Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
R5.0 angle error |
avg. |
Army (Hidden texture) GT im0 im1 |
Mequon (Hidden texture) GT im0 im1 |
Schefflera (Hidden texture) GT im0 im1 |
Wooden (Hidden texture) GT im0 im1 |
Grove (Synthetic) GT im0 im1 |
Urban (Synthetic) GT im0 im1 |
Yosemite (Synthetic) GT im0 im1 |
Teddy (Stereo) GT im0 im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
NNF-Local [87] | 10.8 | 7.69 2 | 26.2 5 | 3.54 2 | 7.19 14 | 30.7 27 | 6.11 20 | 5.88 5 | 19.3 8 | 4.53 14 | 4.01 10 | 23.9 16 | 2.00 12 | 11.7 1 | 16.4 3 | 5.52 3 | 10.4 15 | 29.7 9 | 9.30 10 | 5.25 17 | 20.0 24 | 2.61 7 | 1.88 7 | 6.47 27 | 0.19 1 |
MDP-Flow2 [68] | 12.0 | 10.3 20 | 30.4 19 | 6.57 20 | 5.28 2 | 23.9 3 | 4.13 3 | 5.46 3 | 17.6 3 | 3.58 7 | 4.49 18 | 25.3 21 | 2.11 15 | 15.8 21 | 21.4 21 | 10.2 26 | 10.6 16 | 29.9 10 | 9.87 16 | 4.44 8 | 19.3 17 | 2.81 8 | 1.39 2 | 4.82 5 | 1.11 3 |
OFLAF [77] | 12.8 | 8.96 9 | 27.9 9 | 4.57 8 | 7.36 17 | 26.4 8 | 6.68 22 | 4.80 2 | 14.9 2 | 3.37 6 | 4.43 17 | 21.2 8 | 2.81 26 | 13.4 7 | 19.0 10 | 7.08 7 | 11.4 25 | 28.0 3 | 9.28 9 | 5.35 19 | 19.1 16 | 3.15 10 | 2.47 16 | 5.73 18 | 5.50 32 |
NN-field [71] | 13.9 | 8.65 5 | 28.3 10 | 4.00 4 | 8.38 26 | 33.1 41 | 7.44 28 | 5.86 4 | 19.0 7 | 4.53 14 | 3.15 2 | 21.4 10 | 1.25 3 | 12.0 4 | 16.9 5 | 5.41 2 | 6.58 2 | 20.2 1 | 3.45 1 | 8.64 47 | 23.6 52 | 2.88 9 | 2.47 16 | 8.48 38 | 0.20 2 |
PMMST [114] | 19.5 | 12.9 46 | 32.6 31 | 8.45 42 | 10.2 42 | 30.5 24 | 10.7 58 | 7.39 15 | 22.2 12 | 6.31 31 | 3.87 9 | 13.5 1 | 2.73 23 | 14.0 10 | 18.7 9 | 7.52 8 | 10.9 22 | 28.9 6 | 9.95 17 | 4.99 14 | 20.8 29 | 3.18 11 | 1.52 3 | 3.87 2 | 1.12 4 |
ComponentFusion [96] | 22.0 | 8.86 8 | 28.7 13 | 5.91 14 | 6.30 5 | 24.2 4 | 5.98 15 | 6.79 10 | 21.6 10 | 4.99 20 | 4.11 11 | 24.4 17 | 2.04 14 | 16.2 29 | 22.0 26 | 11.3 37 | 13.4 41 | 40.4 57 | 12.4 56 | 7.66 39 | 21.3 35 | 5.22 33 | 2.05 8 | 5.21 9 | 3.61 16 |
ALD-Flow [66] | 22.4 | 8.44 4 | 27.6 8 | 4.09 5 | 6.49 7 | 27.2 12 | 5.04 9 | 7.66 20 | 24.1 22 | 3.72 9 | 4.58 20 | 27.1 32 | 2.01 13 | 16.0 24 | 22.7 34 | 8.55 12 | 9.39 8 | 33.3 21 | 8.46 8 | 7.21 36 | 18.5 10 | 17.3 85 | 4.06 47 | 11.1 52 | 5.94 40 |
HAST [109] | 22.5 | 7.13 1 | 21.8 1 | 3.37 1 | 7.28 15 | 26.1 7 | 6.10 19 | 3.86 1 | 12.2 1 | 0.97 1 | 3.85 8 | 21.3 9 | 1.50 4 | 11.7 1 | 16.5 4 | 4.64 1 | 15.1 63 | 35.5 32 | 14.0 67 | 19.4 87 | 36.3 95 | 39.0 115 | 1.24 1 | 3.55 1 | 1.32 5 |
NNF-EAC [103] | 23.5 | 10.9 28 | 31.8 26 | 6.97 21 | 6.64 9 | 26.4 8 | 5.65 11 | 6.61 9 | 20.7 9 | 4.44 13 | 5.48 39 | 27.1 32 | 2.97 31 | 16.5 32 | 22.3 30 | 11.1 34 | 12.1 29 | 30.7 11 | 9.97 18 | 6.42 27 | 21.4 37 | 3.94 22 | 2.95 29 | 7.51 33 | 4.63 25 |
nLayers [57] | 23.5 | 8.66 6 | 25.4 3 | 4.54 6 | 13.0 80 | 32.1 34 | 13.7 87 | 7.74 22 | 21.8 11 | 8.85 60 | 3.29 4 | 18.2 2 | 1.89 9 | 11.8 3 | 16.2 2 | 6.65 6 | 12.2 30 | 28.4 4 | 10.3 20 | 8.59 46 | 21.5 39 | 4.98 29 | 2.36 14 | 5.74 19 | 5.08 28 |
LME [70] | 23.6 | 9.71 15 | 29.0 15 | 6.46 19 | 5.49 4 | 22.8 2 | 4.79 7 | 8.62 36 | 22.4 13 | 11.2 71 | 4.73 21 | 28.3 46 | 2.35 18 | 16.5 32 | 21.9 24 | 12.6 50 | 10.7 17 | 34.0 25 | 9.81 15 | 5.57 20 | 21.3 35 | 3.87 20 | 2.40 15 | 6.32 24 | 4.52 23 |
TC/T-Flow [76] | 24.5 | 9.15 10 | 32.1 28 | 3.69 3 | 6.89 12 | 31.2 30 | 4.32 4 | 7.32 14 | 23.1 17 | 4.08 10 | 5.14 30 | 27.2 35 | 2.80 25 | 15.6 20 | 21.9 24 | 9.71 20 | 8.63 6 | 29.2 7 | 8.40 6 | 6.72 29 | 20.2 26 | 19.7 99 | 3.86 45 | 9.43 42 | 6.28 46 |
WLIF-Flow [93] | 25.6 | 9.40 14 | 27.1 6 | 6.06 16 | 10.0 39 | 33.0 39 | 9.71 42 | 7.26 13 | 22.4 13 | 5.90 30 | 4.53 19 | 23.7 14 | 2.56 22 | 16.1 25 | 22.3 30 | 11.3 37 | 12.8 33 | 33.2 20 | 10.4 23 | 6.85 31 | 18.8 14 | 7.36 46 | 2.80 26 | 6.48 28 | 5.62 35 |
FC-2Layers-FF [74] | 26.6 | 9.97 16 | 28.7 13 | 7.96 31 | 10.4 44 | 35.3 49 | 9.95 44 | 6.11 7 | 18.1 6 | 6.82 35 | 4.12 12 | 20.9 6 | 2.48 21 | 13.3 6 | 17.7 6 | 9.47 17 | 13.5 42 | 32.6 15 | 11.3 35 | 14.0 71 | 26.0 65 | 12.5 66 | 1.84 5 | 4.18 3 | 4.53 24 |
RNLOD-Flow [121] | 26.9 | 7.93 3 | 24.8 2 | 5.41 12 | 8.33 25 | 31.7 31 | 6.84 24 | 7.47 16 | 23.3 18 | 4.60 16 | 3.62 6 | 21.1 7 | 1.66 7 | 14.4 12 | 21.0 15 | 7.80 9 | 12.7 32 | 32.9 16 | 12.2 55 | 17.4 83 | 34.4 90 | 20.7 101 | 2.55 19 | 5.57 16 | 5.30 30 |
Layers++ [37] | 27.7 | 10.2 18 | 29.1 16 | 8.58 45 | 10.8 49 | 30.6 25 | 11.0 64 | 5.90 6 | 17.7 4 | 6.34 32 | 3.40 5 | 18.2 2 | 1.66 7 | 12.2 5 | 16.0 1 | 9.69 19 | 13.9 47 | 33.6 22 | 11.9 49 | 13.9 70 | 27.9 70 | 8.74 51 | 2.33 13 | 4.94 6 | 5.70 38 |
