Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
A99 interpolation error |
avg. |
Mequon (Hidden texture) im0 GT im1 |
Schefflera (Hidden texture) im0 GT im1 |
Urban (Synthetic) im0 GT im1 |
Teddy (Stereo) im0 GT im1 |
Backyard (High-speed camera) im0 GT im1 |
Basketball (High-speed camera) im0 GT im1 |
Dumptruck (High-speed camera) im0 GT im1 |
Evergreen (High-speed camera) im0 GT 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 | |
PMMST [114] | 10.3 | 11.2 10 | 21.1 6 | 2.71 2 | 13.8 8 | 19.7 7 | 3.65 22 | 10.3 1 | 19.2 7 | 2.71 1 | 16.8 4 | 30.8 22 | 7.53 31 | 41.1 5 | 51.1 7 | 10.0 17 | 24.6 2 | 43.0 6 | 4.93 12 | 34.2 10 | 70.9 12 | 4.04 8 | 28.8 14 | 45.4 24 | 3.42 9 |
MDP-Flow2 [68] | 10.7 | 11.0 3 | 20.7 5 | 2.71 2 | 13.9 10 | 19.9 9 | 3.46 2 | 10.3 1 | 20.3 14 | 3.00 2 | 16.7 3 | 30.0 14 | 7.35 7 | 41.0 4 | 50.7 4 | 10.1 29 | 27.1 35 | 44.9 19 | 4.97 19 | 33.6 3 | 70.1 7 | 3.92 3 | 29.2 18 | 47.0 35 | 3.42 9 |
NNF-Local [87] | 20.0 | 11.4 16 | 21.6 9 | 2.71 2 | 12.8 1 | 18.4 2 | 3.56 4 | 10.4 3 | 20.0 12 | 3.00 2 | 19.8 58 | 37.3 88 | 7.35 7 | 41.5 11 | 51.4 9 | 10.0 17 | 28.2 62 | 47.3 38 | 5.07 46 | 34.5 13 | 71.9 23 | 4.04 8 | 29.1 17 | 46.1 30 | 3.37 2 |
SepConv-v1 [127] | 20.5 | 9.68 1 | 19.1 1 | 2.52 1 | 15.4 36 | 20.1 11 | 5.26 101 | 11.0 10 | 16.7 1 | 3.87 95 | 20.4 72 | 26.8 1 | 9.59 117 | 41.9 12 | 52.5 16 | 9.00 2 | 24.7 3 | 42.4 3 | 4.69 1 | 30.7 1 | 67.4 1 | 3.92 3 | 24.7 1 | 35.8 1 | 3.32 1 |
NN-field [71] | 22.8 | 11.5 24 | 22.9 23 | 2.71 2 | 13.0 3 | 18.6 3 | 3.42 1 | 12.3 77 | 19.7 8 | 3.00 2 | 21.1 80 | 39.8 102 | 7.44 17 | 41.4 9 | 51.4 9 | 10.0 17 | 27.5 43 | 46.4 28 | 4.97 19 | 33.8 6 | 71.0 14 | 4.04 8 | 29.3 20 | 46.2 31 | 3.37 2 |
NNF-EAC [103] | 26.8 | 11.5 24 | 21.7 10 | 3.11 73 | 14.5 22 | 21.0 24 | 3.70 24 | 12.3 77 | 22.6 35 | 3.00 2 | 17.7 16 | 32.4 41 | 7.55 38 | 43.2 38 | 55.1 42 | 10.1 29 | 25.1 6 | 43.8 9 | 4.90 6 | 34.0 8 | 70.5 9 | 4.08 38 | 29.4 22 | 47.5 40 | 3.42 9 |
DeepFlow2 [108] | 28.7 | 11.4 16 | 23.5 27 | 3.00 60 | 16.7 58 | 23.0 60 | 4.04 56 | 11.0 10 | 20.3 14 | 3.00 2 | 19.0 47 | 29.8 12 | 7.53 31 | 42.7 25 | 54.0 25 | 10.3 52 | 25.0 4 | 43.0 6 | 4.93 12 | 35.2 27 | 73.8 34 | 4.04 8 | 28.9 15 | 44.9 21 | 3.56 67 |
DeepFlow [86] | 28.9 | 11.3 14 | 24.2 40 | 3.00 60 | 16.6 57 | 23.0 60 | 4.32 69 | 11.0 10 | 20.3 14 | 3.00 2 | 19.3 49 | 28.1 6 | 7.59 46 | 42.7 25 | 54.5 30 | 10.2 47 | 25.2 8 | 44.1 10 | 5.00 40 | 32.9 2 | 68.2 2 | 4.04 8 | 28.4 10 | 44.6 17 | 3.56 67 |
SuperFlow [81] | 30.0 | 11.0 3 | 22.1 17 | 3.11 73 | 17.1 63 | 22.7 52 | 4.69 82 | 11.7 46 | 18.7 2 | 3.37 67 | 18.7 40 | 27.4 3 | 7.70 66 | 41.3 7 | 51.2 8 | 9.98 13 | 26.3 22 | 46.9 32 | 4.80 3 | 34.7 16 | 76.0 46 | 4.08 38 | 28.1 8 | 41.5 5 | 3.42 9 |
PH-Flow [101] | 30.6 | 11.9 56 | 25.7 70 | 2.83 17 | 13.3 5 | 19.7 7 | 3.56 4 | 10.7 5 | 22.7 36 | 3.00 2 | 16.5 2 | 30.2 15 | 7.33 3 | 42.3 18 | 52.1 13 | 10.1 29 | 28.7 78 | 50.9 92 | 5.20 70 | 35.6 34 | 77.0 56 | 4.04 8 | 29.6 28 | 47.0 35 | 3.51 51 |
DF-Auto [115] | 30.9 | 10.9 2 | 19.2 2 | 3.11 73 | 17.2 66 | 23.4 68 | 4.43 74 | 10.4 3 | 20.6 21 | 3.00 2 | 18.1 27 | 29.7 9 | 7.55 38 | 41.4 9 | 52.1 13 | 10.0 17 | 26.2 17 | 47.2 35 | 4.97 19 | 35.2 27 | 79.3 68 | 4.08 38 | 29.6 28 | 44.7 18 | 3.56 67 |
