Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
R2.5 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] | 13.6 | 20.0 3 | 43.3 3 | 13.0 3 | 15.9 10 | 45.3 25 | 16.1 14 | 12.5 4 | 34.1 9 | 12.8 9 | 9.68 19 | 32.0 11 | 7.01 23 | 23.3 4 | 30.0 4 | 16.2 4 | 22.0 32 | 45.4 9 | 23.8 61 | 25.8 20 | 44.8 6 | 17.6 17 | 4.37 9 | 14.4 27 | 0.48 1 |
NN-field [71] | 14.3 | 22.1 7 | 44.0 5 | 14.6 4 | 18.4 23 | 47.3 37 | 19.2 27 | 12.5 4 | 32.9 6 | 14.0 14 | 6.57 2 | 28.2 4 | 3.57 2 | 23.4 5 | 30.1 5 | 15.9 3 | 17.9 15 | 36.8 1 | 15.8 4 | 35.9 50 | 51.5 33 | 27.4 48 | 4.58 12 | 15.3 30 | 0.55 2 |
TC/T-Flow [76] | 19.0 | 19.9 2 | 46.9 10 | 10.2 1 | 16.0 11 | 47.8 39 | 13.9 5 | 13.0 8 | 36.6 20 | 11.1 4 | 8.90 12 | 35.0 34 | 6.10 12 | 27.2 17 | 35.7 22 | 21.0 14 | 15.7 4 | 47.2 17 | 15.8 4 | 21.0 8 | 39.2 2 | 42.1 75 | 7.86 40 | 19.5 43 | 10.9 53 |
ALD-Flow [66] | 19.4 | 21.6 6 | 46.0 7 | 15.9 6 | 15.5 8 | 41.3 9 | 15.6 10 | 13.1 9 | 35.2 12 | 12.2 5 | 8.17 10 | 33.4 20 | 5.35 9 | 28.1 24 | 37.3 33 | 20.3 10 | 16.4 6 | 47.4 19 | 16.0 6 | 26.5 23 | 45.4 8 | 41.8 73 | 8.39 44 | 22.3 53 | 11.3 55 |
ComponentFusion [96] | 19.7 | 20.0 3 | 46.3 8 | 14.8 5 | 16.6 14 | 40.3 6 | 18.5 24 | 11.7 3 | 33.6 7 | 10.9 3 | 7.09 5 | 35.2 36 | 4.45 5 | 27.6 20 | 36.0 25 | 21.4 17 | 21.5 28 | 54.1 51 | 20.2 30 | 31.8 43 | 56.8 60 | 16.2 10 | 5.46 22 | 12.8 20 | 7.47 27 |
nLayers [57] | 20.8 | 22.7 9 | 40.3 2 | 18.4 9 | 27.2 88 | 45.9 29 | 30.4 88 | 15.7 22 | 35.4 14 | 21.4 59 | 8.12 9 | 26.6 2 | 6.21 13 | 22.5 2 | 29.0 3 | 15.5 2 | 19.9 20 | 40.8 4 | 17.8 9 | 31.3 39 | 52.6 42 | 16.9 15 | 4.26 6 | 11.2 7 | 5.84 6 |
OFLAF [77] | 21.3 | 29.6 34 | 47.4 12 | 24.8 18 | 17.8 19 | 40.9 7 | 18.3 22 | 11.6 2 | 26.9 2 | 13.2 11 | 11.5 39 | 29.3 8 | 8.97 59 | 23.7 6 | 30.9 6 | 16.5 5 | 22.2 36 | 41.5 5 | 19.3 20 | 30.2 34 | 50.6 27 | 32.9 54 | 5.94 27 | 13.8 22 | 8.44 36 |
WLIF-Flow [93] | 21.6 | 27.0 19 | 47.0 11 | 23.1 16 | 21.7 43 | 46.6 35 | 23.3 41 | 14.8 13 | 36.2 16 | 16.3 22 | 9.33 16 | 32.2 13 | 6.64 17 | 27.7 21 | 35.1 20 | 23.4 29 | 21.6 29 | 47.7 21 | 19.2 17 | 28.7 30 | 45.3 7 | 32.0 53 | 4.50 11 | 11.2 7 | 6.43 11 |
RNLOD-Flow [121] | 21.7 | 20.7 5 | 43.8 4 | 19.4 10 | 18.1 20 | 45.9 29 | 17.0 19 | 12.7 6 | 34.1 9 | 12.3 6 | 7.38 6 | 28.7 6 | 4.87 6 | 26.5 13 | 34.9 18 | 20.9 12 | 20.3 21 | 46.2 12 | 20.2 30 | 43.1 74 | 60.3 70 | 47.5 92 | 4.98 19 | 12.7 19 | 6.55 14 |
HAST [109] | 22.0 | 19.5 1 | 40.1 1 | 11.6 2 | 16.1 12 | 39.7 4 | 14.8 8 | 8.49 1 | 21.2 1 | 7.09 1 | 6.79 3 | 29.0 7 | 3.66 3 | 21.6 1 | 28.3 2 | 13.8 1 | 24.3 56 | 48.5 25 | 24.3 63 | 41.7 71 | 59.8 69 | 63.0 116 | 6.05 29 | 11.5 13 | 8.72 39 |
MDP-Flow2 [68] | 23.9 | 35.3 47 | 55.4 41 | 30.2 43 | 14.2 3 | 39.7 4 | 14.2 7 | 13.6 10 | 31.4 3 | 12.9 10 | 12.2 45 | 34.1 28 | 8.19 46 | 27.7 21 | 35.0 19 | 22.1 20 | 22.4 40 | 45.4 9 | 21.5 43 | 27.1 24 | 54.1 47 | 16.5 11 | 5.87 26 | 14.0 24 | 4.25 3 |
OAR-Flow [125] | 24.5 | 25.6 12 | 54.9 38 | 22.4 14 | 18.7 24 | 44.8 22 | 19.1 25 | 17.2 35 | 43.7 44 | 18.0 28 | 8.53 11 | 31.6 10 | 5.65 10 | 29.7 34 | 39.3 38 | 20.9 12 | 14.5 2 | 47.3 18 | 13.4 2 | 14.1 2 | 38.0 1 | 20.7 30 | 9.84 58 | 21.1 49 | 16.1 70 |
Layers++ [37] | 25.1 | 28.0 31 | 48.8 15 | 30.9 46 | 23.3 58 | 45.6 28 | 25.5 66 | 13.7 11 | 31.4 3 | 18.1 29 | 8.08 8 | 24.9 1 | 5.87 11 | 22.9 3 | 28.1 1 | 19.6 8 | 22.2 36 | 46.3 14 | 20.7 34 | 39.6 66 | 55.9 56 | 35.0 56 | 4.16 3 | 9.78 2 | 6.81 16 |
TC-Flow [46] | 25.2 | 24.4 11 | 52.2 31 | 22.6 15 | 11.8 2 | 38.8 3 | 11.2 1 | 12.7 6 | 35.7 15 | 9.84 2 | 9.88 21 | 34.9 32 | 7.49 31 | 28.9 31 | 38.6 37 | 21.2 16 | 20.6 23 | 52.1 36 | 21.6 44 | 22.6 15 | 47.1 12 | 36.3 59 | 9.05 50 | 21.5 51 | 12.4 60 |
LME [70] | 27.4 | 31.5 36 | 51.4 26 | 21.0 13 | 14.7 5 | 36.9 2 | 15.7 11 | 16.0 27 | 35.2 12 | 19.8 49 | 11.8 42 | 36.6 40 | 8.08 41 | 28.6 28 | 36.0 25 | 25.5 40 | 21.1 26 | 49.0 27 | 19.8 27 | 29.8 33 | 50.0 24 | 21.5 32 | 6.61 31 | 15.1 28 | 7.95 32 |
AGIF+OF [85] | 27.4 | 26.3 13 | 48.8 15 | 24.1 17 | 24.9 68 | 52.0 67 | 26.2 68 | 16.0 27 | 39.4 30 | 19.7 46 | 8.96 13 | 32.0 11 | 6.64 17 | 26.7 15 | 33.7 12 | 21.5 19 | 21.4 27 | 49.4 28 | 18.5 13 | 28.2 27 | 49.6 21 | 30.5 52 | 4.63 15 | 11.3 12 | 7.30 24 |
PH-Flow [101] | 28.3 | 26.7 15 | 51.6 27 | 25.6 24 | 21.7 43 | 49.4 49 | 23.8 47 | 15.5 17 | 37.6 23 | 19.5 42 | 10.2 26 | 33.8 24 | 7.44 30 | 26.4 11 | 33.7 12 | 21.0 14 | 22.0 32 | 50.3 30 | 20.4 32 | 38.8 60 | 48.4 17 | 45.4 82 | 4.26 6 | 11.2 7 | 6.38 10 |