FESL [72] | 28.8 | 8.67 7 | 25.6 4 | 4.73 9 | 13.6 85 | 39.4 84 | 12.9 82 | 8.22 30 | 24.3 26 | 7.10 39 | 3.76 7 | 20.3 5 | 2.12 16 | 14.1 11 | 20.1 12 | 9.08 14 | 11.2 24 | 31.0 12 | 9.80 14 | 11.3 56 | 30.4 78 | 7.66 48 | 2.10 9 | 5.40 12 | 2.40 8 |
SVFilterOh [111] | 29.1 | 12.7 44 | 28.4 11 | 8.58 45 | 9.41 34 | 29.1 19 | 8.31 33 | 6.39 8 | 17.7 4 | 5.05 22 | 3.23 3 | 18.8 4 | 0.95 2 | 14.9 15 | 20.9 14 | 6.51 5 | 13.2 37 | 32.1 14 | 11.6 42 | 22.0 93 | 46.5 118 | 30.5 110 | 1.61 4 | 4.97 8 | 2.45 10 |
TC-Flow [46] | 30.2 | 9.24 11 | 30.9 22 | 5.24 11 | 5.48 3 | 25.7 6 | 4.01 2 | 7.25 12 | 23.3 18 | 2.66 3 | 5.52 40 | 28.4 47 | 3.26 37 | 16.7 35 | 23.9 40 | 9.52 18 | 11.7 26 | 36.8 37 | 11.5 41 | 6.69 28 | 21.4 37 | 19.0 96 | 4.21 49 | 10.6 49 | 6.91 58 |
OAR-Flow [125] | 32.0 | 10.8 26 | 34.0 40 | 6.23 17 | 8.94 29 | 31.9 32 | 7.53 29 | 10.4 51 | 30.3 53 | 7.58 48 | 5.60 44 | 25.9 27 | 3.04 33 | 17.0 36 | 24.0 41 | 9.35 15 | 8.62 5 | 33.0 17 | 7.87 4 | 3.37 4 | 14.6 3 | 5.54 37 | 4.80 56 | 10.4 48 | 9.44 73 |
Efficient-NL [60] | 32.9 | 9.31 12 | 27.5 7 | 5.65 13 | 12.1 72 | 38.1 69 | 11.2 66 | 8.07 29 | 24.1 22 | 6.69 34 | 5.39 36 | 25.9 27 | 3.51 47 | 14.9 15 | 21.1 17 | 9.39 16 | 14.0 50 | 35.2 30 | 11.1 32 | 11.5 57 | 25.7 63 | 6.90 43 | 2.19 11 | 5.45 14 | 1.94 7 |
AGIF+OF [85] | 33.0 | 10.4 21 | 29.4 17 | 7.42 24 | 12.4 73 | 37.5 62 | 12.4 77 | 7.91 27 | 24.3 26 | 7.24 41 | 4.84 24 | 23.8 15 | 2.91 28 | 14.8 14 | 20.6 13 | 9.72 21 | 13.2 37 | 36.5 35 | 10.5 25 | 7.06 33 | 20.8 29 | 7.54 47 | 3.02 34 | 6.27 22 | 6.37 48 |
IROF++ [58] | 33.4 | 10.2 18 | 30.9 22 | 7.02 22 | 11.1 56 | 38.1 69 | 10.7 58 | 8.32 34 | 25.1 31 | 7.61 49 | 5.83 47 | 28.0 43 | 4.08 56 | 15.4 19 | 21.3 19 | 9.83 22 | 13.6 43 | 38.0 46 | 11.3 35 | 5.83 21 | 20.8 29 | 1.97 6 | 2.32 12 | 5.71 17 | 4.87 27 |
PMF [73] | 34.0 | 11.6 37 | 29.9 18 | 4.55 7 | 7.81 20 | 30.2 21 | 6.00 16 | 7.17 11 | 23.3 18 | 3.21 5 | 4.88 26 | 23.1 12 | 2.42 19 | 13.6 8 | 18.5 7 | 6.49 4 | 16.1 71 | 42.7 67 | 15.4 77 | 27.2 107 | 43.5 115 | 28.9 107 | 2.15 10 | 4.96 7 | 4.81 26 |
PH-Flow [101] | 34.5 | 10.9 28 | 32.6 31 | 7.94 30 | 10.9 51 | 37.4 60 | 10.5 52 | 7.56 19 | 22.8 16 | 7.74 52 | 5.75 46 | 27.2 35 | 4.04 54 | 14.4 12 | 19.8 11 | 8.81 13 | 13.0 35 | 33.6 22 | 11.1 32 | 12.7 64 | 23.1 48 | 17.6 87 | 1.84 5 | 4.19 4 | 4.50 22 |
Classic+CPF [83] | 35.7 | 10.9 28 | 31.7 25 | 7.88 29 | 11.5 62 | 37.9 66 | 10.9 62 | 8.27 32 | 25.1 31 | 7.51 47 | 5.05 28 | 25.8 26 | 3.16 35 | 15.1 17 | 21.0 15 | 10.6 27 | 13.1 36 | 34.6 28 | 10.3 20 | 9.87 51 | 22.0 44 | 13.1 72 | 2.68 22 | 5.85 20 | 5.53 33 |
COFM [59] | 36.1 | 10.1 17 | 32.0 27 | 7.63 25 | 8.06 22 | 30.4 23 | 7.17 25 | 8.93 40 | 25.9 37 | 8.04 56 | 4.17 13 | 24.9 19 | 1.63 6 | 18.8 48 | 24.0 41 | 18.6 89 | 14.4 55 | 33.0 17 | 11.7 44 | 8.15 42 | 20.4 27 | 14.7 79 | 3.16 36 | 5.36 11 | 8.09 68 |
Ramp [62] | 37.0 | 10.9 28 | 32.7 35 | 7.96 31 | 10.9 51 | 37.1 57 | 10.6 54 | 7.85 23 | 24.2 24 | 7.41 45 | 5.29 33 | 27.0 31 | 3.44 42 | 16.1 25 | 22.3 30 | 10.8 28 | 13.8 46 | 35.4 31 | 11.0 31 | 11.6 58 | 21.1 33 | 18.2 91 | 2.52 18 | 5.44 13 | 5.23 29 |
Sparse-NonSparse [56] | 37.5 | 10.7 24 | 32.5 30 | 8.38 40 | 10.9 51 | 36.8 55 | 10.7 58 | 7.95 28 | 24.5 30 | 7.30 43 | 5.42 38 | 27.6 38 | 3.49 46 | 16.1 25 | 22.1 27 | 11.0 32 | 13.3 39 | 36.0 34 | 10.6 27 | 10.6 54 | 21.1 33 | 10.9 57 | 2.91 27 | 5.93 21 | 6.18 44 |
Correlation Flow [75] | 37.6 | 11.9 41 | 35.3 41 | 6.03 15 | 6.85 11 | 28.0 14 | 4.77 6 | 8.29 33 | 25.8 35 | 2.17 2 | 4.84 24 | 27.2 35 | 2.77 24 | 18.5 46 | 25.9 53 | 11.7 39 | 16.9 78 | 39.5 52 | 16.7 83 | 12.1 61 | 24.6 59 | 17.8 88 | 2.59 20 | 7.33 32 | 3.08 11 |
LSM [39] | 38.0 | 10.4 21 | 32.6 31 | 8.24 35 | 10.8 49 | 37.4 60 | 10.4 51 | 7.85 23 | 24.3 26 | 7.05 37 | 5.32 34 | 27.6 38 | 3.41 41 | 15.8 21 | 21.5 22 | 11.1 34 | 13.7 44 | 35.6 33 | 10.9 30 | 13.0 65 | 23.2 49 | 12.5 66 | 2.99 33 | 6.43 26 | 6.14 43 |
ProbFlowFields [128] | 38.8 | 16.2 62 | 47.8 74 | 11.7 73 | 8.96 30 | 31.0 28 | 8.86 36 | 9.73 46 | 28.4 45 | 10.1 65 | 6.09 54 | 25.5 23 | 4.53 65 | 18.2 44 | 25.5 47 | 10.9 30 | 9.76 12 | 34.2 26 | 11.7 44 | 4.63 9 | 18.8 14 | 3.79 19 | 2.95 29 | 8.94 41 | 3.52 14 |
Classic+NL [31] | 40.5 | 10.5 23 | 31.4 24 | 8.38 40 | 11.1 56 | 37.9 66 | 10.6 54 | 7.87 25 | 24.0 21 | 7.48 46 | 5.57 42 | 27.6 38 | 3.62 49 | 15.8 21 | 21.5 22 | 10.8 28 | 14.1 51 | 37.4 41 | 11.4 38 | 14.8 74 | 25.9 64 | 13.4 75 | 2.61 21 | 5.29 10 | 6.10 42 |