CombBMOF [113] | 31.2 | 12.0 62 | 24.3 41 | 2.83 17 | 14.3 16 | 20.6 16 | 3.56 4 | 11.3 27 | 25.7 61 | 3.00 2 | 20.3 71 | 34.9 66 | 7.55 38 | 43.2 38 | 54.0 25 | 10.1 29 | 26.4 23 | 47.7 45 | 4.90 6 | 36.2 52 | 71.4 18 | 4.08 38 | 29.5 25 | 45.7 27 | 3.37 2 |
CBF [12] | 32.8 | 11.0 3 | 19.8 3 | 3.00 60 | 17.1 63 | 22.9 57 | 4.24 66 | 12.0 61 | 19.0 4 | 3.00 2 | 17.8 21 | 28.0 5 | 7.85 80 | 40.6 3 | 49.9 2 | 9.97 9 | 26.2 17 | 44.6 14 | 4.97 19 | 36.3 54 | 76.3 51 | 4.12 81 | 27.9 4 | 41.2 4 | 3.70 104 |
Aniso. Huber-L1 [22] | 33.7 | 11.4 16 | 21.7 10 | 3.11 73 | 19.7 101 | 24.7 101 | 4.55 78 | 12.0 61 | 19.7 8 | 3.11 62 | 18.4 32 | 29.8 12 | 7.55 38 | 42.5 21 | 54.4 29 | 9.98 13 | 25.2 8 | 42.2 2 | 4.83 4 | 35.6 34 | 71.5 19 | 4.04 8 | 27.9 4 | 42.0 7 | 3.56 67 |
LME [70] | 34.0 | 11.4 16 | 22.0 15 | 2.71 2 | 15.1 31 | 21.8 36 | 3.87 49 | 11.3 27 | 36.0 119 | 3.00 2 | 17.4 8 | 32.0 38 | 7.48 21 | 44.5 61 | 57.0 60 | 11.4 123 | 27.6 45 | 47.2 35 | 4.97 19 | 33.6 3 | 69.7 4 | 4.04 8 | 30.0 34 | 48.6 51 | 3.42 9 |
CLG-TV [48] | 35.4 | 11.1 8 | 21.8 13 | 3.11 73 | 18.8 85 | 24.0 82 | 4.43 74 | 11.3 27 | 20.0 12 | 3.70 82 | 18.6 38 | 28.9 7 | 7.72 71 | 42.8 28 | 55.0 41 | 10.0 17 | 25.0 4 | 42.9 5 | 4.93 12 | 36.0 46 | 71.6 20 | 4.04 8 | 29.0 16 | 44.0 13 | 3.56 67 |
IROF++ [58] | 35.4 | 11.9 56 | 24.1 37 | 2.83 17 | 14.7 25 | 21.3 26 | 3.56 4 | 12.1 74 | 29.0 89 | 3.00 2 | 16.3 1 | 27.9 4 | 7.35 7 | 43.9 50 | 56.0 50 | 11.1 93 | 26.4 23 | 47.0 34 | 4.93 12 | 34.5 13 | 72.3 24 | 4.08 38 | 30.3 44 | 49.3 59 | 3.56 67 |
WLIF-Flow [93] | 35.4 | 11.5 24 | 22.1 17 | 2.83 17 | 15.2 32 | 21.6 33 | 3.79 40 | 11.3 27 | 26.4 69 | 3.00 2 | 17.4 8 | 30.3 17 | 7.59 46 | 42.5 21 | 53.5 21 | 10.4 61 | 29.0 84 | 51.1 95 | 5.29 87 | 34.8 19 | 69.7 4 | 4.04 8 | 30.0 34 | 48.4 47 | 3.46 36 |
FMOF [94] | 36.8 | 12.2 82 | 24.5 50 | 2.94 48 | 14.0 11 | 20.0 10 | 3.56 4 | 12.3 77 | 27.7 76 | 3.00 2 | 19.8 58 | 35.4 71 | 7.70 66 | 42.4 19 | 52.1 13 | 10.1 29 | 28.1 58 | 49.1 61 | 4.93 12 | 34.6 15 | 72.7 28 | 3.87 1 | 30.2 40 | 47.6 43 | 3.42 9 |
Brox et al. [5] | 37.7 | 11.4 16 | 24.9 62 | 2.94 48 | 15.9 43 | 22.2 44 | 4.04 56 | 11.3 27 | 21.0 22 | 3.37 67 | 18.4 32 | 27.0 2 | 7.59 46 | 42.2 16 | 53.3 19 | 10.0 17 | 28.2 62 | 51.5 98 | 5.00 40 | 36.8 57 | 88.0 95 | 4.04 8 | 28.4 10 | 42.3 8 | 3.42 9 |
IROF-TV [53] | 38.1 | 11.7 38 | 24.7 57 | 3.00 60 | 15.5 39 | 22.0 42 | 3.70 24 | 11.0 10 | 23.7 46 | 3.00 2 | 17.3 6 | 31.3 26 | 7.57 45 | 43.8 48 | 56.0 50 | 11.2 100 | 27.6 45 | 48.4 52 | 4.97 19 | 35.9 44 | 74.5 42 | 4.08 38 | 28.0 6 | 42.6 9 | 3.56 67 |
ALD-Flow [66] | 39.0 | 12.0 62 | 28.4 95 | 3.11 73 | 16.3 50 | 22.8 54 | 3.83 44 | 11.0 10 | 21.7 28 | 3.00 2 | 17.9 24 | 33.6 54 | 7.39 12 | 43.4 43 | 54.6 34 | 10.8 79 | 25.8 12 | 44.8 18 | 5.00 40 | 34.1 9 | 70.4 8 | 4.04 8 | 31.9 74 | 50.3 67 | 3.46 36 |
nLayers [57] | 39.6 | 11.8 46 | 22.9 23 | 2.83 17 | 14.1 12 | 20.4 13 | 3.56 4 | 11.0 10 | 19.7 8 | 3.00 2 | 18.3 30 | 34.2 62 | 7.39 12 | 46.7 112 | 60.1 108 | 11.0 87 | 27.9 52 | 50.1 68 | 5.20 70 | 35.5 32 | 72.6 27 | 4.08 38 | 30.8 49 | 49.3 59 | 3.42 9 |
LDOF [28] | 41.2 | 11.4 16 | 22.5 20 | 3.56 114 | 16.1 45 | 21.4 31 | 6.35 118 | 12.0 61 | 20.3 14 | 3.70 82 | 19.0 47 | 29.7 9 | 7.94 85 | 41.2 6 | 50.9 5 | 10.1 29 | 26.8 28 | 50.2 70 | 4.90 6 | 34.8 19 | 80.2 72 | 4.08 38 | 29.4 22 | 44.5 15 | 3.46 36 |