FC-2Layers-FF [74] | 28.5 | 26.9 18 | 48.6 14 | 28.3 37 | 22.1 47 | 48.8 44 | 23.8 47 | 14.1 12 | 32.4 5 | 19.6 44 | 9.10 14 | 28.3 5 | 6.47 16 | 25.5 7 | 31.7 7 | 23.0 27 | 23.3 45 | 47.7 21 | 21.8 45 | 44.1 77 | 56.3 59 | 46.0 87 | 3.54 1 | 9.08 1 | 5.44 5 |
Classic+CPF [83] | 29.5 | 27.1 23 | 51.2 25 | 25.5 23 | 23.9 63 | 51.4 63 | 25.1 61 | 15.9 24 | 39.3 29 | 19.4 40 | 9.17 15 | 32.8 16 | 6.69 19 | 27.3 18 | 34.5 16 | 23.9 30 | 21.0 25 | 48.7 26 | 18.0 11 | 35.6 49 | 49.9 23 | 45.7 84 | 4.25 5 | 10.7 4 | 6.61 15 |
NNF-EAC [103] | 29.8 | 34.9 42 | 54.8 36 | 29.9 42 | 15.6 9 | 41.7 11 | 15.9 12 | 15.1 16 | 34.8 11 | 15.7 16 | 12.4 49 | 35.1 35 | 8.33 49 | 28.1 24 | 35.7 22 | 22.9 25 | 24.5 59 | 46.2 12 | 22.7 55 | 31.6 42 | 49.1 19 | 20.1 28 | 7.54 38 | 17.1 38 | 7.44 26 |
COFM [59] | 29.9 | 22.1 7 | 49.1 17 | 16.6 7 | 18.2 21 | 43.5 16 | 19.2 27 | 15.9 24 | 38.3 26 | 21.5 60 | 7.02 4 | 32.6 14 | 4.40 4 | 31.4 42 | 37.9 34 | 35.0 78 | 22.1 34 | 46.4 15 | 18.3 12 | 28.7 30 | 45.9 10 | 45.5 83 | 9.25 51 | 15.5 32 | 15.7 69 |
IROF++ [58] | 30.3 | 27.4 25 | 50.7 21 | 26.7 30 | 22.1 47 | 50.1 58 | 24.1 51 | 16.3 30 | 40.0 34 | 19.6 44 | 10.6 33 | 34.3 29 | 7.72 36 | 27.9 23 | 35.7 22 | 22.5 21 | 22.3 38 | 54.1 51 | 19.9 28 | 25.5 19 | 49.6 21 | 11.5 6 | 5.49 23 | 14.1 25 | 6.54 13 |
Sparse-NonSparse [56] | 30.4 | 26.8 17 | 51.9 30 | 26.8 31 | 22.2 52 | 49.0 47 | 24.6 57 | 15.6 19 | 39.4 30 | 19.0 35 | 9.46 18 | 33.6 22 | 7.07 25 | 29.0 32 | 37.2 32 | 24.3 35 | 21.7 31 | 50.4 31 | 19.5 25 | 34.0 45 | 45.8 9 | 41.6 71 | 4.44 10 | 10.9 5 | 6.96 20 |
FESL [72] | 31.3 | 27.0 19 | 46.3 8 | 31.2 48 | 26.0 79 | 51.8 66 | 26.9 72 | 15.8 23 | 37.0 21 | 19.5 42 | 7.89 7 | 30.7 9 | 5.17 8 | 26.6 14 | 33.8 14 | 22.6 22 | 20.3 21 | 45.8 11 | 19.3 20 | 39.9 67 | 61.2 74 | 35.6 57 | 5.04 20 | 12.5 18 | 6.48 12 |
Efficient-NL [60] | 31.9 | 23.3 10 | 44.7 6 | 17.6 8 | 24.6 67 | 51.6 65 | 25.4 65 | 15.0 15 | 36.2 16 | 17.5 26 | 9.92 22 | 33.1 18 | 6.94 21 | 26.4 11 | 34.0 15 | 20.3 10 | 27.2 68 | 49.4 28 | 22.6 50 | 37.6 55 | 50.5 26 | 37.1 60 | 6.98 36 | 16.2 34 | 8.16 33 |
LSM [39] | 33.4 | 26.5 14 | 50.8 22 | 27.0 32 | 22.1 47 | 49.4 49 | 24.4 55 | 15.6 19 | 38.2 25 | 19.4 40 | 10.1 23 | 33.0 17 | 7.43 29 | 28.6 28 | 36.3 27 | 24.7 36 | 22.8 43 | 50.5 32 | 20.9 38 | 40.3 69 | 49.3 20 | 45.8 86 | 4.76 17 | 12.0 15 | 6.93 19 |
PMMST [114] | 34.0 | 42.4 71 | 58.9 45 | 40.2 67 | 22.1 47 | 45.3 25 | 24.7 60 | 17.9 41 | 38.4 27 | 18.8 32 | 12.2 45 | 28.1 3 | 8.26 47 | 25.7 8 | 32.7 10 | 18.5 7 | 22.3 38 | 45.3 8 | 20.8 36 | 28.5 29 | 50.7 28 | 18.3 19 | 8.51 47 | 16.8 35 | 8.73 40 |
Classic+NL [31] | 34.8 | 27.2 24 | 47.8 13 | 28.4 38 | 22.0 46 | 49.4 49 | 24.1 51 | 15.5 17 | 37.4 22 | 19.8 49 | 10.4 30 | 33.8 24 | 7.40 28 | 28.5 26 | 36.4 28 | 24.2 34 | 23.3 45 | 52.2 37 | 21.1 39 | 43.9 75 | 52.5 39 | 44.6 79 | 4.60 14 | 11.2 7 | 7.04 22 |
Ramp [62] | 34.8 | 27.0 19 | 52.3 32 | 26.1 28 | 22.3 54 | 49.1 48 | 24.6 57 | 15.6 19 | 37.8 24 | 19.8 49 | 10.5 32 | 33.6 22 | 7.61 33 | 28.6 28 | 36.6 29 | 24.0 31 | 23.6 48 | 51.2 33 | 21.8 45 | 38.2 56 | 44.5 4 | 46.1 88 | 4.86 18 | 12.1 16 | 7.13 23 |
2DHMM-SAS [92] | 37.6 | 26.7 15 | 51.8 29 | 25.6 24 | 22.2 52 | 51.3 61 | 23.8 47 | 17.8 39 | 42.3 39 | 20.0 54 | 10.4 30 | 34.6 31 | 7.52 32 | 28.5 26 | 36.6 29 | 24.0 31 | 22.7 42 | 54.5 54 | 20.6 33 | 39.0 62 | 47.8 15 | 45.1 80 | 5.51 24 | 13.9 23 | 7.73 30 |
FMOF [94] | 38.0 | 27.8 30 | 50.4 20 | 27.1 34 | 26.2 81 | 52.5 71 | 27.4 75 | 15.9 24 | 36.4 19 | 21.7 61 | 9.71 20 | 32.7 15 | 6.98 22 | 27.3 18 | 34.6 17 | 24.1 33 | 23.7 50 | 47.6 20 | 19.7 26 | 38.4 57 | 55.4 53 | 48.9 95 | 5.80 25 | 14.1 25 | 7.00 21 |
SVFilterOh [111] | 39.2 | 39.6 61 | 54.6 35 | 39.8 66 | 23.8 62 | 44.7 21 | 24.0 50 | 17.3 36 | 33.8 8 | 18.8 32 | 10.2 26 | 36.4 39 | 4.93 7 | 25.9 10 | 32.1 8 | 19.6 8 | 24.7 60 | 46.7 16 | 22.9 58 | 52.0 99 | 76.3 117 | 59.2 110 | 4.23 4 | 10.9 5 | 5.01 4 |
S2D-Matching [84] | 40.0 | 27.7 27 | 50.2 19 | 28.4 38 | 22.1 47 | 48.8 44 | 24.3 53 | 16.5 32 | 40.0 34 | 19.3 38 | 10.6 33 | 33.8 24 | 7.78 37 | 29.1 33 | 36.7 31 | 25.0 37 | 24.4 58 | 53.0 47 | 22.6 50 | 47.0 88 | 53.6 44 | 50.8 100 | 4.58 12 | 11.2 7 | 7.54 28 |
