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        
R2.0
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]5.3 0.19 25 1.11 28 0.00 1 0.73 3 5.01 3 0.12 2 1.08 3 3.84 2 0.00 1 0.54 6 4.91 6 0.02 4 4.35 2 7.43 2 0.89 2 1.53 1 8.39 2 1.54 3 0.00 1 0.00 1 0.00 1 3.65 8 12.4 19 1.32 2
PMMST [114]9.1 0.20 31 1.20 38 0.03 55 0.57 1 4.20 1 0.21 11 1.12 4 3.98 4 0.06 5 0.16 3 1.79 3 0.00 1 6.17 4 10.4 4 2.09 5 2.24 3 10.3 5 3.42 21 0.00 1 0.00 1 0.00 1 3.14 4 10.1 6 3.34 6
NN-field [71]11.1 0.23 57 1.37 59 0.00 1 0.64 2 4.87 2 0.07 1 1.23 7 4.31 5 0.03 3 0.60 7 5.03 7 0.04 5 4.24 1 7.24 1 0.70 1 5.93 51 6.73 1 2.33 9 0.00 1 0.00 1 0.00 1 3.87 11 13.1 31 1.27 1
OFLAF [77]12.3 0.20 31 1.21 39 0.00 1 0.92 9 5.66 7 0.25 16 1.22 5 4.32 6 0.12 10 1.03 18 8.42 21 0.22 28 7.31 9 12.4 9 2.79 9 3.20 13 11.6 7 3.15 18 0.00 1 0.00 1 0.00 1 3.66 9 9.73 5 7.15 23
Layers++ [37]17.7 0.15 6 0.90 8 0.00 1 0.88 7 6.28 10 0.29 18 1.61 12 5.50 12 0.95 68 0.92 15 5.94 9 0.24 36 6.07 3 9.99 3 3.95 13 6.14 56 15.3 24 5.23 71 0.00 1 0.00 1 0.00 1 4.11 14 10.5 7 7.50 29
ComponentFusion [96]17.9 0.17 14 1.02 18 0.03 55 0.93 10 6.31 11 0.23 15 1.48 10 5.26 10 0.22 17 0.68 8 6.90 13 0.05 6 10.5 41 17.2 43 7.34 43 3.34 15 15.8 28 3.80 30 0.00 1 0.00 1 0.00 1 3.81 10 11.2 12 6.45 18
TC/T-Flow [76]18.0 0.11 2 0.67 2 0.00 1 1.63 48 8.48 32 0.45 26 2.21 18 7.45 19 0.16 13 1.20 41 10.2 50 0.16 9 9.34 33 14.9 29 6.04 31 1.76 2 9.86 4 1.36 1 0.00 1 0.00 1 0.00 1 4.64 23 12.6 22 7.19 24
MDP-Flow2 [68]18.4 0.18 20 1.07 23 0.03 55 0.82 4 5.18 4 0.20 10 1.31 8 4.69 8 0.09 8 1.24 47 11.0 55 0.24 36 9.23 30 15.2 33 5.96 30 2.65 6 11.8 9 3.56 24 0.00 1 0.00 1 0.00 1 3.61 7 11.1 10 5.40 12
CombBMOF [113]22.2 0.20 31 1.18 33 0.03 55 1.05 14 6.42 12 0.16 4 1.66 13 5.67 13 0.01 2 0.79 11 6.82 12 0.16 9 7.66 12 12.5 11 4.37 16 8.16 87 15.3 24 7.67 112 0.00 1 0.00 1 0.00 1 4.31 16 11.0 9 7.79 33
NNF-EAC [103]22.7 0.17 14 1.03 19 0.01 33 1.01 11 5.78 9 0.38 25 1.81 15 6.09 15 0.13 11 1.27 51 11.4 57 0.24 36 8.50 21 14.2 24 5.00 23 4.85 34 12.2 11 4.55 49 0.00 1 0.00 1 0.00 1 4.77 27 13.1 31 7.37 26
WLIF-Flow [93]22.8 0.20 31 1.21 39 0.01 33 0.91 8 5.77 8 0.26 17 2.30 21 7.50 20 0.38 32 1.10 27 8.71 23 0.25 47 8.40 20 14.0 20 4.94 22 4.91 36 13.0 13 3.79 29 0.00 1 0.00 1 0.00 1 4.98 32 12.6 22 8.37 45
3DFlow [135]23.8 0.26 71 1.57 75 0.00 1 1.31 28 9.13 42 0.31 20 2.56 36 8.87 38 0.25 19 0.11 1 1.19 1 0.00 1 8.69 25 14.2 24 5.21 24 8.16 87 15.8 28 4.22 39 0.00 1 0.00 1 0.00 1 2.86 2 9.33 2 2.36 4
MLDP_OF [89]23.9 0.17 14 1.00 16 0.00 1 0.82 4 5.37 5 0.13 3 2.62 38 8.28 30 0.15 12 1.01 17 8.41 20 0.17 16 8.84 26 14.4 26 5.24 26 2.41 4 11.1 6 1.54 3 0.29 109 0.00 1 1.28 112 5.41 42 12.9 28 5.66 14
nLayers [57]24.4 0.19 25 1.13 30 0.00 1 1.04 13 7.08 20 0.31 20 2.42 28 8.37 33 0.50 38 1.10 27 8.82 25 0.38 62 6.91 8 11.4 8 3.98 14 6.52 61 12.6 12 5.28 73 0.00 1 0.00 1 0.00 1 4.63 22 12.5 21 8.25 41
FC-2Layers-FF [74]24.5 0.19 25 1.10 26 0.00 1 1.53 41 10.0 53 0.68 48 1.47 9 5.05 9 0.37 31 1.07 23 8.29 19 0.22 28 6.46 5 10.5 5 3.24 10 6.93 68 15.2 22 5.43 78 0.00 1 0.00 1 0.00 1 4.89 28 12.6 22 7.93 35
FlowFields+ [130]25.5 0.15 6 0.88 6 0.01 33 1.38 33 8.90 39 0.68 48 2.23 20 7.99 23 0.44 36 0.70 9 6.60 10 0.20 22 12.0 51 19.4 54 7.65 46 2.62 5 16.5 43 1.82 7 0.00 1 0.00 1 0.00 1 5.64 47 18.0 57 5.92 15
IIOF-NLDP [131]25.5 0.32 88 1.90 91 0.00 1 1.27 26 8.57 33 0.16 4 3.02 51 9.58 47 0.20 14 0.48 5 3.49 5 0.13 8 9.15 28 14.9 29 4.86 20 6.07 53 14.8 21 4.05 37 0.00 1 0.00 1 0.00 1 4.43 19 12.0 17 5.52 13
Correlation Flow [75]25.7 0.25 68 1.46 69 0.00 1 1.10 18 7.16 21 0.22 13 4.18 66 12.3 62 0.35 28 0.74 10 5.14 8 0.22 28 11.5 46 17.7 45 9.04 57 4.12 26 13.1 14 2.69 12 0.00 1 0.00 1 0.00 1 3.48 5 10.9 8 3.71 8
