17.1 110 39.1 116 23.0 108
FlowNet2 [122]94.3 2.63 126 12.9 127 1.14 122 17.9 128 43.1 130 16.1 130 17.0 119 32.9 117 25.3 128 3.92 97 16.7 51 2.16 98 25.8 112 40.2 124 17.0 86 10.6 85 28.2 70 8.09 109 0.02 49 0.00 1 0.20 58 12.2 80 34.5 98 9.71 18
SuperFlow [81]95.4 1.26 86 5.91 58 0.66 88 6.58 108 24.8 97 5.70 111 12.7 110 26.7 101 20.1 116 5.60 115 28.6 116 3.33 114 24.6 104 33.7 87 31.7 127 8.09 35 30.8 94 7.19 95 0.02 49 0.07 108 0.02 49 16.6 106 37.3 110 22.5 106
EAI-Flow [152]96.4 1.85 117 10.2 119 0.87 103 7.43 109 29.8 111 4.76 108 10.7 103 28.8 110 8.51 103 4.64 104 22.9 92 2.75 107 26.8 120 41.4 126 20.4 97 9.10 52 31.4 98 5.88 46 0.17 70 0.02 40 1.11 81 13.9 92 35.9 107 18.8 98
EPMNet [133]98.0 2.58 125 13.6 128 1.08 119 17.2 127 45.9 132 14.3 126 15.3 118 31.5 115 21.6 119 4.71 105 24.9 100 2.35 102 25.8 112 40.2 124 17.0 86 10.6 85 28.2 70 8.09 109 0.01 44 0.00 1 0.10 53 15.0 103 44.1 127 9.78 22
Second-order prior [8]99.4 1.24 83 6.93 83 0.58 80 5.26 98 27.0 103 3.34 99 9.68 99 26.8 103 5.39 96 4.25 101 26.1 103 2.25 99 22.5 92 34.4 96 19.0 93 12.9 116 41.2 129 8.26 113 1.14 119 0.07 108 2.41 108 12.7 87 32.5 82 18.2 96
AugFNG_ROB [144]101.8 3.78 134 18.3 137 1.78 131 15.9 126 39.3 126 15.3 129 17.3 120 37.8 126 24.2 125 3.99 98 18.6 65 2.27 100 29.6 126 45.3 134 21.5 105 11.1 96 34.5 116 7.60 103 0.00 1 0.00 1 0.00 1 18.5 116 46.2 130 18.8 98
SegOF [10]102.3 1.62 105 9.24 114 1.14 122 14.8 125 38.8 125 14.3 126 17.8 122 33.2 119 22.3 121 6.57 121 27.5 113 4.43 122 32.5 133 41.8 129 43.4 137 14.1 123 38.0 124 10.5 121 0.00 1 0.00 1 0.00 1 14.0 94 33.7 94 12.6 62
StereoOF-V1MT [119]103.2 1.42 96 8.08 100 0.56 72 6.56 107 34.1 119 2.73 94 10.0 101 29.8 112 2.19 56 4.91 106 34.6 124 2.66 106 31.4 132 44.5 133 31.4 124 15.8 128 48.0 136 11.6 126 0.05 58 0.00 1 0.52 67 24.0 126 48.7 134 28.5 119
Shiralkar [42]103.5 1.27 88 7.43 90 0.53 63 5.83 102 30.1 112 2.93 96 9.62 98 26.2 99 3.70 82 5.11 109 30.7 118 3.08 111 25.7 109 39.1 120 22.5 108 17.9 130 45.5 132 9.73 117 1.80 125 0.00 1 8.23 130 18.4 115 44.9 128 19.9 100
WOLF_ROB [149]103.7 2.17 121 11.1 122 0.90 104 11.0 117 38.1 124 6.99 114 14.3 115 33.5 120 10.3 105 5.21 110 25.8 102 3.01 109 26.8 120 38.9 119 26.6 117 12.4 112 30.4 89 7.26 96 0.09 60 0.00 1 0.84 72 16.8 108 39.6 120 24.5 112
FlowNetS+ft+v [112]104.1 1.40 95 7.39 88 0.80 98 5.75 101 23.6 91 4.35 105 11.7 107 27.3 105 12.4 109 5.33 112 27.2 109 3.18 113 25.7 109 35.4 106 26.9 118 8.52 40 32.0 102 6.85 85 2.34 131 1.61 143 10.1 134 14.0 94 34.9 101 20.1 103
CNN-flow-warp+ref [117]105.6 1.63 106 9.14 112 0.91 108 5.41 100 24.0 93 4.66 107 11.6 106 29.8 112 10.7 106 5.59 114 27.1 108 3.43 115 26.6 119 36.0 110 31.5 126 11.3 101 33.1 108 7.62 104 0.03 52 0.25 117 0.07 51 20.4 120 40.5 122 28.3 118