FMOF [94] | 41.8 | 11.0 35 | 30.4 19 | 8.33 39 | 13.0 80 | 38.5 75 | 12.6 78 | 7.51 17 | 22.6 15 | 7.34 44 | 5.06 29 | 25.2 20 | 3.44 42 | 15.3 18 | 21.3 19 | 9.87 24 | 14.9 62 | 33.1 19 | 11.4 38 | 11.7 60 | 24.3 58 | 15.0 81 | 3.92 46 | 8.59 39 | 6.28 46 |
S2D-Matching [84] | 41.9 | 10.7 24 | 32.2 29 | 8.71 47 | 10.7 47 | 36.6 54 | 10.2 47 | 8.94 41 | 27.2 41 | 6.96 36 | 5.17 31 | 26.0 29 | 3.36 40 | 16.3 30 | 22.1 27 | 10.9 30 | 14.4 55 | 37.0 38 | 11.7 44 | 16.4 78 | 26.0 65 | 16.5 83 | 2.79 25 | 5.49 15 | 6.49 49 |
IROF-TV [53] | 44.5 | 11.6 37 | 35.3 41 | 9.03 50 | 11.2 59 | 38.2 72 | 10.9 62 | 8.85 39 | 26.5 38 | 7.73 51 | 6.04 53 | 33.0 70 | 3.62 49 | 17.1 37 | 23.1 36 | 13.5 60 | 16.3 72 | 44.8 75 | 13.5 65 | 3.41 5 | 16.9 5 | 1.13 3 | 2.71 23 | 6.80 30 | 5.67 37 |
TV-L1-MCT [64] | 45.0 | 10.9 28 | 30.5 21 | 8.56 44 | 13.8 88 | 40.9 95 | 13.2 84 | 8.68 37 | 25.8 35 | 7.98 55 | 4.83 23 | 25.7 24 | 3.26 37 | 17.4 39 | 23.5 39 | 13.7 64 | 14.8 61 | 36.7 36 | 12.7 59 | 5.84 22 | 19.4 18 | 10.1 55 | 3.53 40 | 6.42 25 | 6.63 52 |
Aniso-Texture [82] | 46.2 | 9.33 13 | 28.5 12 | 7.26 23 | 9.17 32 | 26.8 11 | 10.2 47 | 10.1 50 | 29.2 48 | 7.28 42 | 2.77 1 | 22.6 11 | 0.94 1 | 19.9 62 | 27.1 66 | 13.3 58 | 14.6 58 | 38.5 49 | 12.4 56 | 31.5 113 | 46.3 117 | 18.2 91 | 4.45 52 | 10.1 45 | 6.60 51 |
2DHMM-SAS [92] | 46.2 | 10.9 28 | 32.6 31 | 8.06 33 | 11.5 62 | 39.5 85 | 10.6 54 | 10.0 49 | 28.3 44 | 7.91 54 | 5.93 49 | 28.2 45 | 4.07 55 | 16.1 25 | 22.3 30 | 11.0 32 | 13.7 44 | 38.3 48 | 11.1 32 | 12.3 63 | 23.2 49 | 18.0 90 | 3.08 35 | 6.48 28 | 6.24 45 |
AggregFlow [97] | 46.5 | 13.9 49 | 33.8 38 | 11.2 67 | 13.7 86 | 39.6 87 | 12.6 78 | 12.0 64 | 31.3 54 | 13.7 81 | 5.40 37 | 23.5 13 | 3.44 42 | 17.5 40 | 25.4 45 | 7.98 11 | 8.57 4 | 25.9 2 | 8.42 7 | 7.00 32 | 24.1 57 | 4.53 26 | 5.53 67 | 9.80 44 | 11.7 85 |
CostFilter [40] | 46.6 | 14.1 50 | 36.2 47 | 8.48 43 | 8.61 28 | 30.6 25 | 7.43 27 | 8.26 31 | 26.9 40 | 4.40 12 | 5.72 45 | 28.1 44 | 3.24 36 | 13.7 9 | 18.5 7 | 7.81 10 | 16.6 75 | 45.0 80 | 16.0 80 | 26.8 105 | 48.6 121 | 32.7 111 | 2.93 28 | 7.59 34 | 5.38 31 |
SimpleFlow [49] | 46.7 | 11.6 37 | 33.7 37 | 8.98 49 | 12.5 76 | 38.9 78 | 12.6 78 | 10.4 51 | 29.3 49 | 9.20 61 | 5.99 50 | 27.6 38 | 4.08 56 | 16.3 30 | 22.2 29 | 11.1 34 | 16.7 76 | 37.4 41 | 12.7 59 | 8.29 43 | 19.9 22 | 6.11 41 | 2.74 24 | 6.28 23 | 5.86 39 |
Adaptive [20] | 47.2 | 10.9 28 | 33.8 38 | 4.92 10 | 10.5 45 | 35.0 48 | 9.53 41 | 12.2 65 | 33.7 58 | 7.68 50 | 5.57 42 | 30.3 56 | 2.95 30 | 21.7 86 | 26.7 61 | 20.6 95 | 10.8 19 | 34.9 29 | 7.26 3 | 14.0 71 | 28.8 73 | 4.88 27 | 4.50 54 | 10.2 47 | 6.84 56 |
MDP-Flow [26] | 47.6 | 12.2 43 | 40.6 54 | 8.88 48 | 9.32 33 | 28.3 16 | 10.5 52 | 9.09 42 | 28.1 43 | 9.37 63 | 6.03 52 | 30.6 58 | 3.99 52 | 17.2 38 | 23.1 36 | 12.4 45 | 13.9 47 | 42.7 67 | 12.5 58 | 7.10 35 | 23.6 52 | 4.09 24 | 5.35 62 | 13.2 62 | 7.09 61 |
RFlow [90] | 48.1 | 14.8 51 | 43.9 63 | 11.2 67 | 6.64 9 | 26.6 10 | 5.76 12 | 11.7 60 | 35.9 67 | 5.04 21 | 4.31 15 | 27.1 32 | 1.94 10 | 19.4 52 | 26.8 63 | 13.0 57 | 14.7 59 | 42.2 64 | 11.8 48 | 13.1 66 | 22.2 45 | 13.1 72 | 5.87 72 | 14.1 69 | 8.71 71 |
Occlusion-TV-L1 [63] | 48.7 | 12.9 46 | 36.1 46 | 8.26 38 | 9.51 37 | 32.7 36 | 8.99 37 | 12.3 66 | 34.4 62 | 8.27 57 | 5.53 41 | 29.8 54 | 3.04 33 | 20.5 73 | 28.5 84 | 13.8 66 | 9.95 13 | 37.9 43 | 11.6 42 | 7.64 38 | 21.8 43 | 3.47 13 | 5.69 69 | 13.9 67 | 7.59 65 |
OFH [38] | 50.2 | 15.0 53 | 40.9 55 | 14.4 84 | 7.06 13 | 29.9 20 | 5.37 10 | 10.8 54 | 33.1 57 | 4.86 19 | 5.84 48 | 30.6 58 | 3.46 45 | 19.5 55 | 26.1 54 | 15.3 73 | 15.6 67 | 46.5 87 | 16.6 82 | 4.19 6 | 21.7 41 | 3.74 18 | 5.39 64 | 15.4 79 | 7.23 62 |
MLDP_OF [89] | 52.6 | 18.8 84 | 51.3 89 | 16.0 87 | 8.16 23 | 32.0 33 | 6.76 23 | 10.7 53 | 31.9 56 | 5.45 25 | 4.81 22 | 26.1 30 | 2.44 20 | 18.7 47 | 24.3 43 | 13.7 64 | 15.6 67 | 37.9 43 | 18.6 91 | 19.2 86 | 28.5 71 | 38.7 114 | 3.53 40 | 7.25 31 | 4.27 20 |
DeepFlow2 [108] | 54.4 | 15.0 53 | 43.6 62 | 11.0 63 | 10.1 40 | 34.2 45 | 9.29 39 | 12.9 68 | 36.8 68 | 11.1 70 | 7.47 70 | 32.1 65 | 4.75 69 | 17.8 41 | 25.4 45 | 9.97 25 | 10.7 17 | 40.2 56 | 10.3 20 | 6.78 30 | 18.7 13 | 13.3 74 | 9.05 91 | 17.3 87 | 15.3 95 |
Steered-L1 [118] | 55.4 | 11.4 36 | 37.9 49 | 7.71 28 | 4.42 1 | 21.7 1 | 3.76 1 | 7.71 21 | 25.7 33 | 4.29 11 | 4.91 27 | 29.8 54 | 2.26 17 | 20.2 68 | 26.7 61 | 16.6 80 | 18.1 83 | 46.1 86 | 14.6 69 | 32.4 114 | 37.9 102 | 51.5 124 | 8.58 88 | 15.5 81 | 15.2 94 |