PH-Flow [101]27.0 0.20 31 1.16 31 0.00 1 1.36 30 7.94 26 0.53 36 1.69 14 5.76 14 0.64 51 1.10 27 8.60 22 0.24 36 6.59 6 11.1 6 3.26 11 3.52 19 11.6 7 3.39 19 0.13 99 0.00 1 0.44 94 4.21 15 11.4 14 7.94 37
PMF [73]27.7 0.20 31 1.19 35 0.03 55 1.06 17 6.51 13 0.18 7 1.50 11 5.33 11 0.09 8 1.26 50 9.04 31 0.23 31 7.32 10 12.4 9 1.91 3 5.47 41 16.3 35 4.67 53 0.09 93 0.00 1 0.25 89 3.51 6 9.50 3 6.99 21
IROF++ [58]28.1 0.23 57 1.37 59 0.00 1 1.37 32 8.26 29 0.45 26 2.40 26 7.86 21 0.51 41 1.16 37 9.50 42 0.24 36 8.06 16 13.2 15 4.86 20 5.64 47 16.4 38 4.51 47 0.00 1 0.00 1 0.00 1 4.62 20 12.7 27 7.93 35
AGIF+OF [85]28.2 0.21 43 1.25 48 0.00 1 1.48 39 8.75 36 0.37 23 2.50 33 8.15 27 0.38 32 1.14 32 8.88 26 0.23 31 7.56 11 12.5 11 4.30 15 6.71 64 15.2 22 4.99 64 0.00 1 0.00 1 0.00 1 5.07 35 13.0 30 8.68 52
HAST [109]29.1 0.21 43 1.27 50 0.03 55 1.55 44 6.58 14 0.85 61 1.07 2 3.84 2 0.06 5 1.18 40 9.57 44 0.19 21 6.70 7 11.3 7 2.10 6 5.68 48 14.2 18 5.14 69 0.01 78 0.00 1 0.05 79 2.21 1 7.87 1 2.21 3
ProbFlowFields [128]30.3 0.20 31 1.18 33 0.03 55 1.25 24 7.90 25 0.64 45 2.55 35 8.95 39 1.08 71 0.25 4 2.68 4 0.05 6 12.5 60 19.9 59 8.91 55 2.82 9 15.8 28 2.70 13 0.00 1 0.00 1 0.00 1 5.90 51 18.1 58 6.95 20
SVFilterOh [111]31.4 0.22 50 1.31 52 0.05 72 1.14 20 6.84 17 0.30 19 2.13 17 7.39 17 0.69 55 0.86 12 7.24 14 0.16 9 8.17 17 13.8 18 2.18 7 6.69 62 15.3 24 4.47 46 0.27 108 0.00 1 0.74 99 2.89 3 9.59 4 3.97 10
EPPM w/o HM [88]31.9 0.21 43 1.25 48 0.03 55 1.05 14 6.95 19 0.19 8 2.42 28 8.24 29 0.08 7 1.00 16 7.81 17 0.21 26 7.69 13 13.0 13 2.55 8 6.45 60 18.5 63 4.04 36 0.43 116 0.00 1 0.76 100 3.98 13 11.1 10 7.10 22
CostFilter [40]31.9 0.22 50 1.32 55 0.03 55 1.16 21 6.61 15 0.22 13 1.22 5 4.37 7 0.21 16 1.29 52 10.2 50 0.21 26 7.77 14 13.2 15 2.07 4 5.43 39 15.9 32 3.96 35 0.07 90 0.00 1 0.12 84 4.75 26 13.5 37 7.19 24
TC-Flow [46]32.3 0.13 3 0.77 3 0.00 1 1.38 33 8.10 28 0.47 29 2.97 50 10.0 51 0.34 26 1.36 58 10.5 53 0.25 47 11.2 44 18.1 47 7.49 44 3.36 16 17.1 50 1.78 6 0.00 1 0.00 1 0.00 1 6.35 57 17.8 56 10.0 70
FlowFields [110]35.0 0.16 10 0.97 12 0.02 50 1.54 43 9.90 52 0.72 51 2.38 24 8.48 35 0.58 49 1.03 18 9.05 32 0.31 55 12.5 60 20.3 64 8.76 54 3.16 12 18.0 62 3.08 17 0.00 1 0.00 1 0.00 1 6.22 55 19.0 62 6.76 19
ALD-Flow [66]35.0 0.14 5 0.85 5 0.01 33 1.70 50 8.34 30 0.50 32 2.94 48 9.96 50 0.38 32 1.68 68 13.0 66 0.32 57 11.8 50 18.8 51 8.42 52 2.93 10 16.4 38 1.70 5 0.00 1 0.00 1 0.00 1 5.91 53 17.4 54 8.45 48
COFM [59]35.5 0.28 77 1.64 77 0.06 77 1.31 28 7.81 23 0.57 40 3.57 58 12.0 60 1.10 73 0.91 14 7.78 16 0.16 9 11.7 49 18.5 50 10.3 71 4.05 24 13.7 17 4.28 42 0.00 1 0.00 1 0.00 1 3.96 12 11.5 15 6.40 17
RNLOD-Flow [121]35.8 0.17 14 1.03 19 0.00 1 1.50 40 9.63 47 0.56 39 3.15 53 10.1 53 0.56 48 1.14 32 9.02 30 0.20 22 9.73 37 15.7 37 6.54 37 5.43 39 14.7 20 4.56 51 0.06 88 0.00 1 0.34 90 4.41 17 11.3 13 7.56 30
Sparse-NonSparse [56]36.6 0.22 50 1.31 52 0.00 1 1.87 60 11.4 62 0.80 57 2.47 32 8.05 25 0.52 43 1.15 36 8.89 27 0.24 36 9.37 34 15.3 34 5.94 29 7.18 70 16.3 35 5.47 80 0.00 1 0.00 1 0.00 1 5.08 36 13.1 31 8.42 46
LSM [39]36.9 0.21 43 1.23 43 0.00 1 1.88 62 11.5 63 0.82 59 2.45 30 8.04 24 0.52 43 1.12 30 9.06 33 0.23 31 9.27 32 15.1 32 6.05 32 7.21 72 16.5 43 5.47 80 0.00 1 0.00 1 0.00 1 5.29 40 13.8 39 8.49 50
S2F-IF [123]36.9 0.18 20 1.07 23 0.02 50 1.53 41 10.0 53 0.72 51 2.37 23 8.45 34 0.54 45 1.21 42 9.59 45 0.35 58 12.7 64 20.3 64 9.20 61 3.41 17 17.7 58 3.70 27 0.00 1 0.00 1 0.00 1 5.36 41 16.5 50 6.13 16