p-harmonic [29] | 41.3 | 11.4 16 | 23.5 27 | 2.83 17 | 19.1 89 | 24.3 90 | 4.80 87 | 11.3 27 | 22.0 30 | 3.70 82 | 20.9 78 | 31.7 32 | 7.62 52 | 42.6 24 | 54.2 27 | 10.1 29 | 25.7 11 | 43.5 8 | 5.07 46 | 36.1 50 | 71.8 21 | 4.08 38 | 29.6 28 | 46.5 32 | 3.51 51 |
Layers++ [37] | 41.4 | 11.4 16 | 21.7 10 | 2.94 48 | 12.8 1 | 18.2 1 | 3.46 2 | 11.0 10 | 26.7 72 | 3.00 2 | 17.7 16 | 32.9 46 | 7.53 31 | 46.6 110 | 60.9 119 | 10.6 72 | 30.9 115 | 60.2 120 | 5.00 40 | 34.9 25 | 72.7 28 | 3.87 1 | 29.9 33 | 47.5 40 | 3.46 36 |
MDP-Flow [26] | 41.6 | 11.2 10 | 21.2 7 | 2.71 2 | 14.2 14 | 20.5 15 | 3.70 24 | 10.7 5 | 19.0 4 | 3.00 2 | 19.7 56 | 32.4 41 | 7.70 66 | 44.2 53 | 57.0 60 | 11.2 100 | 30.0 104 | 51.4 97 | 5.51 115 | 36.1 50 | 72.9 31 | 4.08 38 | 30.8 49 | 48.4 47 | 3.42 9 |
Second-order prior [8] | 41.9 | 11.3 14 | 22.0 15 | 3.11 73 | 19.0 88 | 24.2 88 | 4.32 69 | 13.3 89 | 27.7 76 | 3.70 82 | 18.8 43 | 31.6 31 | 7.51 25 | 42.9 30 | 54.7 36 | 10.0 17 | 26.2 17 | 45.0 20 | 4.97 19 | 35.6 34 | 71.2 15 | 4.04 8 | 29.5 25 | 45.4 24 | 3.56 67 |
SIOF [67] | 42.5 | 11.7 38 | 23.1 25 | 3.11 73 | 19.4 96 | 24.8 104 | 4.76 84 | 11.3 27 | 25.7 61 | 3.11 62 | 18.4 32 | 31.4 28 | 8.04 90 | 40.3 2 | 50.3 3 | 9.95 7 | 25.8 12 | 45.3 22 | 4.97 19 | 33.9 7 | 71.2 15 | 4.08 38 | 30.0 34 | 47.4 37 | 3.70 104 |
Local-TV-L1 [65] | 43.2 | 11.2 10 | 21.5 8 | 3.56 114 | 19.6 99 | 24.4 93 | 5.57 107 | 11.0 10 | 19.1 6 | 3.00 2 | 18.3 30 | 30.4 20 | 7.87 83 | 42.8 28 | 54.5 30 | 10.2 47 | 26.2 17 | 44.7 15 | 5.45 103 | 34.2 10 | 76.1 49 | 4.08 38 | 28.0 6 | 42.8 11 | 3.65 101 |
COFM [59] | 43.9 | 11.8 46 | 24.3 41 | 2.94 48 | 14.5 22 | 20.9 21 | 3.65 22 | 11.0 10 | 26.4 69 | 3.00 2 | 17.4 8 | 32.3 39 | 7.35 7 | 44.2 53 | 55.1 42 | 10.1 29 | 30.0 104 | 54.4 114 | 5.20 70 | 35.8 40 | 79.3 68 | 4.08 38 | 31.2 56 | 48.8 54 | 3.51 51 |
ProbFlowFields [128] | 45.3 | 11.6 30 | 25.4 67 | 2.83 17 | 14.4 18 | 21.1 25 | 3.56 4 | 10.7 5 | 23.7 46 | 3.00 2 | 18.4 32 | 33.4 51 | 7.59 46 | 46.2 100 | 59.2 95 | 11.2 100 | 28.5 74 | 50.7 86 | 5.32 91 | 34.7 16 | 76.9 54 | 4.08 38 | 29.4 22 | 46.5 32 | 3.46 36 |
FlowFields [110] | 45.5 | 11.8 46 | 25.6 69 | 2.83 17 | 14.4 18 | 20.9 21 | 3.56 4 | 11.3 27 | 24.3 52 | 3.00 2 | 20.0 64 | 38.1 93 | 7.51 25 | 43.6 45 | 54.5 30 | 11.0 87 | 28.2 62 | 50.7 86 | 5.16 65 | 34.8 19 | 75.1 45 | 4.04 8 | 32.0 79 | 52.0 91 | 3.46 36 |
TV-L1-MCT [64] | 47.7 | 12.4 98 | 24.7 57 | 2.83 17 | 16.4 51 | 23.1 62 | 3.83 44 | 11.9 60 | 32.7 110 | 3.00 2 | 17.6 13 | 31.7 32 | 7.53 31 | 47.0 120 | 61.2 120 | 11.0 87 | 25.5 10 | 44.7 15 | 4.97 19 | 36.0 46 | 80.7 77 | 4.04 8 | 28.4 10 | 44.8 20 | 3.46 36 |
BlockOverlap [61] | 47.9 | 11.1 8 | 20.1 4 | 3.56 114 | 19.3 93 | 23.7 75 | 6.16 114 | 11.3 27 | 20.4 19 | 3.70 82 | 18.4 32 | 29.6 8 | 8.72 109 | 43.1 35 | 54.5 30 | 10.2 47 | 27.4 40 | 48.6 55 | 5.35 98 | 34.8 19 | 72.8 30 | 4.08 38 | 27.2 3 | 40.9 3 | 3.56 67 |
HAST [109] | 49.2 | 11.7 38 | 23.6 29 | 2.94 48 | 13.8 8 | 19.6 6 | 3.56 4 | 12.0 61 | 31.7 106 | 3.00 2 | 17.8 21 | 31.7 32 | 7.14 1 | 45.3 78 | 57.0 60 | 9.97 9 | 33.7 124 | 62.8 127 | 5.10 62 | 38.4 79 | 88.4 97 | 4.04 8 | 33.0 96 | 51.0 75 | 3.42 9 |
Sparse-NonSparse [56] | 49.2 | 12.0 62 | 24.3 41 | 2.83 17 | 15.0 28 | 21.3 26 | 3.56 4 | 11.7 46 | 29.0 89 | 3.00 2 | 17.6 13 | 29.7 9 | 7.39 12 | 45.7 86 | 59.3 96 | 11.0 87 | 28.8 79 | 48.7 57 | 5.07 46 | 38.6 84 | 90.1 106 | 4.04 8 | 32.4 87 | 51.8 87 | 3.42 9 |