S2F-IF [123] | 56.3 | 18.0 77 | 51.9 92 | 10.9 60 | 11.1 56 | 38.6 76 | 10.6 54 | 13.9 73 | 40.6 82 | 13.4 80 | 7.68 77 | 32.6 67 | 5.18 76 | 19.7 60 | 27.2 68 | 13.3 58 | 10.8 19 | 39.5 52 | 11.9 49 | 4.99 14 | 19.9 22 | 6.26 42 | 3.26 38 | 10.1 45 | 3.57 15 |
Sparse Occlusion [54] | 56.4 | 12.7 44 | 35.8 45 | 8.24 35 | 12.4 73 | 33.4 42 | 13.4 85 | 9.67 44 | 29.1 47 | 6.55 33 | 5.99 50 | 28.5 48 | 3.56 48 | 19.4 52 | 26.4 59 | 12.4 45 | 14.7 59 | 39.4 51 | 11.7 44 | 37.7 121 | 48.6 121 | 17.8 88 | 3.66 42 | 9.43 42 | 5.64 36 |
PGM-C [120] | 56.5 | 17.7 72 | 50.5 83 | 11.0 63 | 11.9 66 | 39.1 80 | 11.6 71 | 13.9 73 | 40.4 81 | 13.3 79 | 7.52 73 | 35.8 84 | 4.62 68 | 19.6 58 | 27.5 71 | 12.4 45 | 9.48 10 | 37.9 43 | 9.36 11 | 4.63 9 | 16.9 5 | 5.02 30 | 4.83 57 | 14.2 72 | 6.69 53 |
Classic++ [32] | 56.6 | 10.8 26 | 32.7 35 | 8.25 37 | 10.5 45 | 32.9 37 | 10.7 58 | 10.8 54 | 31.6 55 | 8.46 58 | 5.25 32 | 29.7 53 | 2.99 32 | 20.0 64 | 28.0 79 | 13.9 67 | 15.2 65 | 44.1 72 | 11.9 49 | 17.3 82 | 26.2 67 | 18.3 93 | 5.82 71 | 12.7 58 | 8.14 69 |
CPM-Flow [116] | 57.4 | 17.7 72 | 50.5 83 | 11.0 63 | 11.9 66 | 39.0 79 | 11.7 72 | 13.7 72 | 39.8 79 | 13.2 77 | 7.49 72 | 35.5 82 | 4.58 67 | 19.5 55 | 27.2 68 | 12.3 44 | 9.44 9 | 37.3 40 | 9.46 12 | 5.05 16 | 19.5 19 | 5.17 32 | 5.21 60 | 14.8 75 | 7.36 63 |
BriefMatch [124] | 57.8 | 11.8 40 | 35.7 44 | 6.41 18 | 7.52 18 | 30.3 22 | 5.97 14 | 7.54 18 | 24.2 24 | 4.62 17 | 4.28 14 | 25.4 22 | 1.98 11 | 20.6 75 | 26.2 57 | 20.9 97 | 26.8 110 | 49.2 90 | 28.2 112 | 22.8 97 | 35.9 94 | 39.6 118 | 9.81 94 | 15.1 78 | 18.3 103 |
FlowFields+ [130] | 58.0 | 18.4 79 | 52.2 96 | 11.4 70 | 11.9 66 | 39.9 89 | 11.5 68 | 14.9 80 | 43.4 90 | 14.4 84 | 7.97 80 | 33.1 71 | 5.58 80 | 19.4 52 | 26.9 65 | 12.7 52 | 10.2 14 | 39.9 55 | 10.5 25 | 4.74 12 | 20.1 25 | 4.29 25 | 3.80 43 | 12.4 57 | 3.48 13 |
ACK-Prior [27] | 58.2 | 19.5 88 | 41.5 57 | 14.3 83 | 6.57 8 | 27.6 13 | 4.53 5 | 7.87 25 | 25.7 33 | 3.70 8 | 4.33 16 | 25.7 24 | 1.53 5 | 20.5 73 | 25.6 50 | 18.3 86 | 23.1 101 | 44.0 71 | 18.5 90 | 29.9 109 | 33.1 85 | 45.6 122 | 7.91 85 | 14.8 75 | 11.7 85 |
NL-TV-NCC [25] | 58.5 | 16.5 65 | 40.4 52 | 9.10 51 | 10.7 47 | 37.0 56 | 8.07 31 | 8.59 35 | 26.8 39 | 3.17 4 | 6.24 56 | 33.4 73 | 3.26 37 | 21.4 83 | 29.7 97 | 12.7 52 | 21.2 93 | 48.2 89 | 17.3 86 | 13.4 69 | 35.6 93 | 13.0 71 | 4.73 55 | 12.8 59 | 3.24 12 |
EpicFlow [102] | 58.6 | 17.7 72 | 50.6 85 | 10.9 60 | 12.0 70 | 39.3 83 | 11.7 72 | 14.5 76 | 42.2 86 | 13.2 77 | 7.47 70 | 35.5 82 | 4.57 66 | 19.8 61 | 27.6 72 | 12.8 55 | 9.73 11 | 38.1 47 | 10.1 19 | 4.63 9 | 17.2 7 | 4.88 27 | 5.31 61 | 14.3 74 | 7.47 64 |
CombBMOF [113] | 59.0 | 15.2 55 | 48.2 76 | 7.67 26 | 11.3 60 | 34.5 46 | 9.95 44 | 8.75 38 | 27.2 41 | 5.37 24 | 7.60 76 | 32.1 65 | 5.65 83 | 18.0 43 | 23.0 35 | 13.9 67 | 21.7 96 | 44.9 77 | 24.3 104 | 22.6 95 | 37.2 97 | 14.5 78 | 2.97 32 | 7.73 36 | 4.35 21 |
Complementary OF [21] | 60.4 | 20.9 90 | 51.7 90 | 21.5 96 | 6.41 6 | 28.3 16 | 4.86 8 | 9.56 43 | 30.2 52 | 5.62 26 | 8.21 82 | 31.4 61 | 6.20 86 | 19.2 50 | 25.6 50 | 15.5 74 | 21.5 95 | 49.3 91 | 17.4 87 | 6.34 25 | 19.8 21 | 11.5 60 | 6.44 78 | 16.1 84 | 10.2 78 |
FlowFields [110] | 60.6 | 18.3 78 | 51.9 92 | 11.1 66 | 11.9 66 | 39.5 85 | 11.5 68 | 14.8 78 | 43.3 89 | 14.2 82 | 7.96 79 | 33.5 76 | 5.52 79 | 19.9 62 | 27.6 72 | 13.6 62 | 11.0 23 | 40.5 58 | 12.1 53 | 4.93 13 | 19.7 20 | 5.34 36 | 3.85 44 | 12.3 56 | 3.89 17 |
TF+OM [100] | 61.3 | 14.8 51 | 35.4 43 | 7.68 27 | 9.06 31 | 28.4 18 | 9.32 40 | 11.6 59 | 28.4 45 | 16.0 89 | 6.43 57 | 29.0 51 | 4.29 59 | 20.2 68 | 25.6 50 | 18.4 87 | 17.9 81 | 38.5 49 | 16.9 85 | 16.6 79 | 33.8 86 | 14.7 79 | 6.87 81 | 15.5 81 | 9.68 75 |
ROF-ND [107] | 62.0 | 18.4 79 | 45.8 70 | 11.5 71 | 7.31 16 | 25.4 5 | 6.02 17 | 9.70 45 | 29.4 50 | 4.66 18 | 9.09 88 | 28.7 49 | 5.98 85 | 21.6 85 | 29.5 94 | 14.5 70 | 19.9 89 | 44.8 75 | 15.3 75 | 33.3 118 | 41.0 107 | 30.1 109 | 2.95 29 | 7.63 35 | 2.41 9 |
TV-L1-improved [17] | 63.2 | 11.9 41 | 36.8 48 | 8.23 34 | 8.49 27 | 31.0 28 | 7.83 30 | 11.9 62 | 33.7 58 | 7.19 40 | 5.35 35 | 28.9 50 | 2.91 28 | 20.3 71 | 28.0 79 | 12.0 42 | 27.2 112 | 55.4 107 | 30.4 114 | 23.1 100 | 38.0 103 | 22.9 104 | 5.61 68 | 14.0 68 | 7.74 67 |