LME [70]37.0 0.24 61 1.40 63 0.04 69 0.84 6 5.51 6 0.21 11 3.70 59 8.78 36 5.39 98 1.38 59 11.0 55 0.37 60 9.52 36 15.3 34 7.58 45 3.73 21 16.9 48 4.43 44 0.00 1 0.00 1 0.00 1 4.62 20 12.6 22 7.77 32
FMOF [94]37.2 0.20 31 1.19 35 0.00 1 1.61 47 9.42 45 0.53 36 2.03 16 6.86 16 0.22 17 1.04 20 8.71 23 0.16 9 8.59 22 14.0 20 4.44 17 7.80 81 16.2 33 5.73 87 0.09 93 0.00 1 0.81 102 5.75 49 14.6 44 8.44 47
HBM-GC [105]37.5 0.29 79 1.72 82 0.03 55 1.36 30 8.81 37 0.71 50 2.92 46 10.0 51 0.79 56 1.21 42 8.97 29 0.37 60 8.90 27 14.6 27 5.72 28 5.58 45 9.50 3 3.51 23 0.00 1 0.00 1 0.00 1 5.23 39 15.1 45 8.28 42
MDP-Flow [26]37.5 0.13 3 0.78 4 0.00 1 1.05 14 6.71 16 0.64 45 2.31 22 8.09 26 1.26 79 1.35 57 12.5 65 0.28 50 10.4 40 16.8 42 7.29 41 5.39 38 16.9 48 4.89 60 0.00 1 0.00 1 0.00 1 8.69 84 21.5 79 12.1 83
FESL [72]37.8 0.23 57 1.35 58 0.00 1 1.71 52 9.38 44 0.54 38 2.22 19 7.40 18 0.31 21 1.08 24 9.18 35 0.16 9 7.97 15 13.0 13 4.61 18 7.68 78 16.5 43 5.87 89 0.09 93 0.00 1 0.17 87 4.96 31 12.4 19 8.31 43
DPOF [18]38.7 0.17 14 0.99 14 0.00 1 2.06 70 10.3 56 0.92 66 0.99 1 3.51 1 0.05 4 1.08 24 9.87 48 0.17 16 8.25 19 13.8 18 3.72 12 9.58 107 18.7 65 5.78 88 1.06 122 0.00 1 2.93 120 4.41 17 13.4 36 3.94 9
NL-TV-NCC [25]38.8 0.24 61 1.43 67 0.01 33 1.43 36 9.86 51 0.16 4 3.10 52 10.1 53 0.20 14 1.13 31 9.56 43 0.16 9 11.5 46 18.3 49 7.31 42 8.51 91 20.7 87 4.68 54 0.00 1 0.00 1 0.00 1 5.59 46 16.1 48 5.10 11
Classic+NL [31]39.3 0.23 57 1.34 57 0.01 33 1.93 65 11.7 64 0.80 57 2.57 37 8.35 31 0.58 49 1.22 44 9.29 39 0.24 36 8.66 24 14.1 22 5.48 27 7.52 76 16.3 35 5.42 76 0.00 1 0.00 1 0.00 1 5.06 34 12.9 28 8.47 49
Classic+CPF [83]41.2 0.21 43 1.23 43 0.01 33 1.47 38 8.95 40 0.37 23 2.73 40 8.84 37 0.35 28 1.14 32 9.32 40 0.23 31 8.60 23 14.1 22 5.23 25 8.01 85 16.4 38 5.26 72 0.20 105 0.00 1 0.86 104 4.71 24 12.0 17 8.34 44
Efficient-NL [60]41.3 0.22 50 1.29 51 0.00 1 1.25 24 7.99 27 0.48 31 2.92 46 9.31 41 0.31 21 1.23 46 9.67 47 0.31 55 8.23 18 13.5 17 4.72 19 8.45 90 17.1 50 6.06 91 0.12 98 0.00 1 0.54 96 4.71 24 11.6 16 7.75 31
Complementary OF [21]42.6 0.15 6 0.89 7 0.00 1 1.43 36 8.69 35 0.35 22 2.54 34 8.95 39 0.28 20 1.45 60 12.4 62 0.28 50 14.9 89 21.6 85 15.4 93 7.75 79 17.6 57 3.64 25 0.00 1 0.00 1 0.00 1 7.27 69 22.2 86 9.59 65
Aniso-Texture [82]42.7 0.16 10 0.94 10 0.02 50 1.16 21 8.46 31 0.50 32 5.29 81 14.6 82 1.10 73 0.87 13 6.69 11 0.17 16 14.2 82 20.8 69 14.7 88 5.50 43 18.6 64 4.62 52 0.00 1 0.00 1 0.00 1 6.99 63 18.1 58 10.3 73
SRR-TVOF-NL [91]42.9 0.19 25 1.05 21 0.03 55 3.08 92 13.8 88 1.68 90 3.97 63 12.4 63 0.84 57 1.22 44 9.35 41 0.20 22 11.5 46 16.7 41 12.3 80 2.79 7 13.5 15 3.68 26 0.00 1 0.00 1 0.00 1 5.69 48 13.1 31 10.1 71
Ramp [62]44.6 0.21 43 1.24 46 0.00 1 1.77 53 11.1 60 0.79 55 2.39 25 7.95 22 0.55 47 1.17 39 9.16 34 0.24 36 9.25 31 14.9 29 6.31 34 7.18 70 15.7 27 5.42 76 0.19 104 0.00 1 0.96 106 5.18 38 13.3 35 8.87 58
IROF-TV [53]45.0 0.22 50 1.24 46 0.01 33 1.83 58 11.9 67 0.87 63 2.96 49 9.37 42 0.50 38 1.70 69 14.6 74 0.46 68 9.51 35 15.4 36 6.49 36 4.78 32 22.9 98 4.55 49 0.00 1 0.00 1 0.00 1 5.17 37 14.4 43 8.73 54
OFH [38]45.5 0.17 14 1.00 16 0.00 1 1.80 55 9.80 49 0.66 47 4.49 72 13.2 74 0.47 37 1.62 66 13.6 69 0.35 58 13.2 68 20.8 69 10.2 69 3.85 22 20.4 84 2.41 10 0.00 1 0.00 1 0.00 1 7.06 66 21.6 81 9.31 61
ROF-ND [107]46.6 0.29 79 1.73 84 0.01 33 2.75 87 11.0 58 0.73 53 3.45 56 10.7 55 0.51 41 0.13 2 1.44 2 0.00 1 12.2 53 18.8 51 10.5 72 6.28 59 17.1 50 4.80 58 0.00 1 0.00 1 0.00 1 8.30 81 21.5 79 9.38 62
OAR-Flow [125]46.7 0.19 25 1.12 29 0.06 77 2.86 88 12.0 68 1.41 85 4.36 69 13.9 77 1.43 85 1.51 62 11.7 59 0.23 31 12.6 63 20.0 62 8.47 53 2.80 8 16.4 38 1.37 2 0.00 1 0.00 1 0.00 1 5.56 45 16.7 51 8.15 40