Kuang [131] | 49.5 | 11.9 56 | 25.3 66 | 2.83 17 | 15.0 28 | 21.4 31 | 3.70 24 | 12.7 83 | 28.0 80 | 3.00 2 | 20.5 74 | 40.0 104 | 7.51 25 | 44.6 64 | 56.4 54 | 10.8 79 | 27.7 50 | 46.5 29 | 4.97 19 | 36.8 57 | 74.2 39 | 4.12 81 | 30.8 49 | 50.4 68 | 3.42 9 |
Modified CLG [34] | 49.8 | 11.0 3 | 21.9 14 | 3.11 73 | 19.6 99 | 23.9 79 | 5.94 112 | 12.4 81 | 26.3 67 | 3.87 95 | 19.8 58 | 30.8 22 | 8.12 95 | 42.1 14 | 52.9 17 | 10.1 29 | 27.0 31 | 48.1 50 | 5.23 77 | 34.7 16 | 70.8 11 | 4.08 38 | 29.5 25 | 45.3 23 | 3.56 67 |
OAR-Flow [125] | 50.1 | 12.0 62 | 24.9 62 | 3.00 60 | 16.4 51 | 22.4 47 | 4.08 61 | 11.0 10 | 20.5 20 | 3.00 2 | 17.4 8 | 33.6 54 | 7.33 3 | 46.2 100 | 60.0 107 | 11.3 116 | 27.0 31 | 47.6 42 | 5.23 77 | 37.6 68 | 74.0 36 | 4.08 38 | 31.0 55 | 49.2 57 | 3.46 36 |
CPM-Flow [116] | 50.5 | 11.8 46 | 27.3 85 | 2.83 17 | 14.4 18 | 20.4 13 | 3.70 24 | 11.7 46 | 24.0 49 | 3.00 2 | 21.4 87 | 40.1 105 | 7.77 75 | 45.5 82 | 58.1 77 | 11.2 100 | 26.6 27 | 48.0 48 | 5.07 46 | 36.0 46 | 72.3 24 | 4.04 8 | 30.9 53 | 50.4 68 | 3.56 67 |
AdaConv-v1 [126] | 50.9 | 15.0 123 | 28.2 94 | 3.70 118 | 17.6 71 | 20.7 19 | 7.68 126 | 17.4 106 | 22.0 30 | 7.00 120 | 27.5 116 | 33.7 58 | 17.0 127 | 39.9 1 | 49.8 1 | 8.19 1 | 23.8 1 | 39.5 1 | 4.76 2 | 34.2 10 | 68.5 3 | 4.12 81 | 26.9 2 | 39.5 2 | 3.42 9 |
F-TV-L1 [15] | 51.5 | 12.0 62 | 26.5 81 | 3.56 114 | 19.2 91 | 24.7 101 | 4.83 89 | 11.7 46 | 21.5 26 | 4.00 97 | 19.3 49 | 32.7 44 | 7.68 61 | 43.1 35 | 55.3 45 | 9.83 3 | 25.1 6 | 42.8 4 | 5.07 46 | 34.8 19 | 74.0 36 | 4.16 90 | 28.5 13 | 42.7 10 | 3.56 67 |
2DHMM-SAS [92] | 51.5 | 12.2 82 | 24.5 50 | 2.83 17 | 17.9 74 | 24.1 85 | 3.87 49 | 12.0 61 | 28.7 86 | 3.00 2 | 17.3 6 | 31.4 28 | 7.51 25 | 45.1 74 | 58.2 81 | 11.2 100 | 27.9 52 | 49.0 59 | 4.83 4 | 37.0 60 | 76.1 49 | 4.08 38 | 31.9 74 | 50.5 70 | 3.42 9 |
FlowFields+ [130] | 51.7 | 11.8 46 | 26.1 78 | 2.71 2 | 14.1 12 | 20.6 16 | 3.70 24 | 11.2 26 | 24.8 57 | 3.00 2 | 20.1 66 | 40.2 107 | 7.53 31 | 45.5 82 | 58.0 74 | 11.2 100 | 28.6 77 | 50.6 82 | 5.20 70 | 35.6 34 | 77.5 61 | 4.04 8 | 32.2 82 | 52.5 95 | 3.42 9 |
ComponentFusion [96] | 51.8 | 12.0 62 | 29.6 102 | 2.71 2 | 14.5 22 | 21.3 26 | 3.56 4 | 11.0 10 | 22.0 30 | 3.00 2 | 18.8 43 | 36.2 83 | 7.33 3 | 45.5 82 | 58.2 81 | 10.7 76 | 27.2 36 | 46.3 26 | 4.97 19 | 40.5 103 | 93.3 114 | 4.12 81 | 34.4 110 | 58.3 118 | 3.42 9 |
AGIF+OF [85] | 52.1 | 12.2 82 | 24.3 41 | 2.71 2 | 15.2 32 | 21.8 36 | 3.70 24 | 11.7 46 | 27.7 76 | 3.00 2 | 18.0 25 | 33.0 48 | 7.55 38 | 45.8 90 | 58.8 92 | 11.2 100 | 30.0 104 | 53.4 109 | 5.07 46 | 35.4 29 | 74.8 44 | 3.92 3 | 32.2 82 | 52.6 98 | 3.37 2 |
TC/T-Flow [76] | 53.4 | 12.4 98 | 26.4 80 | 2.83 17 | 16.5 55 | 23.1 62 | 3.83 44 | 11.0 10 | 22.4 34 | 3.00 2 | 18.9 45 | 34.5 63 | 7.33 3 | 45.5 82 | 58.1 77 | 11.4 123 | 27.3 39 | 47.6 42 | 4.93 12 | 41.1 105 | 80.4 75 | 4.20 96 | 30.9 53 | 49.7 63 | 3.37 2 |
DPOF [18] | 53.5 | 12.3 91 | 29.4 101 | 3.11 73 | 13.3 5 | 19.1 5 | 3.56 4 | 15.7 97 | 25.2 59 | 3.70 82 | 19.4 51 | 37.5 90 | 7.59 46 | 43.1 35 | 54.6 34 | 10.0 17 | 29.1 89 | 49.7 64 | 4.90 6 | 36.6 55 | 77.0 56 | 4.08 38 | 31.5 64 | 50.5 70 | 3.51 51 |