ProbFlowFields [128] | 40.5 | 33.9 38 | 68.5 68 | 30.9 46 | 20.3 33 | 45.3 25 | 22.1 37 | 19.2 48 | 44.8 47 | 22.9 65 | 11.7 40 | 39.3 48 | 8.91 58 | 31.0 40 | 40.1 42 | 23.3 28 | 16.8 7 | 47.8 23 | 19.2 17 | 23.7 18 | 55.9 56 | 23.9 42 | 8.39 44 | 22.4 54 | 9.82 49 |
SimpleFlow [49] | 40.9 | 28.6 33 | 51.6 27 | 29.5 41 | 25.0 69 | 51.3 61 | 28.2 80 | 18.6 46 | 43.0 42 | 23.3 66 | 10.1 23 | 33.5 21 | 7.04 24 | 29.9 35 | 37.9 34 | 26.2 42 | 27.8 73 | 52.2 37 | 24.0 62 | 35.1 48 | 47.9 16 | 29.7 51 | 4.66 16 | 12.4 17 | 6.92 18 |
PMF [73] | 42.0 | 37.7 56 | 58.3 43 | 27.3 36 | 19.4 26 | 45.0 24 | 18.3 22 | 16.2 29 | 39.9 33 | 14.0 14 | 13.6 61 | 35.7 37 | 8.03 40 | 25.8 9 | 32.5 9 | 17.1 6 | 30.2 80 | 57.0 64 | 31.6 82 | 58.9 107 | 74.7 110 | 55.9 107 | 3.95 2 | 10.3 3 | 6.15 9 |
Adaptive [20] | 42.6 | 27.0 19 | 52.6 33 | 19.8 11 | 21.9 45 | 47.8 39 | 22.6 39 | 20.5 53 | 47.8 55 | 19.7 46 | 10.3 28 | 39.9 51 | 6.31 15 | 45.6 112 | 52.6 110 | 51.3 111 | 17.4 8 | 48.2 24 | 13.9 3 | 34.8 47 | 56.9 62 | 19.8 26 | 6.04 28 | 15.2 29 | 7.54 28 |
TV-L1-MCT [64] | 43.4 | 27.5 26 | 49.4 18 | 27.0 32 | 26.5 82 | 52.8 76 | 27.8 79 | 16.8 33 | 39.1 28 | 21.8 62 | 10.6 33 | 33.8 24 | 7.82 38 | 30.3 37 | 38.1 36 | 28.7 58 | 24.7 60 | 53.4 49 | 23.4 59 | 27.4 25 | 52.5 39 | 19.4 23 | 7.28 37 | 15.3 30 | 11.4 57 |
Correlation Flow [75] | 43.5 | 36.6 53 | 55.3 40 | 34.4 56 | 16.6 14 | 44.4 20 | 14.8 8 | 18.3 45 | 42.9 41 | 12.7 8 | 12.4 49 | 39.7 50 | 8.46 53 | 32.2 45 | 40.6 45 | 25.2 38 | 29.0 76 | 54.2 53 | 29.7 79 | 39.1 63 | 52.1 37 | 47.4 91 | 6.53 30 | 16.1 33 | 6.88 17 |
IROF-TV [53] | 44.0 | 30.9 35 | 54.8 36 | 31.6 50 | 22.8 57 | 50.5 59 | 25.1 61 | 16.9 34 | 40.8 36 | 20.8 56 | 14.0 63 | 43.7 65 | 10.1 63 | 31.2 41 | 39.5 39 | 28.6 55 | 26.8 67 | 58.7 73 | 25.6 67 | 18.8 4 | 48.4 17 | 8.08 5 | 5.28 21 | 13.6 21 | 7.77 31 |
AggregFlow [97] | 44.3 | 36.3 52 | 52.7 34 | 35.7 58 | 26.6 83 | 52.6 74 | 26.7 70 | 23.3 66 | 48.2 57 | 28.9 84 | 12.1 43 | 34.9 32 | 8.63 55 | 30.2 36 | 40.3 44 | 21.4 17 | 15.9 5 | 38.3 2 | 16.8 7 | 26.1 22 | 47.3 13 | 16.8 13 | 12.6 71 | 20.3 45 | 20.0 80 |
Occlusion-TV-L1 [63] | 44.8 | 34.3 41 | 58.5 44 | 25.1 19 | 20.0 29 | 46.5 34 | 20.8 33 | 22.3 63 | 49.9 58 | 20.6 55 | 12.6 55 | 41.7 57 | 8.41 52 | 35.2 64 | 44.9 73 | 32.3 69 | 17.7 11 | 52.6 42 | 21.1 39 | 28.2 27 | 52.5 39 | 13.0 7 | 9.66 54 | 23.7 58 | 10.6 51 |
Aniso-Texture [82] | 48.0 | 28.5 32 | 50.9 23 | 32.7 53 | 21.2 37 | 41.7 11 | 25.3 64 | 17.6 38 | 41.2 37 | 21.1 58 | 5.72 1 | 33.2 19 | 2.54 1 | 35.1 63 | 43.7 60 | 31.3 67 | 23.6 48 | 53.6 50 | 22.6 50 | 62.2 114 | 75.8 115 | 53.5 104 | 6.89 35 | 17.4 39 | 8.20 34 |
Classic++ [32] | 48.1 | 27.7 27 | 51.0 24 | 28.7 40 | 21.5 42 | 45.9 29 | 24.3 53 | 18.1 44 | 44.3 45 | 19.9 52 | 10.3 28 | 37.7 42 | 7.14 26 | 33.4 48 | 44.1 63 | 27.9 51 | 24.0 54 | 57.9 69 | 21.4 42 | 46.3 84 | 55.6 54 | 49.7 97 | 8.45 46 | 20.7 46 | 9.69 48 |
MDP-Flow [26] | 49.3 | 35.5 48 | 65.0 54 | 32.4 51 | 20.6 35 | 43.8 18 | 24.4 55 | 18.0 43 | 43.4 43 | 19.9 52 | 14.9 71 | 41.8 59 | 11.5 72 | 30.8 39 | 39.6 40 | 25.3 39 | 23.8 52 | 57.4 67 | 22.2 47 | 31.0 37 | 59.3 67 | 16.8 13 | 10.8 66 | 26.5 63 | 10.9 53 |
DeepFlow2 [108] | 49.7 | 39.1 59 | 66.4 58 | 44.4 75 | 20.1 31 | 47.9 41 | 20.9 34 | 23.8 69 | 52.8 65 | 26.3 76 | 12.2 45 | 43.2 64 | 7.64 34 | 31.4 42 | 41.7 52 | 22.9 25 | 18.2 17 | 52.4 39 | 17.9 10 | 29.6 32 | 44.7 5 | 39.0 64 | 16.2 85 | 31.2 85 | 22.7 86 |
OFH [38] | 50.1 | 41.9 70 | 61.6 49 | 48.5 81 | 14.7 5 | 42.7 14 | 14.1 6 | 17.4 37 | 47.6 53 | 12.6 7 | 10.6 33 | 38.5 44 | 8.39 51 | 34.8 61 | 43.7 60 | 34.5 76 | 27.2 68 | 61.9 87 | 29.5 78 | 21.3 11 | 57.6 63 | 21.4 31 | 12.2 70 | 29.8 77 | 16.2 71 |
BriefMatch [124] | 51.3 | 34.1 40 | 59.4 46 | 30.2 43 | 17.1 16 | 43.6 17 | 16.1 14 | 14.8 13 | 36.3 18 | 13.4 12 | 9.41 17 | 34.3 29 | 6.26 14 | 33.4 48 | 41.2 49 | 31.8 68 | 40.3 107 | 63.5 89 | 42.7 110 | 47.2 89 | 61.1 72 | 59.1 109 | 12.7 73 | 23.4 55 | 21.6 84 |
CPM-Flow [116] | 52.1 | 35.2 43 | 67.0 60 | 25.3 20 | 25.8 76 | 53.6 80 | 28.2 80 | 25.5 73 | 58.5 85 | 27.5 77 | 12.4 49 | 48.0 78 | 8.11 44 | 33.9 53 | 44.2 64 | 27.1 45 | 17.6 9 | 51.8 34 | 19.1 15 | 21.3 11 | 51.7 34 | 22.6 38 | 9.92 59 | 27.2 68 | 11.3 55 |
PGM-C [120] | 52.8 | 35.2 43 | 67.1 62 | 25.4 22 | 25.8 76 | 53.6 80 | 28.2 80 | 25.8 76 | 59.3 88 | 27.5 77 | 12.4 49 | 48.1 79 | 8.16 45 | 33.9 53 | 44.3 67 | 27.1 45 | 17.7 11 | 52.8 46 | 19.1 15 | 20.8 7 | 50.3 25 | 22.4 36 | 9.82 57 | 27.2 68 | 11.5 59 |