TCOF [69]48.3 0.18 20 1.06 22 0.00 1 1.56 45 9.24 43 0.60 42 4.63 74 12.8 70 0.89 60 1.34 56 12.4 62 0.20 22 12.4 56 19.6 57 9.52 63 6.02 52 14.3 19 5.03 65 0.34 114 0.00 1 1.23 111 4.94 29 13.6 38 8.00 38
TV-L1-MCT [64]48.7 0.22 50 1.33 56 0.00 1 1.64 49 9.85 50 0.52 34 2.86 45 9.38 43 0.32 24 1.14 32 8.89 27 0.24 36 10.6 42 16.4 40 9.05 58 8.81 97 17.2 54 5.12 68 0.08 92 0.00 1 0.84 103 5.93 54 14.3 42 10.1 71
ACK-Prior [27]49.4 0.15 6 0.91 9 0.00 1 1.21 23 7.63 22 0.19 8 2.41 27 8.36 32 0.35 28 1.25 49 10.5 53 0.18 19 12.4 56 18.0 46 11.2 73 9.00 102 19.4 75 6.39 97 0.17 102 0.00 1 1.01 108 9.72 91 20.1 69 13.3 88
2DHMM-SAS [92]49.9 0.20 31 1.21 39 0.00 1 1.80 55 10.4 57 0.63 44 4.15 64 11.3 57 0.86 58 1.24 47 9.61 46 0.25 47 9.18 29 14.8 28 6.44 35 8.98 101 17.3 55 4.98 62 0.13 99 0.00 1 0.69 98 5.55 44 14.2 41 9.22 59
CRTflow [80]50.6 0.18 20 0.99 14 0.03 55 1.70 50 9.09 41 0.59 41 4.56 73 12.8 70 0.68 52 2.03 85 15.1 79 0.64 76 12.4 56 20.0 62 8.26 50 4.42 27 24.0 103 3.47 22 0.00 1 0.00 1 0.00 1 7.88 75 22.0 85 10.4 75
PGM-C [120]50.7 0.20 31 1.19 35 0.07 86 1.87 60 11.8 66 0.85 61 2.76 41 9.82 49 0.92 64 1.99 82 15.1 79 0.74 85 13.1 66 21.2 72 9.19 60 3.52 19 19.2 72 2.47 11 0.00 1 0.00 1 0.00 1 6.38 58 19.5 66 8.65 51
Sparse Occlusion [54]51.9 0.24 61 1.38 61 0.06 77 1.27 26 7.83 24 0.45 26 3.42 54 11.1 56 0.33 25 1.52 64 11.4 57 0.28 50 10.9 43 17.6 44 6.76 39 4.10 25 16.2 33 4.27 41 0.03 80 0.17 124 0.15 85 5.90 51 15.7 46 8.69 53
SimpleFlow [49]52.0 0.22 50 1.31 52 0.00 1 1.78 54 11.0 58 0.82 59 4.30 68 12.5 66 1.22 78 1.16 37 9.20 36 0.24 36 9.84 39 15.8 38 6.94 40 8.51 91 17.3 55 6.11 94 0.09 93 0.00 1 0.39 92 5.01 33 14.1 40 8.00 38
CPM-Flow [116]52.9 0.21 43 1.23 43 0.07 86 1.92 64 12.1 69 0.89 64 2.64 39 9.39 44 0.92 64 1.96 78 14.8 75 0.72 83 13.1 66 21.2 72 8.92 56 4.84 33 19.1 71 3.40 20 0.00 1 0.00 1 0.00 1 6.92 62 20.5 71 9.43 63
ComplOF-FED-GPU [35]54.2 0.19 25 1.10 26 0.03 55 2.32 77 12.5 76 0.92 66 2.76 41 9.65 48 0.31 21 1.65 67 13.1 67 0.38 62 13.4 73 21.2 72 10.2 69 8.60 95 22.8 96 4.22 39 0.00 1 0.00 1 0.00 1 7.44 70 22.4 87 9.81 66
EpicFlow [102]56.5 0.20 31 1.17 32 0.07 86 1.91 63 12.1 69 0.90 65 3.70 59 12.7 68 0.89 60 1.96 78 14.8 75 0.74 85 13.4 73 21.3 76 9.97 65 6.71 64 19.3 73 3.90 32 0.00 1 0.00 1 0.00 1 7.03 64 20.1 69 9.91 67
S2D-Matching [84]57.5 0.33 90 1.92 93 0.06 77 2.04 68 12.4 73 0.79 55 4.15 64 13.0 72 1.09 72 1.09 26 8.04 18 0.24 36 9.82 38 15.9 39 6.68 38 7.85 82 16.4 38 5.58 83 0.20 105 0.00 1 0.96 106 4.94 29 12.6 22 8.81 56
AggregFlow [97]57.8 0.53 102 2.62 109 0.12 104 2.72 85 13.2 81 1.45 86 3.90 62 13.0 72 1.85 89 1.06 22 9.26 37 0.18 19 12.1 52 19.4 54 7.83 47 3.05 11 12.1 10 2.29 8 0.04 86 0.00 1 0.44 94 5.82 50 15.9 47 9.26 60
TF+OM [100]58.0 0.16 10 0.98 13 0.01 33 1.85 59 10.0 53 1.15 78 4.71 77 12.6 67 5.84 99 1.79 73 14.0 72 0.69 80 15.4 94 22.1 89 16.5 97 5.62 46 19.8 79 3.95 34 0.00 1 0.00 1 0.00 1 8.18 80 20.6 73 12.0 82
DeepFlow2 [108]58.2 0.26 71 1.53 72 0.08 93 2.56 82 11.7 64 1.30 83 3.73 61 11.5 59 0.90 62 1.99 82 15.1 79 0.65 78 12.3 54 19.5 56 9.07 59 4.57 29 18.7 65 2.81 15 0.00 1 0.00 1 0.00 1 8.01 79 21.0 74 10.8 77
Adaptive [20]59.6 0.29 79 1.72 82 0.06 77 2.04 68 12.5 76 1.13 76 5.51 85 14.7 83 0.68 52 1.83 74 13.9 71 0.59 75 12.7 64 19.9 59 10.1 66 7.15 69 18.9 69 4.08 38 0.00 1 0.00 1 0.00 1 6.38 58 16.4 49 8.82 57
Steered-L1 [118]63.9 0.10 1 0.59 1 0.01 33 1.01 11 6.84 17 0.52 34 2.76 41 9.44 45 0.91 63 1.78 71 14.9 77 0.51 72 14.0 81 20.5 66 15.2 91 9.02 103 19.9 80 6.57 101 1.07 123 0.00 1 7.19 124 12.1 101 22.9 90 20.6 107