Ad-TV-NDC [36] | 54.9 | 12.2 82 | 22.5 20 | 4.32 125 | 20.6 120 | 24.8 104 | 5.80 108 | 11.7 46 | 21.6 27 | 3.37 67 | 21.6 88 | 31.8 35 | 8.04 90 | 42.5 21 | 53.4 20 | 9.97 9 | 26.4 23 | 47.6 42 | 5.16 65 | 36.8 57 | 70.9 12 | 4.08 38 | 28.3 9 | 41.8 6 | 3.70 104 |
PGM-C [120] | 55.7 | 11.8 46 | 27.3 85 | 2.83 17 | 14.4 18 | 20.7 19 | 3.70 24 | 12.3 77 | 23.0 40 | 3.00 2 | 20.6 76 | 42.3 113 | 7.62 52 | 45.8 90 | 59.5 101 | 11.2 100 | 27.2 36 | 47.4 39 | 4.97 19 | 37.1 62 | 79.2 66 | 4.04 8 | 32.4 87 | 55.0 109 | 3.51 51 |
Ramp [62] | 56.0 | 12.0 62 | 24.6 53 | 2.94 48 | 14.8 26 | 21.3 26 | 3.70 24 | 11.7 46 | 29.4 95 | 3.00 2 | 16.9 5 | 30.3 17 | 7.39 12 | 45.4 80 | 58.5 84 | 11.0 87 | 30.2 109 | 50.9 92 | 5.23 77 | 39.8 96 | 89.6 103 | 4.04 8 | 32.4 87 | 52.5 95 | 3.42 9 |
TF+OM [100] | 56.1 | 11.6 30 | 30.1 107 | 3.11 73 | 15.0 28 | 21.6 33 | 4.04 56 | 11.7 46 | 24.0 49 | 3.00 2 | 21.3 84 | 39.0 101 | 7.68 61 | 44.3 55 | 56.7 58 | 10.3 52 | 28.8 79 | 50.4 77 | 5.07 46 | 37.7 69 | 83.5 89 | 4.08 38 | 29.2 18 | 46.0 28 | 3.56 67 |
PMF [73] | 56.1 | 12.2 82 | 25.9 73 | 2.71 2 | 15.4 36 | 21.8 36 | 3.56 4 | 12.7 83 | 35.7 117 | 3.00 2 | 20.2 69 | 35.9 77 | 7.51 25 | 44.4 59 | 54.9 40 | 10.1 29 | 28.4 67 | 50.5 80 | 5.32 91 | 37.9 73 | 81.1 79 | 4.04 8 | 34.2 109 | 54.1 104 | 3.37 2 |
ComplOF-FED-GPU [35] | 56.3 | 12.0 62 | 27.9 91 | 2.94 48 | 15.7 42 | 22.2 44 | 3.79 40 | 16.0 98 | 21.4 24 | 3.70 82 | 18.4 32 | 33.6 54 | 7.48 21 | 44.9 71 | 57.7 68 | 10.7 76 | 27.4 40 | 45.9 23 | 5.00 40 | 36.6 55 | 78.7 65 | 4.08 38 | 32.6 94 | 52.3 93 | 3.51 51 |
AggregFlow [97] | 56.5 | 13.7 116 | 37.1 121 | 3.11 73 | 16.2 48 | 22.6 50 | 4.04 56 | 11.0 10 | 23.3 45 | 3.00 2 | 21.8 90 | 40.7 109 | 7.66 59 | 43.2 38 | 53.5 21 | 10.3 52 | 27.0 31 | 46.0 24 | 5.00 40 | 38.0 74 | 82.4 86 | 4.08 38 | 31.9 74 | 51.9 90 | 3.42 9 |
OFLAF [77] | 57.4 | 11.7 38 | 24.5 50 | 2.71 2 | 13.6 7 | 20.3 12 | 3.56 4 | 11.0 10 | 23.0 40 | 3.00 2 | 17.6 13 | 31.3 26 | 7.39 12 | 47.3 122 | 61.7 123 | 11.2 100 | 29.6 99 | 51.9 104 | 5.32 91 | 41.8 110 | 95.6 119 | 4.16 90 | 33.6 102 | 52.1 92 | 3.42 9 |
S2F-IF [123] | 57.6 | 12.1 75 | 29.8 104 | 2.71 2 | 14.2 14 | 20.6 16 | 3.56 4 | 11.3 27 | 26.3 67 | 3.00 2 | 20.2 69 | 40.1 105 | 7.53 31 | 45.9 94 | 58.7 91 | 11.3 116 | 28.4 67 | 50.7 86 | 5.20 70 | 35.7 38 | 76.0 46 | 4.08 38 | 32.3 85 | 53.1 99 | 3.46 36 |
Classic++ [32] | 58.1 | 11.6 30 | 23.7 30 | 3.11 73 | 17.8 73 | 24.4 93 | 4.08 61 | 11.7 46 | 20.3 14 | 3.37 67 | 20.1 66 | 33.8 59 | 7.62 52 | 44.7 65 | 57.8 71 | 10.0 17 | 28.0 55 | 49.7 64 | 5.35 98 | 37.4 66 | 81.4 81 | 4.08 38 | 30.7 48 | 49.5 61 | 3.56 67 |
Classic+NL [31] | 58.4 | 12.1 75 | 24.3 41 | 3.00 60 | 15.3 35 | 21.8 36 | 3.70 24 | 11.7 46 | 29.4 95 | 3.00 2 | 17.4 8 | 31.4 28 | 7.53 31 | 45.7 86 | 59.4 98 | 10.8 79 | 29.0 84 | 49.8 67 | 5.10 62 | 39.6 93 | 90.4 108 | 4.08 38 | 32.2 82 | 51.8 87 | 3.46 36 |
FlowNetS+ft+v [112] | 58.9 | 11.5 24 | 23.7 30 | 3.46 112 | 19.9 106 | 24.6 99 | 7.87 128 | 12.0 61 | 21.1 23 | 3.37 67 | 19.5 53 | 30.6 21 | 8.91 112 | 43.7 46 | 56.6 57 | 11.2 100 | 26.0 14 | 44.5 13 | 4.97 19 | 38.6 84 | 87.8 93 | 4.08 38 | 30.0 34 | 46.0 28 | 3.51 51 |
FC-2Layers-FF [74] | 60.0 | 12.1 75 | 26.0 77 | 2.83 17 | 13.0 3 | 18.7 4 | 3.56 4 | 11.4 43 | 25.7 61 | 3.00 2 | 17.8 21 | 33.5 53 | 7.48 21 | 46.5 106 | 60.3 113 | 11.2 100 | 30.4 112 | 52.3 108 | 5.32 91 | 39.8 96 | 90.0 105 | 4.08 38 | 31.8 70 | 51.6 83 | 3.46 36 |