S2F-IF [123] | 52.8 | 35.7 49 | 69.0 71 | 26.6 29 | 24.1 65 | 54.0 87 | 26.0 67 | 25.6 75 | 60.9 90 | 25.9 72 | 12.4 49 | 46.6 75 | 8.38 50 | 34.3 57 | 44.2 64 | 27.7 50 | 18.0 16 | 53.2 48 | 19.2 17 | 21.2 10 | 51.7 34 | 22.9 39 | 8.97 49 | 24.9 61 | 9.11 44 |
CostFilter [40] | 54.4 | 43.6 77 | 65.7 56 | 40.8 68 | 20.8 36 | 45.9 29 | 21.0 35 | 18.8 47 | 44.9 48 | 18.3 31 | 17.3 80 | 39.5 49 | 13.9 82 | 26.7 15 | 32.8 11 | 22.7 24 | 30.9 83 | 60.0 81 | 31.6 82 | 59.7 108 | 81.5 124 | 59.3 111 | 4.31 8 | 11.9 14 | 5.93 7 |
EpicFlow [102] | 54.7 | 35.2 43 | 67.2 63 | 25.3 20 | 25.8 76 | 53.8 83 | 28.2 80 | 26.1 78 | 60.1 89 | 27.5 77 | 12.4 49 | 48.1 79 | 8.10 43 | 34.2 56 | 44.5 69 | 28.0 52 | 17.8 13 | 52.7 44 | 19.4 22 | 21.0 8 | 52.1 37 | 22.5 37 | 10.4 62 | 27.3 70 | 12.7 62 |
RFlow [90] | 54.7 | 44.4 79 | 75.2 92 | 50.5 85 | 16.5 13 | 42.1 13 | 17.2 20 | 21.4 57 | 52.2 61 | 16.0 17 | 11.3 38 | 36.2 38 | 7.25 27 | 35.2 64 | 44.3 67 | 32.3 69 | 24.3 56 | 55.6 59 | 22.6 50 | 38.6 58 | 55.3 51 | 41.6 71 | 13.4 75 | 29.9 78 | 16.9 75 |
FlowFields+ [130] | 55.0 | 35.8 51 | 69.2 73 | 26.0 27 | 25.6 74 | 55.3 93 | 27.7 77 | 26.7 79 | 62.9 95 | 27.7 81 | 12.7 56 | 45.9 73 | 8.84 57 | 34.0 55 | 44.2 64 | 26.6 43 | 17.6 9 | 54.9 56 | 19.0 14 | 20.6 6 | 53.9 46 | 22.3 35 | 9.31 53 | 26.5 63 | 8.79 41 |
TV-L1-improved [17] | 56.1 | 27.7 27 | 57.9 42 | 20.5 12 | 18.2 21 | 44.9 23 | 19.1 25 | 19.4 49 | 47.7 54 | 17.0 25 | 10.1 23 | 38.5 44 | 6.75 20 | 35.9 72 | 46.0 79 | 27.3 47 | 43.7 113 | 70.2 110 | 47.5 114 | 51.4 96 | 60.5 71 | 50.3 99 | 10.3 61 | 26.8 67 | 10.8 52 |
FlowFields [110] | 56.9 | 35.7 49 | 68.7 69 | 25.8 26 | 25.6 74 | 55.1 92 | 27.7 77 | 26.8 82 | 62.8 94 | 27.6 80 | 13.0 57 | 46.8 76 | 9.13 60 | 34.6 60 | 44.9 73 | 28.1 53 | 17.8 13 | 54.9 56 | 19.4 22 | 21.3 11 | 54.8 49 | 24.2 43 | 9.25 51 | 26.4 62 | 8.47 37 |
Kuang [131] | 57.6 | 33.2 37 | 67.7 64 | 27.1 34 | 23.4 60 | 56.2 96 | 23.7 45 | 24.5 71 | 62.6 93 | 24.2 69 | 11.7 40 | 44.2 67 | 7.99 39 | 35.7 70 | 46.3 83 | 28.6 55 | 23.7 50 | 59.1 75 | 25.0 66 | 20.2 5 | 50.9 30 | 21.7 33 | 10.6 63 | 28.3 71 | 14.5 66 |
Steered-L1 [118] | 59.0 | 38.7 58 | 67.9 65 | 43.1 73 | 11.6 1 | 34.7 1 | 12.3 2 | 16.3 30 | 41.3 38 | 13.9 13 | 12.1 43 | 38.6 46 | 8.30 48 | 34.5 59 | 43.4 57 | 32.5 71 | 29.4 78 | 61.1 86 | 25.9 68 | 60.6 111 | 67.0 92 | 70.1 122 | 15.9 84 | 30.6 81 | 24.0 88 |
Sparse Occlusion [54] | 59.3 | 38.6 57 | 61.8 50 | 32.5 52 | 26.0 79 | 48.8 44 | 29.5 87 | 20.0 51 | 45.2 49 | 19.2 37 | 14.3 67 | 38.4 43 | 9.67 62 | 34.4 58 | 42.6 54 | 26.7 44 | 25.4 63 | 52.4 39 | 22.4 49 | 67.3 119 | 75.9 116 | 48.3 93 | 8.07 42 | 19.9 44 | 7.36 25 |
DeepFlow [86] | 60.8 | 47.3 85 | 71.9 82 | 64.0 99 | 21.4 40 | 48.2 42 | 22.7 40 | 27.9 86 | 58.2 82 | 31.6 88 | 15.1 72 | 42.7 60 | 10.6 68 | 31.5 44 | 42.1 53 | 22.6 22 | 19.6 19 | 56.7 63 | 19.4 22 | 27.6 26 | 46.2 11 | 39.7 65 | 20.6 93 | 35.3 100 | 28.0 96 |
MLDP_OF [89] | 60.9 | 48.8 88 | 77.3 95 | 52.2 87 | 20.1 31 | 49.6 54 | 19.3 29 | 23.5 68 | 54.6 69 | 18.9 34 | 12.3 48 | 38.6 46 | 7.65 35 | 33.5 51 | 40.9 46 | 29.1 62 | 28.4 74 | 55.9 60 | 31.6 82 | 49.1 93 | 62.2 78 | 60.5 113 | 7.91 41 | 16.8 35 | 8.95 42 |
TF+OM [100] | 62.1 | 39.8 62 | 55.2 39 | 30.4 45 | 20.4 34 | 41.0 8 | 23.5 43 | 19.5 50 | 39.4 30 | 28.0 82 | 18.4 83 | 37.0 41 | 18.0 88 | 35.0 62 | 41.1 47 | 39.6 90 | 29.6 79 | 52.6 42 | 29.1 77 | 49.0 92 | 66.8 91 | 43.6 78 | 14.4 77 | 29.3 74 | 18.0 77 |
CombBMOF [113] | 64.0 | 42.4 71 | 71.5 80 | 31.3 49 | 25.2 70 | 52.9 77 | 25.1 61 | 17.9 41 | 45.8 50 | 16.1 18 | 14.2 65 | 41.7 57 | 11.4 71 | 33.5 51 | 40.2 43 | 29.6 63 | 34.5 90 | 59.9 80 | 37.3 96 | 55.2 105 | 69.9 101 | 46.5 90 | 6.78 33 | 16.8 35 | 8.62 38 |
EPPM w/o HM [88] | 64.5 | 43.1 75 | 72.4 84 | 38.1 64 | 18.7 24 | 52.5 71 | 16.9 18 | 21.3 56 | 56.2 74 | 17.5 26 | 16.2 76 | 45.3 72 | 12.7 79 | 33.4 48 | 39.6 40 | 30.0 64 | 33.5 86 | 65.4 95 | 33.8 88 | 45.5 79 | 66.1 89 | 65.5 119 | 6.88 34 | 18.1 40 | 9.16 46 |
Complementary OF [21] | 65.8 | 51.9 95 | 74.9 91 | 59.3 95 | 14.2 3 | 41.6 10 | 13.7 3 | 20.4 52 | 46.6 51 | 19.7 46 | 22.2 90 | 40.8 53 | 21.0 93 | 36.0 74 | 43.4 57 | 38.5 88 | 33.9 89 | 63.8 90 | 31.6 82 | 31.1 38 | 51.9 36 | 36.2 58 | 18.9 90 | 34.4 98 | 29.4 98 |
Aniso. Huber-L1 [22] | 66.6 | 33.9 38 | 65.1 55 | 32.8 54 | 34.0 94 | 54.0 87 | 40.0 94 | 27.9 86 | 55.0 71 | 38.4 93 | 15.2 73 | 49.9 83 | 12.0 74 | 35.3 66 | 44.6 70 | 28.5 54 | 23.9 53 | 55.9 60 | 20.7 34 | 50.6 94 | 62.1 77 | 39.7 65 | 8.15 43 | 20.7 46 | 8.39 35 |