RFlow [90]64.3 0.20 31 1.21 39 0.01 33 1.58 46 9.77 48 0.77 54 4.69 76 13.5 75 0.34 26 2.30 96 17.7 96 0.80 90 14.3 83 21.4 78 15.1 90 5.47 41 20.9 89 4.98 62 0.01 78 0.00 1 0.15 85 7.91 77 21.0 74 10.6 76
TriangleFlow [30]65.2 0.24 61 1.39 62 0.00 1 2.50 81 14.3 89 0.98 69 4.46 71 12.7 68 0.41 35 1.49 61 12.2 61 0.42 66 15.8 98 23.1 98 16.4 96 8.57 93 17.7 58 4.86 59 0.03 80 0.00 1 0.05 79 6.59 60 17.3 53 9.55 64
Aniso. Huber-L1 [22]65.4 0.29 79 1.66 78 0.06 77 2.43 80 13.1 80 1.12 75 5.68 86 14.3 81 1.27 82 1.56 65 12.4 62 0.30 54 12.4 56 19.2 53 10.1 66 4.70 31 17.1 50 4.45 45 0.17 102 0.00 1 0.89 105 6.28 56 16.7 51 8.80 55
DeepFlow [86]65.8 0.34 93 1.74 86 0.09 95 2.87 89 12.4 73 1.56 87 4.42 70 12.4 63 2.69 93 2.20 90 16.1 85 0.81 91 12.3 54 19.8 58 8.36 51 4.85 34 20.1 81 2.95 16 0.00 1 0.00 1 0.00 1 9.35 87 23.3 94 12.7 85
Occlusion-TV-L1 [63]66.0 0.27 75 1.55 74 0.06 77 1.99 67 12.1 69 1.14 77 5.42 83 14.9 85 0.93 66 1.83 74 14.0 72 0.49 70 13.6 75 21.2 72 11.5 75 6.13 55 19.6 78 5.37 75 0.00 1 0.00 1 0.00 1 9.19 86 23.4 95 11.5 80
CBF [12]67.5 0.18 20 1.09 25 0.01 33 2.37 78 12.9 78 1.94 93 4.28 67 12.0 60 1.13 76 1.97 81 16.1 85 0.66 79 13.3 72 20.5 66 12.7 83 5.89 50 18.8 68 4.73 55 0.45 118 0.00 1 1.33 114 7.67 72 18.9 61 12.7 85
LocallyOriented [52]68.5 0.49 101 2.66 110 0.06 77 3.28 93 15.4 92 1.91 92 6.59 95 16.9 97 1.20 77 1.29 52 10.1 49 0.52 74 14.6 85 21.5 80 12.6 81 7.79 80 16.7 46 4.33 43 0.00 1 0.00 1 0.00 1 7.87 74 19.1 64 11.1 79
OFRF [134]68.7 0.54 104 2.51 104 0.12 104 7.58 117 15.8 94 7.13 121 7.71 103 15.0 86 5.91 101 1.78 71 9.27 38 1.09 99 11.3 45 18.2 48 6.18 33 6.74 67 13.5 15 2.79 14 0.00 1 0.00 1 0.00 1 12.7 103 19.0 62 27.9 117
FlowNet2 [122]70.6 0.74 113 3.32 116 0.12 104 5.00 107 17.2 99 2.46 100 6.13 91 15.0 86 5.85 100 1.29 52 10.3 52 0.40 65 13.2 68 21.6 85 8.11 48 7.27 73 17.7 58 6.06 91 0.00 1 0.00 1 0.05 79 5.52 43 17.5 55 3.70 7
TV-L1-improved [17]70.8 0.25 68 1.46 69 0.07 86 1.82 57 11.1 60 1.02 70 5.46 84 15.0 86 1.32 83 2.26 93 16.4 88 0.79 89 13.8 77 21.5 80 11.8 76 9.40 104 23.6 102 6.48 98 0.00 1 0.00 1 0.00 1 7.89 76 21.3 78 10.3 73
DF-Auto [115]70.8 0.61 108 2.33 101 0.10 100 4.04 100 15.3 91 2.49 101 6.59 95 14.8 84 6.66 103 1.84 76 15.0 78 0.51 72 14.9 89 21.5 80 16.8 99 3.47 18 16.7 46 3.82 31 0.00 1 0.00 1 0.00 1 7.99 78 19.5 66 11.6 81
TriFlow [95]71.3 0.27 75 1.62 76 0.01 33 2.27 76 13.2 81 1.24 80 7.10 100 16.9 97 7.37 106 1.31 55 11.7 59 0.43 67 17.3 106 23.4 104 20.6 108 3.24 14 15.8 28 3.91 33 4.67 130 0.00 1 18.1 130 6.86 61 18.1 58 7.89 34
EPMNet [133]72.2 0.64 111 3.15 113 0.09 95 5.25 108 18.8 105 2.74 105 5.08 80 14.0 78 2.76 94 1.51 62 13.3 68 0.28 50 13.2 68 21.6 85 8.11 48 7.27 73 17.7 58 6.06 91 0.00 1 0.00 1 0.02 78 7.03 64 23.1 91 3.19 5
CLG-TV [48]72.7 0.31 86 1.67 80 0.06 77 2.10 72 13.0 79 0.92 66 5.33 82 14.2 80 1.04 70 1.71 70 13.7 70 0.38 62 13.9 79 21.4 78 12.0 77 5.20 37 22.7 95 5.07 66 0.20 105 0.00 1 1.01 108 7.85 73 19.4 65 9.91 67
Bartels [41]74.5 0.24 61 1.40 63 0.01 33 1.42 35 8.88 38 0.62 43 3.51 57 12.4 63 1.00 69 2.26 93 15.8 83 0.95 95 15.5 95 23.3 102 15.8 95 7.99 84 23.0 99 5.20 70 0.33 111 0.00 1 1.92 117 9.95 93 24.0 96 13.7 91
Brox et al. [5]74.5 0.25 68 1.45 68 0.03 55 2.22 75 13.7 87 1.07 72 3.44 55 11.4 58 0.68 52 2.20 90 16.7 92 0.72 83 17.8 110 23.4 104 24.6 116 8.90 100 24.6 105 6.63 102 0.00 1 0.00 1 0.00 1 10.6 96 25.9 103 14.8 95
Fusion [6]75.0 0.24 61 1.41 65 0.05 72 1.13 19 8.57 33 0.47 29 2.45 30 8.15 27 0.93 66 2.12 89 18.3 102 1.21 100 16.2 102 23.1 98 19.6 106 6.72 66 18.7 65 5.67 85 0.07 90 0.15 122 0.10 83 10.4 95 24.9 101 14.6 94