MLDP_OF [89] | 60.0 | 11.9 56 | 24.7 57 | 2.83 17 | 17.4 69 | 23.8 77 | 3.87 49 | 10.7 5 | 24.6 55 | 3.00 2 | 20.5 74 | 33.6 54 | 8.35 101 | 44.1 51 | 56.5 55 | 10.1 29 | 29.3 92 | 50.5 80 | 5.57 116 | 35.8 40 | 73.4 33 | 4.20 96 | 31.2 56 | 50.6 73 | 3.70 104 |
LSM [39] | 60.1 | 12.3 91 | 24.7 57 | 2.83 17 | 15.4 36 | 21.9 40 | 3.56 4 | 12.0 61 | 30.3 101 | 3.00 2 | 18.7 40 | 33.2 50 | 7.44 17 | 46.1 98 | 59.4 98 | 11.1 93 | 29.3 92 | 51.9 104 | 5.07 46 | 39.2 89 | 91.0 110 | 4.04 8 | 32.3 85 | 52.5 95 | 3.42 9 |
TCOF [69] | 61.1 | 12.0 62 | 24.7 57 | 2.83 17 | 20.3 115 | 26.4 128 | 5.07 94 | 11.1 25 | 29.0 89 | 3.00 2 | 17.7 16 | 32.4 41 | 7.68 61 | 43.2 38 | 55.5 46 | 9.97 9 | 28.8 79 | 46.3 26 | 5.07 46 | 41.2 108 | 94.9 117 | 4.08 38 | 31.8 70 | 51.3 79 | 3.70 104 |
CRTflow [80] | 61.1 | 11.7 38 | 24.4 48 | 3.32 101 | 19.5 98 | 24.9 107 | 4.51 76 | 12.0 61 | 22.7 36 | 4.00 97 | 18.1 27 | 30.3 17 | 7.68 61 | 45.0 72 | 58.1 77 | 11.3 116 | 26.0 14 | 45.1 21 | 4.97 19 | 37.7 69 | 87.9 94 | 4.08 38 | 30.8 49 | 50.2 64 | 3.56 67 |
RNLOD-Flow [121] | 61.2 | 11.8 46 | 24.6 53 | 2.89 44 | 17.3 68 | 24.0 82 | 3.74 38 | 12.7 83 | 36.0 119 | 3.11 62 | 18.1 27 | 31.2 25 | 7.48 21 | 45.8 90 | 59.6 102 | 11.1 93 | 29.3 92 | 50.6 82 | 5.16 65 | 35.4 29 | 74.1 38 | 4.08 38 | 32.0 79 | 51.6 83 | 3.42 9 |
RFlow [90] | 61.8 | 11.6 30 | 24.3 41 | 3.00 60 | 19.3 93 | 24.8 104 | 4.36 71 | 11.6 45 | 29.7 97 | 3.37 67 | 20.0 64 | 36.1 79 | 7.72 71 | 43.0 31 | 55.2 44 | 10.1 29 | 27.9 52 | 51.8 103 | 4.97 19 | 37.1 62 | 82.8 88 | 4.08 38 | 31.6 66 | 49.5 61 | 3.56 67 |
Fusion [6] | 61.9 | 11.6 30 | 24.3 41 | 2.89 44 | 15.6 40 | 21.9 40 | 3.83 44 | 11.0 10 | 23.7 46 | 3.37 67 | 21.0 79 | 33.4 51 | 7.62 52 | 44.1 51 | 56.3 53 | 10.1 29 | 30.3 111 | 54.1 112 | 5.45 103 | 38.0 74 | 83.7 90 | 4.08 38 | 34.0 107 | 54.7 106 | 3.56 67 |
Sparse Occlusion [54] | 62.5 | 11.7 38 | 25.9 73 | 3.00 60 | 18.1 78 | 24.6 99 | 3.83 44 | 11.3 27 | 22.7 36 | 3.11 62 | 18.7 40 | 34.1 61 | 7.70 66 | 45.0 72 | 58.0 74 | 11.1 93 | 28.5 74 | 44.2 11 | 5.26 81 | 39.3 91 | 83.7 90 | 3.92 3 | 31.9 74 | 51.7 85 | 3.56 67 |
S2D-Matching [84] | 63.0 | 12.3 91 | 25.7 70 | 2.94 48 | 17.2 66 | 23.7 75 | 4.00 54 | 11.7 46 | 28.7 86 | 3.00 2 | 17.7 16 | 31.9 37 | 7.55 38 | 46.8 115 | 60.1 108 | 10.4 61 | 30.0 104 | 51.5 98 | 5.29 87 | 37.0 60 | 77.7 62 | 4.04 8 | 31.8 70 | 50.9 74 | 3.46 36 |
TC-Flow [46] | 63.5 | 12.0 62 | 30.3 109 | 2.89 44 | 16.8 60 | 23.4 68 | 3.92 53 | 11.7 46 | 21.4 24 | 3.00 2 | 19.5 53 | 36.1 79 | 8.12 95 | 46.5 106 | 59.8 105 | 11.3 116 | 27.0 31 | 48.4 52 | 5.26 81 | 35.5 32 | 74.6 43 | 4.04 8 | 33.3 99 | 54.5 105 | 3.51 51 |
Black & Anandan [4] | 64.0 | 12.3 91 | 24.0 35 | 3.46 112 | 21.2 122 | 25.4 114 | 5.35 103 | 18.1 109 | 25.0 58 | 5.35 112 | 24.4 108 | 34.9 66 | 7.77 75 | 42.2 16 | 53.5 21 | 10.1 29 | 26.9 30 | 46.5 29 | 4.97 19 | 39.5 92 | 77.2 58 | 4.08 38 | 29.3 20 | 42.8 11 | 3.56 67 |
HBM-GC [105] | 64.0 | 11.8 46 | 23.8 33 | 3.11 73 | 16.8 60 | 24.2 88 | 3.87 49 | 10.7 5 | 18.7 2 | 3.00 2 | 18.9 45 | 32.9 46 | 7.68 61 | 46.8 115 | 60.8 117 | 11.5 129 | 34.5 127 | 61.7 122 | 5.48 111 | 37.7 69 | 81.9 85 | 4.04 8 | 30.5 47 | 47.8 44 | 3.51 51 |