ComplOF-FED-GPU [35] | 63.6 | 17.9 75 | 52.0 94 | 15.4 86 | 7.90 21 | 33.9 44 | 5.82 13 | 10.8 54 | 34.2 60 | 5.67 27 | 6.99 64 | 31.5 62 | 4.51 64 | 19.2 50 | 26.3 58 | 12.9 56 | 18.2 84 | 50.5 97 | 18.6 91 | 15.1 75 | 23.6 52 | 22.3 103 | 5.37 63 | 15.4 79 | 6.76 54 |
TCOF [69] | 63.8 | 17.2 70 | 45.4 69 | 15.3 85 | 12.6 77 | 37.6 63 | 12.3 75 | 15.7 83 | 39.5 76 | 16.6 90 | 6.72 60 | 27.7 42 | 4.48 63 | 22.5 92 | 30.9 106 | 11.9 40 | 9.21 7 | 28.4 4 | 10.8 29 | 22.9 98 | 35.0 92 | 9.29 52 | 4.22 50 | 11.3 53 | 6.79 55 |
DeepFlow [86] | 63.8 | 17.5 71 | 46.9 72 | 16.5 88 | 11.8 64 | 35.8 50 | 11.2 66 | 15.1 81 | 39.6 78 | 15.2 87 | 7.81 78 | 32.6 67 | 5.12 75 | 17.8 41 | 25.5 47 | 9.86 23 | 12.0 28 | 44.9 77 | 11.4 38 | 6.11 24 | 18.0 8 | 12.8 69 | 10.8 100 | 18.7 94 | 18.8 105 |
EPPM w/o HM [88] | 64.7 | 19.4 86 | 53.2 98 | 11.2 67 | 8.23 24 | 34.8 47 | 6.07 18 | 11.1 57 | 35.1 65 | 5.89 29 | 7.31 68 | 33.4 73 | 4.76 70 | 18.9 49 | 23.2 38 | 17.1 82 | 21.3 94 | 50.3 96 | 20.1 95 | 20.7 91 | 30.3 77 | 40.9 120 | 3.20 37 | 8.13 37 | 5.59 34 |
Kuang [131] | 65.3 | 17.1 68 | 52.1 95 | 10.8 58 | 11.0 55 | 40.8 94 | 9.84 43 | 14.7 77 | 44.8 93 | 11.8 74 | 7.30 67 | 33.1 71 | 5.00 73 | 20.8 77 | 28.6 88 | 14.8 71 | 14.1 51 | 44.7 74 | 15.3 75 | 4.37 7 | 18.5 10 | 5.30 35 | 5.49 65 | 14.2 72 | 9.48 74 |
HBM-GC [105] | 65.4 | 31.9 101 | 41.2 56 | 25.6 101 | 13.2 82 | 32.9 37 | 14.2 89 | 9.93 48 | 24.4 29 | 8.75 59 | 10.1 96 | 24.7 18 | 6.95 94 | 16.6 34 | 21.1 17 | 13.6 62 | 18.5 85 | 33.7 24 | 15.5 78 | 33.9 120 | 47.5 120 | 20.1 100 | 3.38 39 | 8.62 40 | 5.97 41 |
Aniso. Huber-L1 [22] | 67.4 | 13.6 48 | 40.4 52 | 9.77 52 | 19.4 94 | 40.1 90 | 22.0 94 | 16.4 86 | 38.4 70 | 18.3 92 | 7.56 74 | 33.4 73 | 5.00 73 | 20.1 67 | 27.7 77 | 12.5 48 | 14.5 57 | 39.7 54 | 10.4 23 | 20.8 92 | 32.0 81 | 12.9 70 | 4.35 51 | 10.8 50 | 6.56 50 |
SIOF [67] | 68.0 | 16.5 65 | 40.1 51 | 10.8 58 | 10.3 43 | 37.1 57 | 9.10 38 | 16.4 86 | 38.3 69 | 18.4 93 | 8.56 83 | 35.1 80 | 5.87 84 | 21.3 82 | 28.5 84 | 16.5 79 | 17.6 80 | 43.6 70 | 19.7 94 | 7.08 34 | 21.6 40 | 3.65 16 | 6.65 79 | 16.1 84 | 10.9 82 |
Rannacher [23] | 68.0 | 15.5 58 | 43.5 61 | 10.7 56 | 11.4 61 | 35.8 50 | 11.5 68 | 14.2 75 | 39.0 74 | 10.8 67 | 6.59 59 | 30.8 60 | 4.20 58 | 21.0 79 | 29.6 96 | 12.6 50 | 19.1 87 | 50.8 98 | 15.2 73 | 14.7 73 | 26.8 68 | 16.7 84 | 4.86 58 | 12.9 60 | 7.03 60 |
F-TV-L1 [15] | 68.2 | 31.8 100 | 60.6 103 | 43.6 112 | 13.7 86 | 38.4 74 | 13.1 83 | 15.6 82 | 39.4 75 | 10.1 65 | 10.9 98 | 37.3 90 | 8.78 99 | 20.0 64 | 26.5 60 | 16.0 78 | 12.9 34 | 40.7 59 | 10.7 28 | 9.68 50 | 23.7 55 | 3.52 15 | 4.49 53 | 12.0 54 | 4.19 19 |
Brox et al. [5] | 70.9 | 18.5 81 | 51.2 87 | 20.8 95 | 14.0 89 | 37.8 65 | 15.1 91 | 13.6 71 | 38.8 72 | 11.7 72 | 7.20 66 | 36.8 87 | 4.02 53 | 23.0 96 | 28.5 84 | 24.3 105 | 10.8 19 | 45.3 82 | 9.57 13 | 7.81 40 | 22.7 46 | 1.58 4 | 9.61 93 | 19.2 97 | 15.0 93 |
LocallyOriented [52] | 70.9 | 15.8 61 | 41.5 57 | 10.9 60 | 15.0 91 | 44.5 100 | 13.7 87 | 17.6 90 | 43.4 90 | 14.2 82 | 7.16 65 | 31.5 62 | 4.82 71 | 21.0 79 | 29.0 90 | 12.5 48 | 11.7 26 | 34.5 27 | 12.9 61 | 11.6 58 | 29.6 74 | 12.0 63 | 7.94 86 | 18.4 91 | 11.1 83 |
SRR-TVOF-NL [91] | 71.0 | 22.3 96 | 44.7 65 | 12.5 77 | 12.0 70 | 38.1 69 | 10.2 47 | 14.8 78 | 40.6 82 | 10.9 69 | 6.13 55 | 34.1 77 | 2.81 26 | 19.6 58 | 25.5 47 | 13.5 60 | 16.4 73 | 42.4 65 | 13.0 62 | 30.5 110 | 42.5 111 | 18.3 93 | 6.41 77 | 11.0 51 | 12.0 87 |
CRTflow [80] | 71.6 | 16.5 65 | 49.5 79 | 10.6 55 | 9.63 38 | 33.8 43 | 8.65 35 | 13.1 69 | 38.8 72 | 7.80 53 | 6.86 62 | 34.3 78 | 4.44 62 | 20.0 64 | 27.8 78 | 12.2 43 | 31.4 117 | 59.0 113 | 36.7 118 | 10.3 52 | 30.4 78 | 12.0 63 | 8.56 87 | 20.4 103 | 12.9 91 |
DPOF [18] | 72.0 | 20.5 89 | 50.2 82 | 10.5 53 | 12.6 77 | 41.8 97 | 11.0 64 | 11.8 61 | 34.3 61 | 10.8 67 | 8.61 85 | 38.9 96 | 5.43 77 | 19.5 55 | 26.1 54 | 15.1 72 | 16.8 77 | 41.5 63 | 15.2 73 | 23.3 101 | 23.9 56 | 50.1 123 | 5.05 59 | 14.1 69 | 4.13 18 |
Bartels [41] | 73.9 | 19.3 85 | 39.6 50 | 22.4 98 | 9.47 36 | 28.2 15 | 10.0 46 | 9.91 47 | 29.7 51 | 7.09 38 | 9.18 90 | 29.3 52 | 7.40 96 | 21.7 86 | 27.6 72 | 21.1 98 | 19.1 87 | 44.4 73 | 24.2 103 | 23.0 99 | 36.3 95 | 36.2 112 | 7.46 84 | 14.9 77 | 11.5 84 |
Dynamic MRF [7] | 74.6 | 22.0 94 | 52.3 97 | 25.2 100 | 7.67 19 | 33.0 39 | 6.18 21 | 12.4 67 | 39.8 79 | 5.34 23 | 6.49 58 | 35.4 81 | 3.86 51 | 22.9 94 | 29.2 92 | 20.7 96 | 22.2 98 | 57.8 110 | 22.9 100 | 7.42 37 | 18.1 9 | 25.1 105 | 13.2 106 | 21.3 107 | 20.5 108 |