ComplOF-FED-GPU [35] | 68.8 | 49.5 90 | 75.7 94 | 55.3 90 | 15.3 7 | 47.0 36 | 13.8 4 | 21.1 55 | 52.7 64 | 16.1 18 | 17.1 79 | 40.6 52 | 14.2 83 | 35.7 70 | 45.1 76 | 32.5 71 | 35.3 93 | 67.5 103 | 34.4 90 | 46.5 86 | 59.0 66 | 50.8 100 | 12.8 74 | 29.6 75 | 16.6 74 |
ACK-Prior [27] | 68.9 | 55.9 97 | 72.7 86 | 59.3 95 | 17.5 18 | 43.3 15 | 16.0 13 | 17.8 39 | 42.3 39 | 16.3 22 | 17.6 81 | 41.3 55 | 12.0 74 | 35.3 66 | 41.1 47 | 35.9 79 | 37.4 103 | 59.6 78 | 34.3 89 | 59.8 110 | 61.1 72 | 74.7 123 | 17.7 89 | 29.2 73 | 27.4 91 |
TCOF [69] | 68.9 | 45.0 80 | 70.0 74 | 51.5 86 | 25.5 73 | 53.7 82 | 26.7 70 | 26.7 79 | 56.2 74 | 32.0 89 | 21.9 89 | 43.1 63 | 22.2 95 | 37.8 84 | 48.9 96 | 25.7 41 | 18.8 18 | 44.7 7 | 20.0 29 | 52.1 100 | 67.5 94 | 25.8 44 | 10.7 65 | 26.7 65 | 11.4 57 |
Rannacher [23] | 69.0 | 43.1 75 | 71.0 78 | 45.2 77 | 24.1 65 | 49.4 49 | 26.4 69 | 26.0 77 | 56.9 78 | 26.0 74 | 14.2 65 | 42.7 60 | 10.5 67 | 37.1 81 | 47.9 91 | 30.7 66 | 32.3 84 | 65.2 94 | 27.0 72 | 44.0 76 | 56.0 58 | 39.7 65 | 7.83 39 | 21.2 50 | 9.19 47 |
F-TV-L1 [15] | 71.2 | 66.8 105 | 84.2 104 | 77.3 107 | 27.1 86 | 52.0 67 | 29.1 86 | 27.2 83 | 57.3 80 | 24.2 69 | 24.1 94 | 52.0 87 | 19.5 91 | 39.3 91 | 47.7 90 | 39.3 89 | 24.2 55 | 56.5 62 | 24.9 64 | 33.2 44 | 53.7 45 | 20.1 28 | 6.69 32 | 18.6 41 | 5.94 8 |
ROF-ND [107] | 71.2 | 49.2 89 | 71.5 80 | 49.4 83 | 22.5 56 | 46.2 33 | 20.6 31 | 21.4 57 | 50.0 59 | 18.1 29 | 23.1 92 | 53.7 91 | 16.0 85 | 35.9 72 | 46.1 81 | 28.6 55 | 33.5 86 | 58.5 71 | 30.3 80 | 60.7 112 | 70.5 102 | 60.4 112 | 9.67 55 | 20.9 48 | 10.2 50 |
LDOF [28] | 71.5 | 41.7 69 | 70.7 75 | 47.2 80 | 24.0 64 | 53.9 86 | 24.6 57 | 26.7 79 | 58.4 84 | 25.5 71 | 15.8 74 | 57.4 97 | 10.2 65 | 36.0 74 | 45.3 77 | 34.8 77 | 22.1 34 | 58.1 70 | 21.3 41 | 30.6 35 | 56.8 60 | 23.4 40 | 22.5 102 | 38.6 107 | 30.2 99 |
SIOF [67] | 72.4 | 50.3 93 | 66.0 57 | 47.1 79 | 19.8 28 | 48.4 43 | 20.7 32 | 29.8 93 | 55.1 72 | 32.6 91 | 25.9 96 | 48.3 81 | 25.0 97 | 37.7 82 | 46.4 84 | 36.8 82 | 32.9 85 | 58.6 72 | 35.6 94 | 37.2 54 | 53.1 43 | 18.6 20 | 16.8 87 | 33.0 90 | 21.3 83 |
LocallyOriented [52] | 73.2 | 39.4 60 | 60.5 47 | 35.7 58 | 27.9 89 | 57.8 100 | 28.5 84 | 28.1 89 | 58.3 83 | 30.6 87 | 13.9 62 | 41.3 55 | 10.1 63 | 37.8 84 | 47.3 88 | 33.0 75 | 24.8 62 | 52.5 41 | 28.1 74 | 39.4 65 | 62.4 79 | 37.5 61 | 15.7 82 | 33.0 90 | 18.2 79 |
Second-order prior [8] | 73.5 | 37.6 55 | 70.9 77 | 37.2 62 | 22.4 55 | 51.2 60 | 23.7 45 | 24.5 71 | 59.1 87 | 22.6 63 | 11.2 37 | 41.2 54 | 8.48 54 | 37.9 86 | 49.6 103 | 28.8 59 | 29.0 76 | 68.8 107 | 26.0 69 | 55.5 106 | 64.7 84 | 52.7 103 | 14.7 79 | 34.1 96 | 17.3 76 |
CRTflow [80] | 73.6 | 40.9 64 | 72.5 85 | 36.2 60 | 21.3 39 | 49.4 49 | 21.8 36 | 22.9 64 | 57.5 81 | 19.0 35 | 14.0 63 | 44.7 69 | 10.3 66 | 35.4 69 | 45.0 75 | 30.4 65 | 46.6 117 | 73.4 112 | 53.8 118 | 38.8 60 | 65.5 86 | 38.2 62 | 19.5 92 | 38.5 106 | 27.6 94 |
NL-TV-NCC [25] | 73.8 | 46.1 82 | 68.3 67 | 43.4 74 | 25.2 70 | 55.3 93 | 23.5 43 | 21.8 62 | 47.2 52 | 16.9 24 | 16.9 78 | 44.1 66 | 11.9 73 | 38.5 88 | 49.1 100 | 27.3 47 | 36.5 99 | 65.7 96 | 34.9 92 | 46.2 81 | 75.7 114 | 45.7 84 | 12.6 71 | 28.8 72 | 9.10 43 |
Brox et al. [5] | 73.9 | 43.7 78 | 74.4 89 | 56.4 92 | 27.0 85 | 52.5 71 | 30.5 89 | 23.4 67 | 54.5 68 | 23.3 66 | 13.4 58 | 50.0 84 | 8.66 56 | 39.8 94 | 46.5 85 | 47.6 106 | 21.6 29 | 59.8 79 | 22.8 57 | 30.9 36 | 59.3 67 | 7.61 3 | 23.1 105 | 37.0 104 | 33.4 106 |
FlowNetS+ft+v [112] | 74.0 | 36.8 54 | 67.0 60 | 39.4 65 | 25.3 72 | 52.1 69 | 27.6 76 | 27.8 85 | 57.2 79 | 35.5 92 | 13.5 59 | 50.9 85 | 9.44 61 | 40.1 95 | 49.5 102 | 36.8 82 | 20.9 24 | 57.0 64 | 20.8 36 | 46.3 84 | 66.3 90 | 41.0 69 | 17.4 88 | 34.3 97 | 24.1 89 |
DF-Auto [115] | 74.0 | 41.6 68 | 64.2 53 | 32.8 54 | 42.0 99 | 58.8 103 | 49.6 100 | 34.8 99 | 62.2 92 | 47.2 100 | 20.7 87 | 53.4 90 | 14.5 84 | 36.2 77 | 44.7 71 | 37.2 85 | 15.1 3 | 42.9 6 | 17.4 8 | 45.3 78 | 69.0 98 | 13.0 7 | 24.2 108 | 37.7 105 | 31.9 102 |
TriangleFlow [30] | 74.7 | 41.5 67 | 63.2 51 | 42.6 72 | 21.4 40 | 52.4 70 | 20.2 30 | 21.7 61 | 53.6 67 | 16.2 20 | 14.8 69 | 44.4 68 | 10.9 69 | 43.2 105 | 52.9 112 | 43.4 97 | 36.8 102 | 65.9 97 | 38.8 99 | 42.2 72 | 65.4 85 | 41.8 73 | 15.8 83 | 35.2 99 | 22.5 85 |