SegOF [10]75.5 0.24 61 1.41 65 0.05 72 4.72 105 21.4 109 3.68 108 9.28 108 19.5 107 4.83 96 1.05 21 7.42 15 0.78 88 20.7 120 27.1 118 28.6 121 10.4 110 26.0 108 7.80 113 0.00 1 0.00 1 0.00 1 7.25 68 20.0 68 7.44 28
Classic++ [32]75.5 0.26 71 1.50 71 0.07 86 2.08 71 12.2 72 1.03 71 4.84 79 14.0 78 1.26 79 2.07 87 16.1 85 0.64 76 13.9 79 22.5 92 10.1 66 6.11 54 23.1 100 5.28 73 0.06 88 0.00 1 0.34 90 8.66 83 21.7 82 11.0 78
Rannacher [23]77.5 0.33 90 1.95 94 0.07 86 2.21 74 13.4 84 1.29 82 5.78 87 15.6 92 1.48 86 2.51 100 17.8 97 0.95 95 14.5 84 22.5 92 12.2 79 9.72 108 24.8 106 6.66 103 0.00 1 0.00 1 0.00 1 7.50 71 21.1 77 9.97 69
SuperFlow [81]78.5 0.45 97 1.75 87 0.10 100 3.01 91 13.4 84 2.04 94 6.82 99 15.2 90 8.24 109 1.96 78 17.0 94 0.50 71 15.6 97 22.2 90 19.2 105 5.87 49 20.6 85 5.46 79 0.00 1 0.00 1 0.00 1 10.1 94 24.6 99 13.4 89
Local-TV-L1 [65]79.5 0.53 102 2.10 95 0.12 104 4.96 106 18.0 103 3.44 107 8.54 106 16.7 96 6.16 102 2.47 99 18.5 104 1.01 98 12.5 60 19.9 59 9.65 64 5.53 44 19.5 76 4.95 61 0.00 1 0.00 1 0.00 1 13.4 107 24.2 97 27.1 116
BriefMatch [124]79.7 0.16 10 0.94 10 0.01 33 1.97 66 9.60 46 1.10 74 2.79 44 9.56 46 0.54 45 2.11 88 15.6 82 0.70 81 14.6 85 21.5 80 15.2 91 10.4 110 22.0 93 8.36 116 2.52 129 0.62 132 13.7 129 13.6 110 25.5 102 22.0 111
SIOF [67]80.0 0.42 96 2.28 97 0.08 93 3.55 96 17.7 102 2.05 95 8.15 105 17.9 104 7.78 108 2.41 98 17.9 98 1.00 97 15.5 95 22.7 95 17.8 103 4.67 30 19.5 76 4.77 57 0.00 1 0.00 1 0.00 1 9.35 87 21.8 83 17.7 101
Second-order prior [8]82.5 0.26 71 1.53 72 0.05 72 2.88 90 15.5 93 1.60 88 5.87 88 15.3 91 1.11 75 2.21 92 17.2 95 0.94 94 13.8 77 21.3 76 12.6 81 7.46 75 27.8 114 5.71 86 0.16 101 0.00 1 0.76 100 8.65 82 21.0 74 13.9 93
p-harmonic [29]82.6 0.29 79 1.73 84 0.02 50 2.16 73 13.2 81 1.33 84 5.87 88 15.8 93 1.59 87 2.55 101 17.9 98 1.49 103 17.0 104 22.7 95 23.3 113 4.53 28 21.5 92 4.53 48 0.03 80 0.02 121 0.00 1 9.65 90 23.2 93 15.0 96
Dynamic MRF [7]84.4 0.30 85 1.79 89 0.04 69 2.37 78 14.9 90 1.09 73 4.81 78 15.0 86 0.86 58 2.66 102 18.2 101 1.25 101 17.6 108 25.7 116 18.1 104 10.9 115 30.4 119 7.45 109 0.00 1 0.00 1 0.00 1 15.1 113 29.9 118 21.9 110
Shiralkar [42]85.0 0.28 77 1.66 78 0.02 50 3.80 98 19.8 108 1.78 91 6.50 93 16.1 95 1.26 79 3.17 106 20.8 108 1.56 105 16.3 103 25.1 114 14.5 87 12.4 119 29.4 117 6.20 95 0.00 1 0.00 1 0.00 1 12.6 102 30.1 119 13.8 92
F-TV-L1 [15]85.2 0.46 98 2.58 106 0.07 86 4.05 101 16.2 96 2.21 96 6.59 95 15.9 94 1.39 84 2.35 97 17.9 98 0.88 93 13.7 76 21.5 80 11.4 74 7.53 77 21.1 91 4.75 56 0.03 80 0.17 124 0.05 79 7.15 67 20.5 71 7.39 27
CNN-flow-warp+ref [117]86.3 0.33 90 1.91 92 0.09 95 2.72 85 12.4 73 2.32 98 6.77 98 18.9 106 2.09 90 2.28 95 16.4 88 0.82 92 17.7 109 23.9 108 22.8 112 9.40 104 24.3 104 6.73 104 0.00 1 0.00 1 0.00 1 14.0 111 26.8 109 20.2 106
GraphCuts [14]89.0 0.29 79 1.67 80 0.16 112 6.77 114 22.4 113 3.81 109 7.73 104 17.2 100 9.04 110 1.86 77 16.8 93 0.46 68 15.8 98 24.0 109 14.1 86 20.2 128 22.8 96 12.5 125 0.00 1 0.00 1 0.00 1 13.4 107 27.0 112 23.4 113
StereoOF-V1MT [119]90.2 0.41 94 2.35 102 0.04 69 4.27 103 21.6 110 1.66 89 6.25 92 17.7 102 0.50 38 3.13 105 23.2 112 1.41 102 19.4 117 27.9 122 20.7 109 11.6 117 32.5 121 7.60 111 0.00 1 0.00 1 0.00 1 16.7 117 32.8 121 21.3 108
Ad-TV-NDC [36]91.8 0.79 114 2.68 111 0.12 104 13.0 123 26.5 117 12.9 123 12.9 116 22.0 111 9.24 111 5.02 111 20.3 107 4.82 111 13.2 68 20.5 66 9.43 62 6.17 57 20.3 83 5.07 66 0.03 80 0.00 1 0.00 1 20.5 122 26.9 110 40.8 128
HBpMotionGpu [43]92.1 0.80 115 2.79 112 0.18 113 5.57 109 23.8 116 4.00 110 13.1 117 27.8 122 11.6 117 2.05 86 16.4 88 0.74 85 17.9 111 25.1 114 22.3 111 6.69 62 21.0 90 6.04 90 0.00 1 0.00 1 0.00 1 14.1 112 27.7 113 25.1 114