CBF [12] | 76.9 | 15.2 55 | 44.8 66 | 12.1 75 | 23.7 99 | 37.7 64 | 30.9 102 | 13.2 70 | 34.6 63 | 14.5 85 | 6.86 62 | 32.8 69 | 4.32 60 | 22.6 93 | 28.4 83 | 20.2 93 | 15.6 67 | 41.0 61 | 12.1 53 | 32.9 116 | 39.7 105 | 29.8 108 | 5.49 65 | 13.2 62 | 8.30 70 |
TriangleFlow [30] | 77.0 | 18.7 83 | 43.9 63 | 18.0 89 | 10.1 40 | 37.2 59 | 8.18 32 | 11.9 62 | 35.5 66 | 5.81 28 | 6.72 60 | 34.6 79 | 4.37 61 | 26.7 112 | 34.7 113 | 23.4 102 | 23.1 101 | 49.6 92 | 23.5 101 | 16.7 80 | 37.2 97 | 16.3 82 | 6.85 80 | 17.3 87 | 10.3 79 |
DF-Auto [115] | 77.1 | 19.4 86 | 46.0 71 | 10.5 53 | 26.6 103 | 46.1 102 | 31.1 103 | 23.7 101 | 46.1 95 | 37.0 103 | 9.05 87 | 36.8 87 | 5.59 81 | 21.7 86 | 29.1 91 | 17.4 84 | 7.80 3 | 31.8 13 | 7.93 5 | 19.5 88 | 37.4 99 | 3.25 12 | 10.9 101 | 19.6 99 | 16.4 97 |
Local-TV-L1 [65] | 77.5 | 24.6 97 | 51.2 87 | 30.0 102 | 22.5 98 | 40.6 92 | 25.2 97 | 23.5 100 | 46.1 95 | 28.3 98 | 9.73 93 | 37.4 91 | 6.92 93 | 18.3 45 | 25.2 44 | 12.7 52 | 13.9 47 | 43.2 69 | 12.0 52 | 5.25 17 | 20.6 28 | 5.15 31 | 15.8 111 | 21.0 105 | 32.1 116 |
SuperFlow [81] | 78.7 | 16.2 62 | 42.7 60 | 13.0 79 | 20.9 95 | 39.6 87 | 25.0 96 | 19.7 95 | 40.6 82 | 31.8 100 | 9.89 95 | 41.2 99 | 7.16 95 | 20.9 78 | 27.1 66 | 20.3 94 | 12.2 30 | 41.1 62 | 11.3 35 | 19.0 85 | 32.1 83 | 3.87 20 | 10.1 96 | 19.3 98 | 16.4 97 |
LDOF [28] | 79.0 | 17.1 68 | 48.0 75 | 12.9 78 | 13.3 83 | 40.6 92 | 12.2 74 | 15.8 84 | 42.4 87 | 12.7 76 | 9.70 92 | 44.0 101 | 6.27 88 | 20.7 76 | 28.0 79 | 16.8 81 | 14.3 54 | 45.9 85 | 13.8 66 | 8.36 44 | 23.3 51 | 7.98 49 | 11.2 103 | 21.2 106 | 18.3 103 |
CNN-flow-warp+ref [117] | 80.1 | 18.5 81 | 50.0 80 | 13.9 82 | 17.8 93 | 37.9 66 | 21.1 93 | 21.3 98 | 47.3 99 | 29.7 99 | 9.13 89 | 38.8 94 | 6.72 91 | 21.8 89 | 28.2 82 | 19.6 90 | 14.2 53 | 45.7 84 | 13.1 63 | 5.94 23 | 18.5 10 | 10.9 57 | 12.4 105 | 20.6 104 | 16.4 97 |
CLG-TV [48] | 80.2 | 15.7 60 | 42.2 59 | 11.7 73 | 20.9 95 | 39.2 82 | 24.8 95 | 16.4 86 | 39.5 76 | 18.0 91 | 9.23 91 | 37.9 92 | 6.54 89 | 22.9 94 | 30.0 101 | 17.9 85 | 16.5 74 | 47.2 88 | 14.2 68 | 19.9 89 | 30.4 78 | 11.5 60 | 5.79 70 | 14.1 69 | 6.98 59 |
TriFlow [95] | 80.7 | 21.3 92 | 44.9 67 | 13.5 81 | 16.0 92 | 36.5 53 | 18.7 92 | 18.2 92 | 38.6 71 | 27.8 97 | 7.35 69 | 30.3 56 | 5.59 81 | 21.2 81 | 27.3 70 | 18.5 88 | 15.1 63 | 37.1 39 | 15.0 72 | 49.5 126 | 41.7 109 | 95.6 129 | 6.38 76 | 13.3 64 | 9.77 76 |
p-harmonic [29] | 81.0 | 21.2 91 | 63.8 108 | 20.6 94 | 12.4 73 | 35.9 52 | 12.7 81 | 17.7 91 | 47.5 100 | 14.9 86 | 10.9 98 | 42.1 100 | 8.85 100 | 20.4 72 | 26.1 54 | 17.1 82 | 17.9 81 | 52.5 101 | 18.4 89 | 15.6 77 | 28.6 72 | 5.86 39 | 5.89 73 | 13.5 65 | 7.67 66 |
FlowNetS+ft+v [112] | 81.7 | 15.2 55 | 44.9 67 | 10.7 56 | 13.4 84 | 38.2 72 | 13.4 85 | 18.8 94 | 42.8 88 | 24.4 95 | 9.01 86 | 38.8 94 | 6.24 87 | 23.2 98 | 31.5 110 | 15.9 76 | 13.3 39 | 42.6 66 | 13.1 63 | 18.2 84 | 32.6 84 | 21.9 102 | 8.73 89 | 19.1 96 | 12.8 90 |
Second-order prior [8] | 84.0 | 15.6 59 | 48.2 76 | 12.1 75 | 12.6 77 | 39.1 80 | 12.3 75 | 16.2 85 | 44.6 92 | 12.2 75 | 7.57 75 | 31.6 64 | 5.45 78 | 22.2 90 | 30.6 103 | 14.3 69 | 20.8 92 | 56.8 109 | 17.7 88 | 28.0 108 | 33.8 86 | 27.1 106 | 7.43 83 | 17.4 89 | 10.4 81 |
StereoFlow [44] | 85.9 | 85.4 129 | 89.0 129 | 87.9 128 | 73.1 129 | 88.5 129 | 68.8 124 | 66.8 128 | 87.5 128 | 52.4 121 | 81.5 128 | 91.1 128 | 78.5 128 | 25.9 111 | 27.6 72 | 29.7 116 | 6.38 1 | 29.4 8 | 6.60 2 | 1.39 1 | 10.9 1 | 0.20 1 | 6.34 75 | 13.8 66 | 10.3 79 |
Fusion [6] | 87.0 | 17.9 75 | 57.7 100 | 18.6 90 | 9.42 35 | 32.3 35 | 10.2 47 | 11.4 58 | 34.8 64 | 11.7 72 | 8.57 84 | 40.2 97 | 6.89 92 | 25.0 108 | 30.8 105 | 24.9 109 | 23.9 104 | 52.3 100 | 25.0 107 | 33.3 118 | 43.4 113 | 19.3 98 | 9.01 90 | 18.8 95 | 13.4 92 |
Learning Flow [11] | 87.5 | 16.4 64 | 47.3 73 | 11.5 71 | 14.0 89 | 40.3 91 | 14.4 90 | 16.4 86 | 41.7 85 | 15.6 88 | 8.05 81 | 40.7 98 | 4.87 72 | 27.1 114 | 35.0 115 | 22.5 101 | 17.2 79 | 50.0 95 | 16.0 80 | 15.5 76 | 34.1 89 | 13.9 77 | 10.1 96 | 20.2 102 | 12.5 89 |
SegOF [10] | 89.6 | 28.8 99 | 51.1 86 | 13.2 80 | 37.3 112 | 51.8 112 | 44.6 114 | 30.0 106 | 53.0 104 | 43.3 111 | 27.0 111 | 49.6 106 | 22.4 107 | 24.0 104 | 27.6 72 | 28.4 115 | 24.9 107 | 58.5 111 | 24.4 105 | 2.04 2 | 16.2 4 | 0.47 2 | 10.0 95 | 16.5 86 | 16.7 100 |
Ad-TV-NDC [36] | 91.6 | 44.8 115 | 63.0 106 | 69.1 121 | 40.3 115 | 48.4 107 | 48.3 116 | 34.8 110 | 58.5 107 | 39.9 106 | 26.5 110 | 47.8 105 | 27.7 111 | 20.2 68 | 28.5 84 | 11.9 40 | 15.2 65 | 40.9 60 | 14.7 70 | 8.46 45 | 21.0 32 | 5.69 38 | 23.9 121 | 28.3 121 | 41.9 125 |