2bit-BM-tele [98]105.9 1.75 111 9.59 116 0.85 100 4.44 88 24.7 96 2.62 92 8.64 94 25.8 97 4.56 93 3.99 98 27.8 114 1.98 96 22.6 94 33.1 83 20.5 99 14.6 125 32.7 107 10.7 122 5.96 143 1.68 144 21.9 144 14.1 96 33.4 90 19.9 100
StereoFlow [44]106.4 7.67 143 21.8 140 3.86 139 51.5 146 74.0 147 46.2 143 43.7 147 63.5 147 36.8 138 51.6 145 79.4 147 47.5 144 26.1 115 38.0 116 21.1 103 5.83 14 26.9 56 4.93 27 0.00 1 0.02 40 0.00 1 20.7 121 38.1 114 29.7 120
Learning Flow [11]106.5 1.35 94 7.83 97 0.56 72 4.48 89 26.8 102 2.43 89 9.85 100 27.1 104 5.06 94 6.65 122 33.5 122 4.13 120 29.9 128 40.0 123 34.1 131 12.8 114 38.5 126 8.86 116 0.28 83 0.29 120 1.13 82 17.0 109 37.6 111 22.8 107
Ad-TV-NDC [36]106.5 3.59 131 8.26 101 6.67 143 21.3 132 38.0 122 22.4 135 19.7 125 33.6 121 21.8 120 13.5 127 33.9 123 15.0 128 19.4 61 30.6 63 12.5 57 9.58 63 28.6 76 6.54 77 0.21 75 0.37 124 0.17 56 28.1 132 43.2 125 47.4 138
LDOF [28]106.8 1.59 104 8.06 98 0.97 112 6.08 105 27.9 104 3.79 103 8.98 95 25.2 96 6.05 98 5.90 118 33.2 121 3.14 112 23.5 99 34.5 100 22.7 109 9.83 69 34.0 112 7.30 98 0.86 114 1.28 141 3.67 118 16.7 107 39.7 121 23.5 110
SPSA-learn [13]107.5 1.77 113 7.72 96 0.90 104 11.0 117 33.2 115 9.40 120 17.3 120 34.2 122 22.7 123 11.0 124 32.2 120 10.9 124 26.1 115 34.9 102 31.8 129 12.8 114 34.2 113 11.9 127 0.00 1 0.03 102 0.00 1 25.5 130 39.4 118 39.6 130
BlockOverlap [61]109.0 1.73 110 8.32 102 1.07 118 8.43 113 28.3 108 7.39 116 14.3 115 29.4 111 16.3 112 6.01 119 26.7 107 4.24 121 20.6 71 29.8 54 20.6 100 12.4 112 29.4 84 8.20 112 3.91 137 0.92 138 16.5 140 19.1 117 31.7 75 36.0 124
Filter Flow [19]110.2 1.97 119 10.2 119 1.14 122 8.79 114 33.9 117 5.66 109 18.8 123 35.7 123 26.2 129 21.9 131 42.4 128 22.0 131 27.9 125 36.8 112 35.0 132 13.2 119 32.6 106 8.11 111 0.05 58 0.02 40 0.37 65 17.5 112 33.0 85 25.2 114
HBpMotionGpu [43]110.8 2.47 123 11.8 124 1.09 120 11.4 120 35.3 120 10.0 122 20.3 128 38.5 128 26.3 130 5.67 116 26.6 105 3.51 117 24.1 102 34.8 101 26.1 115 10.9 91 30.7 93 7.04 89 0.27 82 0.05 106 0.89 77 19.3 119 37.1 108 32.8 122
TVL1_ROB [139]114.0 3.70 132 15.6 132 1.80 132 28.3 137 41.8 129 32.9 139 26.2 134 42.0 130 37.7 141 27.9 135 54.9 136 33.1 137 27.0 122 37.8 115 30.2 122 12.2 107 36.9 121 10.2 120 0.00 1 0.00 1 0.00 1 32.6 138 48.2 133 49.8 140
GraphCuts [14]114.0 1.57 102 8.32 102 0.92 109 12.3 122 39.3 126 8.40 117 15.2 117 31.3 114 23.1 124 5.40 113 28.8 117 2.88 108 25.4 107 38.0 116 21.1 103 24.5 140 31.1 96 14.4 133 1.86 126 0.02 40 7.91 129 23.9 125 41.6 124 37.4 127
IAOF [50]114.7 1.77 113 8.80 109 0.98 114 11.2 119 32.5 114 9.32 119 19.8 126 35.7 123 20.2 117 17.5 129 37.6 125 19.8 129 23.7 100 35.0 103 22.3 107 18.1 133 40.2 127 10.9 123 0.56 102 0.02 40 2.17 107 24.8 128 37.8 113 43.9 133