Filter Flow [19]93.1 0.58 107 2.59 107 0.11 103 4.48 104 19.7 106 2.66 104 12.1 111 23.7 114 13.5 121 14.5 121 30.4 118 15.0 121 18.7 116 23.7 107 27.5 120 8.11 86 20.7 87 6.48 98 0.00 1 0.00 1 0.00 1 11.0 98 21.9 84 17.2 99
StereoFlow [44]93.5 2.82 131 6.92 130 1.29 130 21.5 129 42.6 132 13.8 124 20.5 130 33.3 131 20.4 126 20.6 128 51.2 130 18.6 126 14.9 89 22.6 94 13.7 85 3.89 23 18.9 69 3.74 28 0.00 1 0.00 1 0.00 1 11.3 100 25.9 103 18.7 104
Modified CLG [34]95.2 0.62 109 2.54 105 0.12 104 3.52 95 18.7 104 2.59 103 12.2 113 23.5 113 12.5 119 3.25 107 20.1 106 2.03 107 18.6 115 25.0 113 25.0 117 8.86 99 26.9 113 7.14 107 0.00 1 0.00 1 0.00 1 13.4 107 29.8 117 21.8 109
2bit-BM-tele [98]95.7 0.54 104 2.59 107 0.20 114 2.58 83 16.3 97 1.26 81 6.04 90 17.8 103 2.26 91 2.77 104 19.7 105 1.50 104 15.8 98 23.3 102 16.5 97 8.58 94 22.4 94 5.62 84 1.37 125 0.00 1 5.84 123 10.7 97 24.8 100 16.5 98
Learning Flow [11]96.5 0.32 88 1.89 90 0.01 33 2.61 84 16.0 95 1.21 79 6.52 94 17.9 104 1.65 88 4.69 110 24.9 115 3.14 110 20.8 121 27.4 121 26.9 119 10.9 115 28.6 116 7.90 114 0.10 97 0.00 1 0.64 97 13.3 106 28.5 116 18.1 102
FlowNetS+ft+v [112]97.6 0.31 86 1.76 88 0.09 95 3.39 94 13.5 86 2.49 101 7.24 101 16.9 97 5.12 97 3.32 108 18.3 102 2.07 108 17.1 105 23.2 101 20.3 107 6.23 58 23.2 101 5.50 82 0.35 115 0.52 129 1.50 116 8.79 85 23.1 91 13.6 90
SPSA-learn [13]98.4 0.86 117 3.30 115 0.28 119 6.02 111 22.0 111 4.09 111 10.6 109 21.3 109 9.82 115 5.83 114 22.9 110 5.66 115 17.9 111 23.4 104 23.4 114 10.2 109 25.0 107 8.09 115 0.00 1 0.00 1 0.00 1 15.9 116 28.1 114 23.3 112
IAOF2 [51]98.9 0.47 100 2.28 97 0.33 120 3.77 97 16.3 97 2.22 97 7.40 102 17.2 100 7.06 105 14.7 122 29.4 117 16.6 123 15.2 93 23.0 97 14.7 88 10.5 112 20.6 85 7.03 106 0.32 110 0.00 1 2.00 119 11.2 99 22.6 89 15.4 97
UnFlow [129]99.6 1.88 126 6.59 128 0.87 127 6.75 113 27.2 118 4.57 113 12.5 115 27.9 123 7.37 106 5.65 113 21.0 109 5.26 113 22.5 124 30.2 125 26.4 118 9.48 106 30.5 120 7.32 108 0.00 1 0.00 1 0.00 1 9.58 89 26.9 110 12.3 84
LDOF [28]99.9 0.41 94 2.31 100 0.09 95 3.85 99 17.3 100 2.32 98 4.68 75 13.5 75 2.59 92 3.97 109 24.8 114 2.14 109 16.1 101 23.1 98 17.6 101 8.24 89 26.0 108 6.50 100 0.33 111 0.34 126 1.95 118 9.77 92 26.7 107 12.9 87
IAOF [50]101.7 0.46 98 2.11 96 0.10 100 6.63 112 19.7 106 4.61 114 13.8 119 23.3 112 9.33 112 9.91 116 23.2 112 11.3 118 14.8 88 22.2 90 15.5 94 10.6 113 26.8 112 6.99 105 0.05 87 0.00 1 0.42 93 18.0 120 24.4 98 35.4 125
Nguyen [33]102.4 0.83 116 3.37 117 0.22 115 7.27 116 22.1 112 6.46 117 15.4 122 26.8 120 12.4 118 17.6 125 30.4 118 20.2 128 18.5 114 24.7 111 24.5 115 8.82 98 28.5 115 8.81 118 0.00 1 0.00 1 0.00 1 18.9 121 31.7 120 29.4 119
BlockOverlap [61]102.6 0.62 109 2.30 99 0.14 111 4.11 102 17.6 101 3.02 106 9.12 107 19.6 108 6.97 104 2.74 103 16.5 91 1.72 106 14.7 87 20.9 71 16.8 99 7.89 83 19.3 73 6.25 96 2.12 126 0.52 129 10.9 128 15.2 114 22.4 87 32.3 123
GroupFlow [9]103.2 0.56 106 3.20 114 0.05 72 9.79 120 32.3 124 7.11 120 11.4 110 24.6 115 9.68 114 2.01 84 16.0 84 0.70 81 19.8 118 29.9 124 12.0 77 15.2 125 32.5 121 15.4 127 0.33 111 0.00 1 1.11 110 13.2 105 28.4 115 17.2 99
2D-CLG [1]105.5 1.77 125 6.22 126 0.51 125 5.91 110 22.4 113 4.54 112 16.4 123 28.6 125 18.1 125 17.9 126 35.8 122 19.9 127 20.4 119 25.8 117 29.3 122 12.0 118 29.6 118 11.4 122 0.00 1 0.00 1 0.00 1 17.7 119 32.8 121 26.2 115
Heeger++ [104]106.6 0.95 118 4.26 120 0.26 118 11.8 122 39.5 130 6.54 118 12.3 114 24.7 117 3.51 95 10.7 117 37.1 124 8.97 116 30.7 129 36.7 129 39.2 128 21.4 130 46.3 131 18.3 130 0.00 1 0.00 1 0.00 1 24.4 125 37.0 124 31.9 121