StereoOF-V1MT [119] | 92.1 | 21.7 93 | 68.0 113 | 20.3 93 | 11.8 64 | 50.4 110 | 7.18 26 | 20.7 97 | 62.8 110 | 9.21 62 | 9.80 94 | 50.8 107 | 6.56 90 | 27.9 116 | 35.8 116 | 23.9 103 | 25.0 108 | 67.3 118 | 24.0 102 | 8.00 41 | 27.7 69 | 12.2 65 | 13.4 107 | 23.5 111 | 15.8 96 |
Shiralkar [42] | 92.5 | 22.0 94 | 69.5 115 | 19.6 91 | 10.9 51 | 42.6 98 | 8.48 34 | 18.4 93 | 54.0 105 | 9.43 64 | 10.1 96 | 45.4 102 | 7.72 97 | 21.5 84 | 28.9 89 | 15.9 76 | 26.8 110 | 60.7 114 | 25.4 109 | 24.3 103 | 29.9 76 | 39.4 116 | 11.0 102 | 23.8 112 | 12.2 88 |
FlowNet2 [122] | 95.1 | 47.2 116 | 61.0 104 | 42.4 109 | 44.5 117 | 57.5 114 | 51.3 118 | 37.6 113 | 64.7 112 | 43.1 110 | 21.0 105 | 35.8 84 | 17.9 104 | 25.8 109 | 30.6 103 | 24.6 107 | 20.4 90 | 49.7 94 | 21.0 96 | 32.5 115 | 53.3 125 | 4.06 23 | 4.13 48 | 13.0 61 | 1.49 6 |
HBpMotionGpu [43] | 97.9 | 32.0 102 | 50.0 80 | 22.9 99 | 36.1 111 | 47.0 104 | 43.9 113 | 29.2 105 | 51.9 103 | 38.6 105 | 13.0 100 | 37.1 89 | 10.2 101 | 23.5 100 | 29.5 94 | 24.2 104 | 18.9 86 | 44.9 77 | 15.9 79 | 33.2 117 | 41.2 108 | 12.6 68 | 11.8 104 | 18.5 92 | 22.7 109 |
IAOF2 [51] | 98.2 | 25.3 98 | 49.2 78 | 22.2 97 | 24.6 100 | 44.3 99 | 28.6 101 | 20.0 96 | 45.4 94 | 25.5 96 | 49.8 120 | 57.5 115 | 60.5 122 | 23.2 98 | 31.0 107 | 15.7 75 | 23.2 103 | 49.6 92 | 19.3 93 | 30.5 110 | 39.0 104 | 19.0 96 | 9.25 92 | 18.6 93 | 9.82 77 |
Modified CLG [34] | 98.4 | 34.8 106 | 61.1 105 | 35.3 104 | 33.3 109 | 46.5 103 | 41.7 112 | 36.8 112 | 63.0 111 | 45.1 115 | 22.1 106 | 55.4 111 | 18.7 106 | 23.9 102 | 31.2 108 | 21.7 100 | 15.8 70 | 51.5 99 | 14.8 71 | 9.01 48 | 24.6 59 | 11.1 59 | 17.6 115 | 25.7 117 | 29.6 114 |
2D-CLG [1] | 99.7 | 44.0 113 | 63.3 107 | 36.1 105 | 44.3 116 | 52.3 113 | 55.1 120 | 49.1 121 | 75.4 119 | 50.5 119 | 64.3 125 | 76.4 124 | 67.8 125 | 24.8 106 | 29.7 97 | 27.4 112 | 20.5 91 | 53.6 104 | 22.4 98 | 2.52 3 | 13.0 2 | 3.50 14 | 22.8 120 | 27.9 120 | 36.9 119 |
Filter Flow [19] | 99.8 | 33.3 103 | 51.7 90 | 20.1 92 | 25.0 101 | 47.2 106 | 27.7 100 | 27.7 103 | 50.0 101 | 37.9 104 | 31.7 113 | 54.1 110 | 29.9 112 | 25.8 109 | 31.2 108 | 28.3 114 | 26.4 109 | 52.9 103 | 24.7 106 | 42.3 123 | 61.5 127 | 13.6 76 | 6.09 74 | 12.1 55 | 6.88 57 |
SPSA-learn [13] | 100.2 | 35.8 107 | 71.2 117 | 43.1 111 | 28.4 105 | 47.0 104 | 32.8 106 | 31.4 108 | 57.7 106 | 42.2 109 | 22.2 107 | 51.0 108 | 22.9 109 | 23.9 102 | 29.4 93 | 24.6 107 | 24.8 106 | 56.5 108 | 25.1 108 | 10.7 55 | 25.1 61 | 3.72 17 | 21.7 118 | 24.9 116 | 35.5 118 |
BlockOverlap [61] | 101.1 | 41.4 109 | 54.1 99 | 36.2 106 | 27.3 104 | 41.4 96 | 32.6 105 | 26.2 102 | 46.5 97 | 31.8 100 | 20.0 103 | 36.6 86 | 18.1 105 | 22.4 91 | 26.8 63 | 25.7 110 | 24.5 105 | 45.6 83 | 21.1 97 | 39.3 122 | 47.0 119 | 43.5 121 | 13.8 108 | 16.0 83 | 28.7 113 |
IAOF [50] | 102.1 | 33.8 104 | 58.3 101 | 40.6 107 | 33.0 108 | 44.5 100 | 39.5 110 | 30.6 107 | 58.7 108 | 33.8 102 | 34.1 116 | 52.4 109 | 40.8 116 | 23.1 97 | 29.9 99 | 19.7 92 | 22.5 99 | 53.7 105 | 16.8 84 | 22.3 94 | 34.0 88 | 10.0 54 | 19.5 116 | 23.9 113 | 37.1 121 |
GroupFlow [9] | 103.2 | 42.7 110 | 67.1 112 | 53.4 114 | 44.8 118 | 63.8 122 | 50.2 117 | 36.7 111 | 69.4 116 | 43.9 112 | 17.2 102 | 46.0 103 | 16.7 102 | 27.8 115 | 34.9 114 | 21.2 99 | 36.7 121 | 67.0 117 | 43.6 122 | 6.40 26 | 21.7 41 | 7.17 44 | 16.6 112 | 25.9 118 | 25.0 110 |
GraphCuts [14] | 103.4 | 34.5 105 | 59.0 102 | 32.1 103 | 26.2 102 | 51.1 111 | 26.4 99 | 28.1 104 | 51.7 102 | 40.4 108 | 13.0 100 | 47.5 104 | 7.98 98 | 23.7 101 | 30.0 101 | 24.3 105 | 33.4 118 | 45.2 81 | 25.7 110 | 31.2 112 | 37.7 101 | 36.8 113 | 10.7 99 | 19.7 100 | 17.7 102 |
Black & Anandan [4] | 103.6 | 38.5 108 | 69.5 115 | 53.4 114 | 28.5 106 | 49.6 109 | 32.0 104 | 33.4 109 | 60.5 109 | 40.2 107 | 22.6 108 | 55.9 112 | 22.8 108 | 24.5 105 | 32.2 112 | 19.6 90 | 21.7 96 | 58.9 112 | 22.7 99 | 22.6 95 | 37.6 100 | 5.27 34 | 16.7 113 | 22.6 110 | 25.4 111 |
2bit-BM-tele [98] | 106.3 | 55.1 120 | 64.1 110 | 69.1 121 | 21.4 97 | 38.7 77 | 25.3 98 | 23.3 99 | 46.7 98 | 21.2 94 | 26.2 109 | 38.7 93 | 25.2 110 | 24.9 107 | 29.9 99 | 27.7 113 | 31.3 116 | 52.6 102 | 34.6 116 | 43.3 124 | 51.7 124 | 54.5 125 | 10.3 98 | 20.1 101 | 16.8 101 |
Nguyen [33] | 107.8 | 43.9 112 | 66.0 111 | 42.8 110 | 54.0 123 | 49.4 108 | 70.1 125 | 42.9 116 | 67.4 114 | 47.3 117 | 55.4 123 | 65.7 119 | 64.4 123 | 27.0 113 | 31.8 111 | 31.0 117 | 22.8 100 | 54.8 106 | 27.3 111 | 13.1 66 | 25.2 62 | 6.08 40 | 22.2 119 | 26.9 119 | 38.9 122 |