SRR-TVOF-NL [91] | 74.9 | 47.6 86 | 69.1 72 | 41.9 71 | 23.3 58 | 52.7 75 | 23.3 41 | 25.5 73 | 56.8 77 | 25.9 72 | 13.5 59 | 47.9 77 | 8.09 42 | 36.9 80 | 43.8 62 | 32.9 74 | 25.8 64 | 57.7 68 | 22.6 50 | 62.8 116 | 75.2 112 | 49.1 96 | 21.0 95 | 29.7 76 | 31.6 101 |
DPOF [18] | 75.8 | 45.3 81 | 68.9 70 | 37.6 63 | 26.7 84 | 56.9 97 | 26.9 72 | 24.3 70 | 54.6 69 | 26.2 75 | 18.6 84 | 54.6 94 | 13.6 81 | 33.3 47 | 43.1 55 | 28.9 60 | 27.6 72 | 60.8 83 | 26.3 70 | 47.2 89 | 55.3 51 | 76.0 125 | 14.3 76 | 31.0 84 | 15.3 68 |
Bartels [41] | 76.6 | 48.6 87 | 63.2 51 | 61.4 98 | 23.4 60 | 44.0 19 | 27.1 74 | 21.4 57 | 44.6 46 | 23.8 68 | 26.2 97 | 43.0 62 | 25.4 98 | 36.8 78 | 44.7 71 | 41.7 94 | 33.7 88 | 60.0 81 | 41.7 107 | 52.6 101 | 67.2 93 | 61.1 114 | 11.2 67 | 23.4 55 | 16.3 72 |
Dynamic MRF [7] | 77.0 | 49.5 90 | 78.0 96 | 55.8 91 | 17.2 17 | 47.4 38 | 16.5 17 | 21.6 60 | 56.3 76 | 16.2 20 | 14.8 69 | 46.4 74 | 12.5 77 | 41.2 99 | 49.0 98 | 45.1 101 | 35.3 93 | 70.7 111 | 38.5 98 | 37.1 53 | 57.7 64 | 55.1 105 | 21.3 97 | 36.7 103 | 31.2 100 |
SuperFlow [81] | 77.2 | 35.2 43 | 61.1 48 | 34.4 56 | 35.2 95 | 53.5 79 | 42.5 95 | 27.7 84 | 52.5 63 | 43.5 99 | 27.5 98 | 60.5 101 | 27.6 99 | 36.0 74 | 43.3 56 | 42.2 95 | 22.6 41 | 59.2 77 | 22.2 47 | 46.2 81 | 62.0 76 | 23.4 40 | 21.8 100 | 36.0 101 | 32.5 104 |
CBF [12] | 77.8 | 41.4 65 | 74.0 88 | 48.5 81 | 40.2 98 | 51.5 64 | 51.7 102 | 22.9 64 | 50.8 60 | 28.5 83 | 14.3 67 | 44.7 69 | 11.2 70 | 38.3 87 | 46.1 81 | 36.1 80 | 26.3 66 | 55.1 58 | 24.9 64 | 61.5 113 | 71.0 103 | 52.0 102 | 11.6 69 | 26.7 65 | 14.8 67 |
Local-TV-L1 [65] | 78.0 | 56.8 99 | 79.1 97 | 74.5 103 | 39.5 97 | 53.8 83 | 46.1 97 | 38.1 100 | 66.2 98 | 43.1 98 | 23.9 93 | 52.9 89 | 21.1 94 | 32.3 46 | 41.4 51 | 27.5 49 | 23.2 44 | 54.8 55 | 22.7 55 | 25.8 20 | 47.5 14 | 33.4 55 | 26.9 111 | 40.5 109 | 40.5 115 |
CLG-TV [48] | 78.1 | 41.4 65 | 68.0 66 | 40.8 68 | 37.0 96 | 53.1 78 | 45.3 96 | 30.9 94 | 58.7 86 | 40.2 95 | 22.8 91 | 62.0 102 | 19.3 90 | 39.0 90 | 47.6 89 | 38.2 87 | 27.2 68 | 61.0 85 | 27.1 73 | 46.2 81 | 57.8 65 | 29.3 50 | 9.74 56 | 24.6 60 | 9.11 44 |
CNN-flow-warp+ref [117] | 78.4 | 42.6 73 | 71.2 79 | 49.8 84 | 31.6 93 | 53.8 83 | 37.3 92 | 32.7 96 | 63.8 96 | 42.7 97 | 16.0 75 | 55.1 95 | 12.1 76 | 38.6 89 | 46.0 79 | 43.8 99 | 23.3 45 | 59.1 75 | 23.6 60 | 23.5 17 | 50.9 30 | 21.9 34 | 24.2 108 | 36.2 102 | 32.9 105 |
HBM-GC [105] | 80.0 | 73.5 113 | 79.7 98 | 79.4 109 | 30.0 90 | 49.7 56 | 33.6 90 | 29.3 92 | 47.8 55 | 30.4 85 | 35.4 101 | 45.2 71 | 33.3 101 | 30.5 38 | 35.1 20 | 32.6 73 | 34.6 91 | 52.0 35 | 35.4 93 | 70.9 122 | 80.1 120 | 62.6 115 | 8.83 48 | 19.1 42 | 13.0 63 |
TriFlow [95] | 83.5 | 47.1 84 | 66.5 59 | 41.1 70 | 31.2 92 | 49.6 54 | 37.3 92 | 27.9 86 | 52.3 62 | 39.4 94 | 24.7 95 | 49.3 82 | 22.3 96 | 37.7 82 | 43.5 59 | 43.1 96 | 28.4 74 | 52.7 44 | 29.0 76 | 76.7 126 | 73.7 107 | 99.5 129 | 16.2 85 | 30.5 80 | 20.1 81 |
p-harmonic [29] | 85.7 | 50.4 94 | 86.6 114 | 56.5 94 | 27.1 86 | 54.5 89 | 28.9 85 | 32.9 97 | 69.3 104 | 30.4 85 | 19.8 85 | 65.1 105 | 16.2 86 | 39.6 93 | 47.2 87 | 40.3 92 | 30.4 81 | 66.5 99 | 32.2 86 | 45.6 80 | 64.4 82 | 28.9 49 | 10.2 60 | 24.1 59 | 13.2 64 |
Learning Flow [11] | 86.2 | 42.9 74 | 70.7 75 | 44.8 76 | 30.2 91 | 54.7 90 | 34.7 91 | 28.2 90 | 55.9 73 | 32.3 90 | 17.6 81 | 57.1 96 | 12.6 78 | 44.0 108 | 52.6 110 | 47.8 108 | 30.5 82 | 64.6 92 | 30.3 80 | 46.9 87 | 63.3 80 | 42.8 77 | 14.7 79 | 31.6 88 | 16.3 72 |
Fusion [6] | 87.1 | 40.5 63 | 75.6 93 | 45.9 78 | 20.0 29 | 50.0 57 | 22.5 38 | 20.8 54 | 52.8 65 | 22.8 64 | 16.2 76 | 52.8 88 | 13.5 80 | 43.1 104 | 49.0 98 | 47.5 103 | 39.6 106 | 67.8 105 | 43.8 112 | 63.9 117 | 75.0 111 | 46.3 89 | 35.5 120 | 42.6 115 | 53.3 125 |
StereoFlow [44] | 87.3 | 95.9 129 | 96.0 128 | 97.4 129 | 88.3 129 | 96.2 129 | 86.2 125 | 82.6 126 | 94.8 128 | 73.7 123 | 91.4 128 | 96.3 128 | 90.3 128 | 53.0 119 | 61.6 123 | 52.8 112 | 11.2 1 | 39.3 3 | 11.7 1 | 10.5 1 | 42.5 3 | 1.70 1 | 11.5 68 | 23.6 57 | 18.0 77 |
Shiralkar [42] | 89.2 | 46.1 82 | 85.6 110 | 54.3 89 | 19.7 27 | 57.7 99 | 18.2 21 | 28.2 90 | 70.8 105 | 19.3 38 | 20.5 86 | 59.0 99 | 18.4 89 | 39.5 92 | 49.7 104 | 36.3 81 | 40.4 108 | 76.1 114 | 41.2 106 | 51.9 98 | 65.8 87 | 64.2 117 | 21.0 95 | 42.4 114 | 25.3 90 |