FFV1MT [106]109.8 1.42 121 6.80 129 0.25 116 10.3 121 35.9 127 6.76 119 18.0 124 30.0 127 16.5 123 17.2 124 51.3 131 16.2 122 31.5 130 37.1 130 43.2 131 20.9 129 44.0 130 17.2 128 0.00 1 0.00 1 0.00 1 24.4 125 37.0 124 31.9 121
TI-DOFE [24]109.9 1.58 123 5.19 123 0.36 122 16.8 125 34.3 125 17.7 126 19.3 129 30.2 129 21.6 128 23.3 129 39.1 126 27.6 129 21.1 122 27.1 118 29.5 123 14.4 123 35.1 125 12.1 124 0.00 1 0.00 1 0.00 1 27.2 129 40.8 128 41.2 129
Black & Anandan [4]111.1 0.68 112 2.46 103 0.13 110 7.01 115 23.6 115 4.65 115 12.1 111 21.6 110 9.40 113 5.45 112 23.1 111 4.84 112 17.5 107 24.3 110 21.6 110 10.6 113 26.6 111 7.49 110 0.43 116 0.15 122 1.31 113 12.7 103 26.7 107 18.8 105
Horn & Schunck [3]112.3 1.05 119 4.22 119 0.25 116 7.74 118 29.1 121 5.17 116 13.6 118 24.6 115 10.8 116 12.7 119 36.1 123 12.8 119 21.4 123 27.3 120 30.9 125 13.9 122 35.2 126 11.6 123 0.03 80 0.00 1 0.17 87 22.3 124 37.9 126 31.7 120
SILK [79]115.8 1.05 119 4.27 121 0.44 123 9.69 119 27.9 119 8.93 122 15.2 121 26.9 121 13.1 120 6.14 115 25.9 116 5.57 114 23.0 125 29.2 123 34.1 126 12.6 120 33.9 123 9.78 120 0.81 121 0.00 1 3.50 121 21.5 123 33.3 123 34.5 124
HCIC-L [99]117.1 1.95 127 6.24 127 0.99 129 28.7 131 32.2 123 35.8 131 18.6 127 26.2 118 25.7 131 25.4 132 46.6 129 27.7 130 15.1 92 21.9 88 12.7 83 8.77 96 20.2 82 9.24 119 6.40 132 0.49 128 23.0 132 15.3 115 26.4 106 18.4 103
Adaptive flow [45]120.5 1.75 124 5.07 122 0.34 121 18.4 127 28.3 120 18.5 128 18.5 125 28.6 125 22.9 129 13.3 120 37.4 125 13.9 120 17.9 111 24.7 111 17.7 102 12.9 121 26.2 110 8.68 117 5.20 131 0.61 131 22.8 131 16.7 117 26.0 105 28.2 118
PGAM+LK [55]120.5 2.98 132 6.17 125 6.36 135 16.8 125 36.2 128 17.8 127 14.7 120 26.5 119 14.5 122 19.1 127 53.9 132 18.3 125 23.1 126 30.6 126 29.9 124 14.4 123 36.8 127 11.1 121 1.07 123 0.00 1 4.16 122 25.9 127 40.1 127 40.3 127
SLK [47]120.6 1.44 122 5.58 124 0.49 124 14.4 124 35.8 126 14.8 125 18.5 125 30.1 128 21.4 127 24.6 130 35.7 121 27.7 130 26.3 128 31.9 127 39.4 129 15.6 126 38.8 128 13.6 126 0.55 120 0.00 1 1.35 115 31.7 130 41.0 129 49.0 130
FOLKI [16]122.4 1.98 128 7.18 131 0.87 127 24.5 130 36.3 129 30.3 130 18.7 128 32.4 130 16.5 123 15.2 123 33.2 120 18.1 124 26.0 127 32.3 128 36.0 127 17.7 127 40.6 129 17.9 129 2.33 128 0.00 1 10.6 126 33.9 131 43.6 130 52.7 131
Periodicity [78]123.0 2.36 130 9.12 132 0.79 126 19.1 128 40.7 131 20.6 129 28.2 132 35.2 132 26.8 132 11.2 118 40.6 127 10.3 117 42.3 132 55.4 132 41.1 130 31.7 131 56.3 132 27.7 131 0.54 119 0.00 1 7.78 125 26.1 128 51.0 131 36.2 126
Pyramid LK [2]129.2 2.31 129 4.20 118 3.47 134 31.6 132 32.0 122 40.4 132 21.0 131 28.5 124 24.0 130 24.6 130 43.7 128 28.6 132 37.5 131 46.6 131 43.7 132 33.1 132 34.2 124 31.3 132 2.17 127 0.47 127 10.7 127 46.5 132 57.3 132 67.2 132
AdaConv-v1 [126]132.9 6.16 133 11.8 133 2.11 131 91.0 133 93.3 133 87.2 133 83.4 133 79.4 133 87.3 133 47.3 133 64.4 133 46.2 133 89.6 133 93.2 133 73.3 133 69.7 133 60.5 133 67.1 133 41.7 133 14.2 133 92.5 133 99.6 133 98.7 133 100.0 133
SepConv-v1 [127]132.9 6.16 133 11.8 133 2.11 131 91.0 133 93.3 133 87.2 133 83.4 133 79.4 133 87.3 133 47.3 133 64.4 133 46.2 133 89.6 133 93.2 133 73.3 133 69.7 133 60.5 133 67.1 133 41.7 133 14.2 133 92.5 133 99.6 133 98.7 133 100.0 133
SuperSlomo [132]132.9 6.16 133 11.8 133 2.11 131 91.0 133 93.3 133 87.2 133 83.4 133 79.4 133 87.3 133 47.3 133 64.4 133 46.2 133 89.6 133 93.2 133 73.3 133 69.7 133 60.5 133 67.1 133 41.7 133 14.2 133 92.5 133 99.6 133 98.7 133 100.0 133
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.