SILK [79] | 110.0 | 49.5 119 | 69.2 114 | 69.3 123 | 39.9 114 | 60.6 117 | 47.0 115 | 40.4 115 | 70.7 117 | 45.6 116 | 32.0 114 | 56.5 113 | 31.2 114 | 31.4 118 | 36.9 119 | 33.3 119 | 31.1 115 | 63.2 115 | 32.3 115 | 10.3 52 | 23.0 47 | 17.3 85 | 25.0 122 | 31.9 122 | 36.9 119 |
UnFlow [129] | 110.0 | 70.9 125 | 78.9 120 | 58.5 117 | 51.3 122 | 67.4 125 | 56.9 121 | 54.4 123 | 83.6 126 | 52.8 122 | 33.4 115 | 60.2 116 | 30.1 113 | 36.7 125 | 38.4 122 | 46.2 126 | 38.2 122 | 69.6 121 | 42.8 121 | 26.2 104 | 40.3 106 | 1.60 5 | 7.20 82 | 18.3 90 | 8.75 72 |
Periodicity [78] | 111.8 | 48.9 118 | 63.9 109 | 41.0 108 | 34.5 110 | 60.0 116 | 37.5 109 | 55.4 124 | 67.4 114 | 56.6 124 | 20.4 104 | 56.9 114 | 17.5 103 | 53.2 128 | 66.7 129 | 46.5 127 | 48.3 126 | 76.0 127 | 46.4 124 | 9.14 49 | 34.4 90 | 9.98 53 | 28.3 125 | 48.2 128 | 40.6 124 |
Horn & Schunck [3] | 112.2 | 43.3 111 | 80.7 123 | 58.6 118 | 32.5 107 | 59.7 115 | 35.1 107 | 40.2 114 | 76.3 122 | 44.7 114 | 31.5 112 | 64.8 117 | 32.6 115 | 29.3 117 | 36.4 118 | 27.0 111 | 27.5 113 | 68.7 119 | 29.7 113 | 27.0 106 | 43.3 112 | 7.32 45 | 25.9 123 | 36.5 124 | 34.6 117 |
Heeger++ [104] | 114.8 | 61.9 123 | 80.2 122 | 47.4 113 | 44.8 118 | 77.8 128 | 40.9 111 | 68.0 129 | 84.7 127 | 62.1 127 | 43.6 119 | 69.1 120 | 41.9 117 | 32.6 120 | 37.9 120 | 32.0 118 | 51.1 127 | 78.4 128 | 54.2 127 | 13.3 68 | 43.4 113 | 10.4 56 | 15.0 109 | 21.4 108 | 19.6 106 |
SLK [47] | 115.5 | 44.7 114 | 78.9 120 | 59.1 119 | 58.2 125 | 71.2 126 | 70.9 126 | 47.5 119 | 83.5 125 | 50.6 120 | 65.0 126 | 69.5 121 | 73.4 126 | 34.7 122 | 38.9 124 | 42.9 125 | 34.8 119 | 70.9 124 | 39.4 119 | 12.1 61 | 29.8 75 | 11.5 60 | 34.4 126 | 40.1 125 | 48.8 126 |
TI-DOFE [24] | 117.6 | 73.1 126 | 84.6 127 | 89.6 129 | 61.2 127 | 64.7 124 | 74.8 128 | 58.6 125 | 88.7 129 | 58.0 125 | 70.9 127 | 81.6 126 | 76.1 127 | 31.7 119 | 38.0 121 | 35.4 120 | 29.7 114 | 68.7 119 | 36.3 117 | 17.1 81 | 32.0 81 | 8.67 50 | 35.5 127 | 42.8 126 | 49.8 127 |
FFV1MT [106] | 117.8 | 59.9 122 | 77.8 119 | 53.6 116 | 37.7 113 | 72.5 127 | 37.0 108 | 63.6 127 | 82.1 124 | 62.4 128 | 42.8 118 | 73.9 123 | 42.6 118 | 41.9 127 | 45.8 127 | 52.3 128 | 52.5 128 | 81.8 129 | 56.1 128 | 20.2 90 | 42.4 110 | 18.3 93 | 15.0 109 | 21.4 108 | 19.6 106 |
FOLKI [16] | 120.0 | 48.0 117 | 71.5 118 | 68.8 120 | 48.6 121 | 63.2 119 | 59.5 122 | 43.0 117 | 75.6 120 | 44.0 113 | 40.4 117 | 65.6 118 | 45.8 119 | 35.3 123 | 40.6 125 | 41.6 123 | 36.3 120 | 71.6 126 | 44.4 123 | 23.6 102 | 44.7 116 | 40.4 119 | 36.9 128 | 43.4 127 | 54.5 128 |
PGAM+LK [55] | 122.0 | 58.6 121 | 80.9 124 | 69.8 124 | 45.1 120 | 63.7 121 | 51.9 119 | 43.2 118 | 76.2 121 | 47.5 118 | 50.3 121 | 82.2 127 | 51.4 120 | 32.7 121 | 36.0 117 | 42.3 124 | 41.4 123 | 70.1 122 | 41.2 120 | 56.3 127 | 58.0 126 | 55.0 126 | 25.9 123 | 32.4 123 | 40.3 123 |
Adaptive flow [45] | 122.4 | 76.7 128 | 83.7 126 | 86.4 126 | 57.9 124 | 63.6 120 | 67.3 123 | 48.7 120 | 73.2 118 | 52.9 123 | 52.7 122 | 69.9 122 | 56.0 121 | 35.4 124 | 38.4 122 | 39.4 122 | 46.1 124 | 70.6 123 | 47.6 125 | 73.1 128 | 75.2 128 | 88.1 127 | 17.2 114 | 24.6 115 | 25.6 112 |
HCIC-L [99] | 124.2 | 76.5 127 | 86.4 128 | 73.3 125 | 70.1 128 | 62.5 118 | 85.3 129 | 63.5 126 | 66.1 113 | 79.5 129 | 83.3 129 | 91.8 129 | 86.5 129 | 39.0 126 | 42.8 126 | 38.7 121 | 46.4 125 | 66.6 116 | 52.3 126 | 89.6 129 | 85.9 129 | 94.0 128 | 19.8 117 | 24.2 114 | 29.6 114 |
Pyramid LK [2] | 125.7 | 68.1 124 | 83.5 125 | 86.8 127 | 59.4 126 | 64.5 123 | 73.1 127 | 52.8 122 | 76.3 122 | 61.4 126 | 60.2 124 | 79.0 125 | 65.9 124 | 53.8 129 | 61.8 128 | 64.5 129 | 59.4 129 | 71.1 125 | 63.0 129 | 43.9 125 | 49.4 123 | 39.5 117 | 50.2 129 | 60.2 129 | 70.8 129 |
AdaConv-v1 [126] | 130.0 | 100.0 130 | 99.9 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.8 130 | 100.0 130 | 99.7 130 | 97.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 |
SepConv-v1 [127] | 130.0 | 100.0 130 | 99.9 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.8 130 | 100.0 130 | 99.7 130 | 97.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 |
Method | time* | frames | color | 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] Kuang | 9.9 | 2 | gray | F. Kuang. PatchMatch algorithms for motion estimation and stereo reconstruction. Master thesis, University of Stuttgart, 2017. |