SVFilterOh [111] | 64.0 | 11.9 56 | 26.1 78 | 2.94 48 | 14.3 16 | 20.9 21 | 3.70 24 | 12.0 61 | 26.7 72 | 3.00 2 | 19.9 62 | 36.1 79 | 7.62 52 | 46.7 112 | 59.8 105 | 11.4 123 | 30.7 114 | 55.1 115 | 5.07 46 | 36.0 46 | 77.2 58 | 4.04 8 | 32.4 87 | 53.2 100 | 3.51 51 |
Classic+CPF [83] | 65.5 | 12.2 82 | 24.6 53 | 2.83 17 | 15.6 40 | 22.1 43 | 3.74 38 | 12.0 61 | 30.7 102 | 3.00 2 | 17.7 16 | 30.9 24 | 7.44 17 | 47.2 121 | 61.3 121 | 11.2 100 | 31.2 118 | 55.9 116 | 5.26 81 | 39.9 98 | 88.8 100 | 4.04 8 | 33.6 102 | 54.0 103 | 3.42 9 |
FESL [72] | 66.2 | 12.2 82 | 25.1 65 | 2.83 17 | 14.9 27 | 21.6 33 | 3.70 24 | 12.1 74 | 33.7 113 | 3.00 2 | 19.7 56 | 35.0 68 | 7.72 71 | 46.2 100 | 60.2 112 | 11.3 116 | 29.3 92 | 50.4 77 | 5.32 91 | 39.6 93 | 88.6 99 | 3.92 3 | 32.4 87 | 51.2 77 | 3.42 9 |
CostFilter [40] | 66.5 | 13.1 112 | 33.1 116 | 2.71 2 | 15.2 32 | 21.3 26 | 3.56 4 | 14.0 91 | 42.7 127 | 3.00 2 | 22.0 91 | 44.4 120 | 7.26 2 | 45.8 90 | 57.2 65 | 10.4 61 | 27.2 36 | 48.1 50 | 5.45 103 | 39.9 98 | 89.4 102 | 4.08 38 | 35.6 114 | 56.1 113 | 3.37 2 |
Efficient-NL [60] | 66.7 | 11.8 46 | 23.8 33 | 2.83 17 | 16.7 58 | 23.3 66 | 3.70 24 | 18.4 111 | 29.0 89 | 3.70 82 | 19.4 51 | 34.0 60 | 7.51 25 | 45.1 74 | 58.5 84 | 11.1 93 | 30.0 104 | 51.5 98 | 5.07 46 | 40.1 101 | 88.9 101 | 4.08 38 | 33.0 96 | 52.4 94 | 3.42 9 |
Bartels [41] | 67.0 | 12.2 82 | 29.9 105 | 3.37 105 | 17.4 69 | 24.3 90 | 4.83 89 | 11.3 27 | 24.7 56 | 3.70 82 | 21.2 81 | 35.4 71 | 9.15 115 | 41.3 7 | 51.0 6 | 9.87 4 | 29.7 101 | 50.2 70 | 6.32 128 | 33.7 5 | 70.7 10 | 4.20 96 | 30.2 40 | 48.4 47 | 3.79 121 |
2D-CLG [1] | 67.0 | 11.6 30 | 24.1 37 | 3.11 73 | 19.4 96 | 23.3 66 | 6.24 116 | 18.7 112 | 24.3 52 | 4.69 106 | 22.4 95 | 31.8 35 | 8.66 108 | 43.3 42 | 56.1 52 | 10.4 61 | 26.0 14 | 44.2 11 | 5.35 98 | 40.2 102 | 91.5 112 | 4.20 96 | 29.6 28 | 44.5 15 | 3.51 51 |
EpicFlow [102] | 67.1 | 11.9 56 | 27.6 89 | 2.83 17 | 16.0 44 | 22.2 44 | 3.79 40 | 11.8 59 | 21.7 28 | 3.00 2 | 21.3 84 | 42.9 115 | 7.85 80 | 46.3 103 | 59.4 98 | 11.2 100 | 27.4 40 | 47.5 41 | 5.16 65 | 38.2 76 | 76.6 52 | 4.12 81 | 35.2 113 | 58.0 116 | 3.56 67 |
Filter Flow [19] | 67.2 | 11.8 46 | 23.1 25 | 3.37 105 | 20.0 107 | 25.1 109 | 5.23 100 | 12.2 76 | 26.0 64 | 3.70 82 | 22.1 92 | 32.7 44 | 7.94 85 | 42.1 14 | 51.9 11 | 10.4 61 | 28.1 58 | 49.0 59 | 5.07 46 | 38.4 79 | 81.6 82 | 4.16 90 | 30.0 34 | 45.5 26 | 3.74 118 |
SRR-TVOF-NL [91] | 67.8 | 12.9 109 | 28.7 96 | 3.00 60 | 16.9 62 | 23.1 62 | 4.69 82 | 11.5 44 | 27.0 74 | 3.00 2 | 22.2 93 | 37.3 88 | 7.59 46 | 44.8 69 | 57.9 72 | 11.0 87 | 29.1 89 | 51.9 104 | 4.90 6 | 35.7 38 | 77.7 62 | 4.08 38 | 33.0 96 | 51.5 82 | 3.56 67 |
Steered-L1 [118] | 68.0 | 11.2 10 | 22.6 22 | 2.89 44 | 16.2 48 | 22.6 50 | 4.55 78 | 21.7 115 | 32.4 109 | 5.00 109 | 23.4 102 | 38.3 95 | 10.7 119 | 44.7 65 | 57.4 66 | 9.88 5 | 28.0 55 | 48.5 54 | 5.32 91 | 37.1 62 | 79.2 66 | 4.12 81 | 31.4 60 | 51.1 76 | 3.51 51 |
Occlusion-TV-L1 [63] | 70.8 | 11.6 30 | 25.0 64 | 3.11 73 | 19.8 104 | 26.0 122 | 4.83 89 | 11.3 27 | 23.0 40 | 3.46 79 | 22.5 98 | 43.0 117 | 7.94 85 | 43.0 31 | 54.8 39 | 9.88 5 | 28.0 55 | 50.7 86 | 5.32 91 | 39.6 93 | 76.6 52 | 4.62 119 | 31.5 64 | 50.5 70 | 3.56 67 |
EPPM w/o HM [88] | 71.5 | 12.7 106 | 30.9 111 | 2.71 2 | 16.1 45 | 23.1 62 | 3.70 24 | 17.7 107 | 42.4 126 | 3.70 82 | 21.3 84 | 42.5 114 | 7.70 66 | 43.0 31 | 53.1 18 | 10.3 52 | 30.2 109 | 57.1 118 | 4.97 19 | 38.5 82 | 89.6 103 | 4.12 81 | 32.4 87 | 51.3 79 | 3.42 9 |