SegOF [10] | 92.5 | 56.3 98 | 71.9 82 | 37.1 61 | 57.3 113 | 62.9 110 | 68.3 115 | 46.0 106 | 69.0 103 | 57.2 112 | 41.0 103 | 59.5 100 | 37.2 102 | 43.5 106 | 48.3 94 | 56.4 116 | 38.2 104 | 69.6 109 | 39.1 100 | 17.9 3 | 64.5 83 | 3.40 2 | 22.7 104 | 33.0 90 | 32.0 103 |
StereoOF-V1MT [119] | 93.0 | 49.7 92 | 86.0 111 | 56.4 92 | 21.2 37 | 68.8 113 | 16.3 16 | 32.2 95 | 80.7 112 | 20.8 56 | 21.3 88 | 66.1 107 | 17.4 87 | 47.0 114 | 57.0 114 | 47.5 103 | 41.7 111 | 81.2 118 | 40.9 104 | 38.6 58 | 68.1 96 | 48.6 94 | 23.2 106 | 42.2 113 | 27.7 95 |
Ad-TV-NDC [36] | 93.5 | 73.7 114 | 85.4 108 | 89.5 124 | 56.9 112 | 60.4 106 | 67.5 114 | 51.0 110 | 75.9 108 | 57.6 113 | 45.7 106 | 65.7 106 | 47.9 109 | 35.3 66 | 45.3 77 | 28.9 60 | 27.3 71 | 57.2 66 | 28.2 75 | 34.6 46 | 55.0 50 | 27.3 47 | 34.0 117 | 48.7 121 | 47.5 119 |
Modified CLG [34] | 95.8 | 68.7 108 | 80.5 99 | 76.1 105 | 52.0 109 | 61.0 107 | 63.6 111 | 51.9 111 | 79.4 110 | 55.6 110 | 47.4 109 | 72.1 112 | 46.7 108 | 41.2 99 | 49.7 104 | 46.0 102 | 26.0 65 | 64.7 93 | 26.7 71 | 31.4 41 | 55.6 54 | 19.9 27 | 29.0 114 | 43.8 117 | 39.9 114 |
IAOF2 [51] | 97.2 | 54.9 96 | 73.7 87 | 53.9 88 | 42.6 100 | 58.3 101 | 50.7 101 | 33.9 98 | 61.9 91 | 42.1 96 | 64.4 118 | 75.7 115 | 74.3 120 | 41.5 101 | 49.9 107 | 37.1 84 | 36.4 98 | 64.0 91 | 34.4 90 | 59.7 108 | 69.6 100 | 41.3 70 | 19.4 91 | 33.4 94 | 23.0 87 |
Filter Flow [19] | 99.2 | 62.9 100 | 74.4 89 | 60.8 97 | 42.8 101 | 60.1 105 | 49.4 99 | 42.5 102 | 66.0 97 | 51.2 103 | 52.1 114 | 69.5 109 | 50.2 110 | 44.8 110 | 49.7 104 | 54.4 114 | 41.9 112 | 66.7 100 | 43.6 111 | 74.3 125 | 88.9 127 | 42.6 76 | 10.6 63 | 21.6 52 | 12.6 61 |
GroupFlow [9] | 99.9 | 66.4 103 | 85.2 107 | 80.8 112 | 61.6 116 | 75.4 120 | 69.0 116 | 51.9 111 | 83.6 115 | 57.0 111 | 33.5 100 | 63.9 103 | 32.5 100 | 49.6 115 | 61.0 118 | 39.9 91 | 51.3 122 | 81.7 119 | 59.4 122 | 22.8 16 | 51.1 32 | 16.5 11 | 28.0 113 | 41.9 112 | 37.9 112 |
SPSA-learn [13] | 100.8 | 65.1 101 | 87.4 117 | 72.7 102 | 45.7 105 | 59.3 104 | 53.4 105 | 45.2 105 | 74.7 107 | 52.2 105 | 41.6 104 | 69.9 111 | 42.5 104 | 42.7 103 | 48.9 96 | 48.7 110 | 38.8 105 | 69.0 108 | 42.5 109 | 39.1 63 | 61.9 75 | 19.3 22 | 36.0 121 | 45.6 118 | 48.3 120 |
2D-CLG [1] | 100.9 | 77.2 117 | 82.3 102 | 75.4 104 | 61.5 115 | 65.9 112 | 73.7 119 | 63.2 120 | 89.6 122 | 60.8 118 | 82.8 126 | 88.3 123 | 86.8 126 | 43.5 106 | 49.3 101 | 54.8 115 | 35.1 92 | 67.5 103 | 36.1 95 | 21.3 11 | 50.8 29 | 15.5 9 | 34.4 119 | 46.3 120 | 46.0 117 |
BlockOverlap [61] | 101.5 | 77.2 117 | 86.0 111 | 82.8 114 | 48.2 106 | 55.8 95 | 57.6 108 | 46.9 108 | 66.9 99 | 51.9 104 | 49.1 110 | 54.1 92 | 51.2 111 | 36.8 78 | 41.3 50 | 47.5 103 | 40.5 109 | 59.0 74 | 39.6 102 | 68.9 121 | 80.2 121 | 65.1 118 | 20.8 94 | 30.8 82 | 34.9 108 |
IAOF [50] | 101.5 | 66.3 102 | 81.3 101 | 77.8 108 | 50.1 108 | 58.4 102 | 59.7 109 | 45.0 104 | 74.1 106 | 49.6 102 | 50.8 111 | 68.2 108 | 58.0 116 | 40.2 96 | 48.7 95 | 37.8 86 | 36.7 100 | 66.9 101 | 33.5 87 | 54.9 103 | 63.5 81 | 40.8 68 | 30.1 116 | 41.3 111 | 43.5 116 |
HBpMotionGpu [43] | 102.1 | 67.0 106 | 80.7 100 | 72.3 101 | 55.3 111 | 57.3 98 | 66.7 113 | 44.7 103 | 67.2 101 | 54.1 108 | 39.5 102 | 57.8 98 | 38.4 103 | 42.0 102 | 48.2 93 | 48.3 109 | 35.9 95 | 60.9 84 | 39.2 101 | 65.1 118 | 72.0 105 | 50.1 98 | 22.6 103 | 32.5 89 | 36.9 109 |
Black & Anandan [4] | 103.7 | 70.3 110 | 88.0 118 | 84.1 115 | 45.5 104 | 61.4 108 | 52.0 103 | 47.4 109 | 77.3 109 | 52.9 106 | 42.3 105 | 77.5 116 | 42.8 105 | 44.0 108 | 51.8 108 | 45.0 100 | 35.9 95 | 75.9 113 | 38.3 97 | 50.8 95 | 71.3 104 | 17.8 18 | 29.8 115 | 42.7 116 | 37.6 111 |
GraphCuts [14] | 104.0 | 66.6 104 | 87.0 115 | 80.0 111 | 43.1 102 | 63.0 111 | 46.1 97 | 41.8 101 | 67.0 100 | 53.4 107 | 28.5 99 | 64.0 104 | 20.8 92 | 40.2 96 | 48.1 92 | 43.5 98 | 46.5 115 | 63.4 88 | 40.5 103 | 62.7 115 | 75.4 113 | 69.5 121 | 23.8 107 | 33.3 93 | 38.5 113 |
FlowNet2 [122] | 105.6 | 78.8 119 | 86.2 113 | 79.4 109 | 63.5 120 | 70.2 115 | 72.8 118 | 57.2 117 | 82.0 113 | 59.7 117 | 46.2 107 | 51.4 86 | 45.6 107 | 45.3 111 | 54.0 113 | 41.1 93 | 36.7 100 | 67.3 102 | 41.0 105 | 67.6 120 | 80.8 122 | 55.1 105 | 14.5 78 | 30.0 79 | 13.9 65 |
Nguyen [33] | 107.8 | 75.6 116 | 85.4 108 | 85.8 117 | 67.0 121 | 61.6 109 | 83.0 123 | 57.1 116 | 80.2 111 | 64.1 120 | 70.8 119 | 80.2 118 | 77.4 122 | 45.9 113 | 52.2 109 | 56.4 116 | 36.3 97 | 68.1 106 | 42.0 108 | 41.4 70 | 66.0 88 | 19.7 25 | 34.1 118 | 45.6 118 | 46.1 118 |