UnFlow [129]115.2 7.34 140 24.6 145 3.32 136 21.7 133 50.1 135 19.1 131 26.8 136 53.1 142 25.0 126 13.7 128 42.5 129 12.5 127 42.2 141 53.7 142 45.6 140 15.1 127 46.2 133 12.1 128 0.00 1 0.00 1 0.00 1 17.5 112 43.7 126 21.5 104
IAOF2 [51]116.4 1.85 117 9.64 117 1.13 121 7.56 110 29.4 110 5.66 109 12.2 108 27.5 106 15.7 111 32.6 138 43.3 131 38.7 141 24.3 103 35.0 103 23.9 112 17.9 130 33.1 108 13.0 129 1.11 118 0.25 117 4.83 121 17.8 114 35.5 103 25.9 117
Black & Anandan [4]117.9 1.75 111 8.07 99 0.73 94 11.6 121 36.6 121 8.94 118 18.9 124 36.4 125 20.3 118 12.4 126 40.5 127 12.0 126 26.3 118 36.2 111 30.5 123 13.4 120 37.3 122 11.0 124 0.75 110 0.42 127 1.90 104 21.4 124 38.6 115 32.5 121
Nguyen [33]120.5 2.73 127 11.0 121 1.16 126 33.4 140 38.0 122 43.1 142 24.6 132 41.9 129 32.1 135 28.7 136 46.5 132 32.2 136 29.8 127 39.8 121 35.5 133 13.9 122 40.4 128 13.0 129 0.03 52 0.02 40 0.20 58 31.6 133 46.3 131 50.5 141
Modified CLG [34]121.5 2.46 122 12.2 125 1.37 127 10.5 116 33.6 116 9.99 121 20.2 127 37.9 127 27.9 132 9.52 123 38.0 126 7.95 123 27.6 123 38.6 118 31.7 127 11.2 99 37.6 123 8.53 115 0.70 109 0.24 116 3.33 116 24.7 127 45.8 129 38.5 129
2D-CLG [1]123.3 6.98 139 23.0 142 3.54 137 20.1 131 40.7 128 21.4 133 26.6 135 44.0 131 36.7 136 34.7 139 55.1 137 39.7 142 31.1 131 41.5 128 38.2 134 15.0 126 42.0 131 13.6 132 0.02 49 0.02 40 0.12 54 31.7 134 51.0 136 44.9 134
GroupFlow [9]126.3 3.39 129 16.8 135 1.37 127 23.0 134 51.6 137 21.5 134 20.7 129 45.1 134 22.3 121 5.67 116 27.3 111 3.50 116 34.6 135 51.5 140 22.0 106 22.4 137 47.9 135 25.4 141 0.55 101 0.47 129 1.70 100 25.2 129 47.9 132 33.5 123
SILK [79]126.3 3.45 130 15.8 133 2.61 134 19.0 129 44.9 131 19.5 132 23.5 131 44.1 132 26.6 131 12.0 125 42.7 130 11.1 125 35.3 136 46.3 137 44.8 138 18.0 132 49.4 137 14.5 134 1.53 123 0.00 1 5.00 122 32.1 137 50.8 135 47.1 137
Horn & Schunck [3]128.6 3.02 128 12.7 126 1.15 125 14.5 124 45.9 132 11.1 123 22.6 130 44.4 133 25.2 127 21.6 130 47.3 133 22.5 132 34.0 134 43.8 130 43.1 136 19.6 134 51.5 139 18.6 137 0.56 102 0.22 114 1.77 101 34.9 140 55.9 140 46.4 136
Heeger++ [104]129.9 3.74 133 16.1 134 1.49 130 23.6 135 64.4 146 14.1 125 36.0 143 49.4 140 37.3 140 38.6 143 67.3 143 38.6 140 46.7 144 58.2 145 50.9 143 36.6 145 68.1 147 34.5 145 0.41 96 0.00 1 1.87 102 31.8 135 51.3 137 37.0 125
TI-DOFE [24]130.5 7.50 141 18.0 136 10.6 144 41.8 144 54.1 140 49.7 144 31.9 140 54.7 145 39.7 143 41.8 144 61.8 140 48.6 145 35.5 138 45.7 136 45.0 139 21.9 136 52.6 140 21.7 139 0.25 79 0.00 1 1.31 89 43.7 143 61.4 143 58.6 143
FFV1MT [106]132.8 4.51 136 19.1 138 2.74 135 19.4 130 58.6 144 14.7 128 40.8 145 53.4 144 50.0 146 38.5 142 73.8 146 37.7 138 46.4 143 56.0 144 56.7 146 33.1 143 66.2 145 31.1 143 0.75 110 0.02 40 2.04 105 31.8 135 51.3 137 37.0 125