SILK [79] | 107.8 | 72.5 111 | 85.1 106 | 88.3 121 | 61.9 117 | 71.8 116 | 73.7 119 | 54.9 114 | 85.3 116 | 58.0 115 | 53.6 115 | 69.8 110 | 54.6 115 | 52.8 117 | 57.9 115 | 61.8 120 | 46.5 115 | 77.6 115 | 48.9 115 | 31.3 39 | 54.3 48 | 38.9 63 | 37.8 122 | 50.6 122 | 49.7 122 |
2bit-BM-tele [98] | 107.9 | 82.4 121 | 87.2 116 | 91.8 125 | 44.4 103 | 54.7 90 | 52.9 104 | 46.0 106 | 68.3 102 | 47.4 101 | 51.5 113 | 54.4 93 | 53.4 114 | 40.5 98 | 47.1 86 | 47.7 107 | 47.9 118 | 66.4 98 | 53.1 116 | 71.7 123 | 83.6 125 | 75.1 124 | 21.9 101 | 39.3 108 | 29.2 97 |
UnFlow [129] | 109.5 | 89.6 126 | 94.1 124 | 86.4 118 | 72.2 123 | 83.9 126 | 77.9 122 | 71.4 123 | 93.2 125 | 69.8 121 | 54.8 116 | 74.4 113 | 51.4 112 | 62.0 124 | 66.9 125 | 69.1 127 | 50.0 120 | 80.9 116 | 57.1 119 | 53.2 102 | 69.0 98 | 7.68 4 | 15.6 81 | 30.8 82 | 21.0 82 |
Periodicity [78] | 110.8 | 68.9 109 | 83.5 103 | 65.5 100 | 52.2 110 | 69.8 114 | 57.0 107 | 78.4 125 | 82.5 114 | 87.2 127 | 47.2 108 | 74.7 114 | 45.5 106 | 69.7 129 | 81.9 129 | 65.6 124 | 59.5 124 | 84.9 126 | 60.7 123 | 36.3 52 | 79.8 119 | 19.2 21 | 40.7 124 | 66.5 128 | 53.1 124 |
Horn & Schunck [3] | 111.2 | 74.1 115 | 93.2 123 | 86.9 119 | 49.1 107 | 73.8 117 | 53.9 106 | 53.1 113 | 89.0 121 | 54.6 109 | 50.9 112 | 81.4 119 | 52.4 113 | 51.3 116 | 58.8 116 | 54.3 113 | 41.2 110 | 82.3 120 | 44.6 113 | 55.0 104 | 74.3 109 | 19.6 24 | 40.7 124 | 56.8 124 | 48.8 121 |
Heeger++ [104] | 113.4 | 86.1 123 | 91.0 120 | 77.1 106 | 67.6 122 | 91.6 128 | 65.1 112 | 85.6 128 | 94.6 127 | 83.6 126 | 71.0 120 | 88.2 122 | 68.8 118 | 62.9 125 | 69.8 127 | 67.3 125 | 69.4 128 | 91.0 128 | 70.8 126 | 40.2 68 | 80.9 123 | 26.3 46 | 21.7 98 | 31.2 85 | 27.4 91 |
SLK [47] | 114.4 | 67.5 107 | 90.3 119 | 82.1 113 | 72.2 123 | 84.7 127 | 84.8 124 | 58.4 118 | 94.0 126 | 58.1 116 | 78.1 123 | 82.5 120 | 84.6 125 | 55.4 122 | 61.5 121 | 68.1 126 | 49.4 119 | 83.7 124 | 57.7 120 | 36.2 51 | 68.1 96 | 26.2 45 | 50.3 127 | 60.0 125 | 65.2 128 |
FFV1MT [106] | 115.7 | 85.0 122 | 92.0 121 | 84.4 116 | 60.6 114 | 83.8 125 | 60.8 110 | 85.4 127 | 92.2 124 | 88.2 128 | 71.2 121 | 89.9 125 | 69.1 119 | 64.0 127 | 69.3 126 | 78.0 128 | 69.2 127 | 91.5 129 | 73.2 128 | 51.7 97 | 73.9 108 | 45.3 81 | 21.7 98 | 31.2 85 | 27.4 91 |
TI-DOFE [24] | 116.4 | 90.7 127 | 94.6 126 | 97.1 128 | 76.9 127 | 79.5 124 | 89.4 128 | 73.1 124 | 96.1 129 | 74.4 124 | 84.6 127 | 93.6 127 | 88.3 127 | 52.9 118 | 59.9 117 | 63.9 122 | 44.5 114 | 83.6 123 | 53.5 117 | 42.9 73 | 68.0 95 | 17.0 16 | 50.5 128 | 65.5 127 | 62.4 126 |
FOLKI [16] | 116.6 | 72.5 111 | 84.5 105 | 87.5 120 | 62.3 118 | 74.9 119 | 74.0 121 | 56.9 115 | 87.2 118 | 57.7 114 | 59.8 117 | 78.1 117 | 65.4 117 | 53.3 120 | 61.2 120 | 62.7 121 | 50.9 121 | 81.0 117 | 62.7 124 | 47.3 91 | 73.3 106 | 56.8 108 | 49.0 126 | 62.9 126 | 64.3 127 |
PGAM+LK [55] | 121.9 | 79.4 120 | 92.7 122 | 88.7 122 | 62.9 119 | 76.8 123 | 71.9 117 | 59.9 119 | 88.3 120 | 62.8 119 | 74.9 122 | 90.6 126 | 75.6 121 | 54.4 121 | 61.0 118 | 64.6 123 | 58.1 123 | 82.7 121 | 58.6 121 | 77.6 127 | 85.6 126 | 78.1 126 | 38.8 123 | 52.7 123 | 50.7 123 |
Adaptive flow [45] | 122.3 | 91.3 128 | 95.7 127 | 96.2 126 | 75.8 126 | 75.9 121 | 86.2 125 | 68.9 121 | 85.6 117 | 72.4 122 | 80.6 125 | 85.2 121 | 83.9 124 | 57.3 123 | 61.5 121 | 60.2 119 | 66.7 125 | 84.1 125 | 70.4 125 | 90.2 128 | 92.7 128 | 95.0 127 | 27.7 112 | 40.5 109 | 37.0 110 |
HCIC-L [99] | 123.1 | 88.6 125 | 96.7 129 | 89.3 123 | 80.8 128 | 74.4 118 | 93.1 129 | 86.6 129 | 87.2 118 | 95.2 129 | 95.8 129 | 97.4 129 | 96.9 129 | 63.4 126 | 66.7 124 | 57.8 118 | 68.9 126 | 82.7 121 | 73.1 127 | 96.0 129 | 95.9 129 | 98.6 128 | 25.3 110 | 33.9 95 | 34.7 107 |
Pyramid LK [2] | 125.3 | 86.7 124 | 94.5 125 | 96.2 126 | 73.1 125 | 76.5 122 | 86.4 127 | 70.8 122 | 89.6 122 | 78.5 125 | 78.1 123 | 88.6 124 | 82.7 123 | 68.8 128 | 76.4 128 | 80.4 129 | 75.7 129 | 85.1 127 | 78.1 129 | 73.1 124 | 79.6 118 | 69.3 120 | 60.8 129 | 74.5 129 | 79.9 129 |
AdaConv-v1 [126] | 130.0 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 100.0 130 | 99.7 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 |
SepConv-v1 [127] | 130.0 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 100.0 130 | 99.7 130 | 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. |