H+S_ROB [138]132.9 9.19 147 27.8 152 4.80 142 31.3 139 62.4 145 29.2 137 34.2 142 55.9 146 37.2 139 53.5 147 70.4 145 59.5 146 47.3 145 54.7 143 66.6 147 34.7 144 64.3 144 38.0 146 0.03 52 0.02 40 0.30 62 57.6 147 67.9 146 63.1 146
Periodicity [78]134.4 6.73 138 29.6 153 3.88 140 24.0 136 52.2 138 25.5 136 36.6 144 47.1 137 40.1 144 23.0 132 60.3 139 20.8 130 53.1 147 69.7 147 49.1 142 36.9 146 67.0 146 33.4 144 0.54 100 0.02 40 7.78 128 34.7 139 64.9 145 46.1 135
Adaptive flow [45]134.8 4.48 135 15.3 131 1.90 133 37.1 142 47.9 134 40.5 140 28.1 137 45.1 134 37.9 142 23.3 133 53.8 135 24.8 133 30.1 130 41.4 126 28.5 120 22.6 138 46.3 134 15.6 135 17.3 145 5.51 146 58.1 145 26.0 131 41.5 123 40.5 132
SLK [47]135.8 8.22 146 24.0 144 12.3 145 41.4 143 57.7 143 50.8 145 29.7 139 53.3 143 36.7 136 52.4 146 57.7 138 61.8 147 42.6 142 52.1 141 54.9 144 23.9 139 54.4 142 24.4 140 3.11 136 0.00 1 7.07 127 45.8 145 61.9 144 61.9 144
PGAM+LK [55]139.4 7.83 144 22.3 141 13.7 146 29.1 138 54.2 141 31.3 138 25.6 133 48.1 139 29.9 134 29.7 137 68.4 144 28.3 135 38.2 139 50.8 139 43.0 135 25.1 141 56.4 143 21.4 138 6.54 144 0.57 131 19.1 141 38.5 141 60.8 142 51.7 142
FOLKI [16]139.9 5.65 137 23.4 143 4.60 141 35.1 141 52.9 139 42.6 141 28.3 138 52.7 141 29.6 133 24.1 134 53.7 134 27.7 134 38.9 140 49.3 138 47.8 141 25.3 142 54.3 141 27.7 142 5.73 142 1.38 142 20.1 143 43.9 144 60.5 141 62.2 145
HCIC-L [99]140.2 8.04 145 19.9 139 3.64 138 56.4 147 56.0 142 70.0 147 40.9 146 45.5 136 62.3 147 38.3 141 62.5 141 38.2 139 35.3 136 45.3 134 32.0 130 20.7 135 38.1 125 18.5 136 26.5 147 13.0 147 59.2 147 40.6 142 51.8 139 48.7 139
Pyramid LK [2]142.9 7.59 142 14.5 130 15.4 147 47.0 145 50.5 136 58.8 146 32.1 141 47.7 138 42.4 145 36.1 140 62.9 142 41.1 143 48.9 146 61.1 146 55.0 145 41.7 147 50.3 138 40.3 147 4.64 141 2.07 145 16.3 139 56.9 146 71.9 147 77.2 147
AdaConv-v1 [126]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
SepConv-v1 [127]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
SuperSlomo [132]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
FGIK [136]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
CtxSyn [137]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
CyclicGen [154]148.2 25.9 148 27.4 146 29.8 148 96.8 148 97.6 148 95.4 148 93.0 148 90.8 148 99.0 148 88.2 148 85.6 148 91.5 148 97.0 148 98.5 149 88.6 148 86.2 148 81.3 148 83.9 148 64.9 149 56.4 149 97.3 149 100.0 149 99.9 149 99.9 149
AVG_FLOW_ROB [142]152.0 73.2 154 62.5 154 69.7 154 98.2 154 97.8 154 97.4 154 99.9 154 99.9 154 99.8 154 92.1 154 87.3 154 92.8 154 98.1 154 97.7 148 97.7 154 87.7 154 86.5 154 83.9 148 58.7 148 25.5 148 95.7 148 98.8 148 99.4 148 99.7 148
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.