OFH [38] | 71.8 | 12.0 62 | 27.3 85 | 3.00 60 | 18.1 78 | 23.4 68 | 4.20 65 | 12.4 81 | 32.7 110 | 3.00 2 | 18.6 38 | 35.4 71 | 7.35 7 | 46.5 106 | 60.1 108 | 10.8 79 | 27.5 43 | 47.2 35 | 5.26 81 | 41.1 105 | 81.1 79 | 4.20 96 | 35.7 115 | 56.1 113 | 3.46 36 |
CNN-flow-warp+ref [117] | 72.0 | 11.0 3 | 22.4 19 | 3.11 73 | 17.6 71 | 22.9 57 | 5.92 111 | 16.1 99 | 28.3 85 | 4.00 97 | 23.5 103 | 30.2 15 | 10.7 119 | 44.8 69 | 58.5 84 | 11.3 116 | 26.5 26 | 46.5 29 | 5.29 87 | 41.5 109 | 91.5 112 | 4.32 108 | 30.4 45 | 47.5 40 | 3.51 51 |
Adaptive [20] | 72.2 | 11.6 30 | 26.7 82 | 3.11 73 | 20.2 111 | 25.9 119 | 5.07 94 | 12.0 61 | 23.0 40 | 3.37 67 | 20.4 72 | 36.6 85 | 7.77 75 | 44.3 55 | 58.5 84 | 9.98 13 | 28.3 65 | 49.1 61 | 5.16 65 | 42.5 114 | 90.6 109 | 4.08 38 | 31.6 66 | 48.8 54 | 3.65 101 |
Horn & Schunck [3] | 73.8 | 12.1 75 | 23.7 30 | 3.32 101 | 21.4 124 | 25.6 117 | 5.89 110 | 17.0 103 | 28.2 84 | 5.35 112 | 27.3 115 | 37.9 91 | 8.04 90 | 42.4 19 | 54.3 28 | 10.3 52 | 26.2 17 | 44.7 15 | 5.07 46 | 40.9 104 | 81.7 83 | 4.20 96 | 30.2 40 | 44.3 14 | 3.70 104 |
IAOF [50] | 74.5 | 13.0 110 | 29.2 99 | 3.37 105 | 23.7 129 | 27.4 131 | 6.45 120 | 16.4 101 | 28.7 86 | 3.46 79 | 22.7 99 | 33.1 49 | 8.37 102 | 43.4 43 | 55.6 48 | 10.0 17 | 27.6 45 | 50.1 68 | 4.97 19 | 38.3 77 | 82.7 87 | 4.08 38 | 30.0 34 | 46.8 34 | 3.56 67 |
TV-L1-improved [17] | 75.2 | 11.5 24 | 25.4 67 | 3.11 73 | 20.1 110 | 26.0 122 | 5.26 101 | 16.8 102 | 19.7 8 | 4.04 102 | 19.5 53 | 32.3 39 | 7.79 78 | 43.8 48 | 56.5 55 | 10.0 17 | 28.9 83 | 51.1 95 | 5.07 46 | 43.2 117 | 98.9 123 | 4.43 114 | 31.4 60 | 50.2 64 | 3.70 104 |
TriFlow [95] | 75.6 | 12.5 102 | 36.7 120 | 3.00 60 | 18.7 83 | 24.5 96 | 4.76 84 | 11.7 46 | 28.1 83 | 3.00 2 | 21.7 89 | 41.4 111 | 7.62 52 | 46.8 115 | 60.4 114 | 11.2 100 | 29.9 102 | 51.7 102 | 4.97 19 | 37.8 72 | 76.9 54 | 4.08 38 | 31.7 69 | 48.6 51 | 3.51 51 |
HBpMotionGpu [43] | 76.2 | 12.3 91 | 32.0 114 | 3.79 120 | 20.6 120 | 25.4 114 | 6.00 113 | 11.3 27 | 26.1 66 | 3.00 2 | 23.2 101 | 44.0 119 | 7.85 80 | 44.3 55 | 56.9 59 | 10.8 79 | 29.0 84 | 53.5 111 | 5.26 81 | 34.9 25 | 69.8 6 | 4.04 8 | 31.8 70 | 51.4 81 | 3.70 104 |
Nguyen [33] | 76.5 | 12.0 62 | 25.9 73 | 3.37 105 | 21.2 122 | 24.5 96 | 6.27 117 | 12.7 83 | 28.0 80 | 3.70 82 | 23.8 104 | 34.7 64 | 8.58 106 | 43.0 31 | 54.7 36 | 10.1 29 | 27.7 50 | 50.7 86 | 4.97 19 | 43.4 119 | 93.7 115 | 4.43 114 | 30.2 40 | 47.4 37 | 3.56 67 |
BriefMatch [124] | 77.1 | 12.1 75 | 29.2 99 | 3.11 73 | 16.5 55 | 22.5 48 | 6.61 122 | 18.0 108 | 22.7 36 | 5.69 115 | 26.2 111 | 35.5 75 | 18.2 129 | 43.7 46 | 54.7 36 | 10.4 61 | 29.6 99 | 50.2 70 | 5.94 125 | 35.8 40 | 72.5 26 | 4.16 90 | 32.1 81 | 50.2 64 | 3.56 67 |
GraphCuts [14] | 77.4 | 13.9 119 | 30.2 108 | 3.32 101 | 16.4 51 | 22.5 48 | 4.36 71 | 33.4 127 | 24.1 51 | 5.35 112 | 22.3 94 | 34.7 64 | 7.87 83 | 44.5 61 | 57.0 60 | 9.98 13 | 28.3 65 | 50.3 75 | 4.90 6 | 38.5 82 | 88.2 96 | 4.20 96 | 33.9 106 | 53.6 102 | 3.56 67 |
FlowNet2 [122] | 78.7 | 19.1 127 | 47.5 128 | 3.11 73 | 17.1 63 | 24.1 85 | 4.55 78 | 14.2 93 | 29.8 99 | 3.37 67 | 23.8 104 | 42.9 115 | 8.33 99 | 45.9 94 | 58.1 77 | 10.6 72 | 27.6 45 | 49.4 63 | 4.93 12 | 39.2 89 | 81.0 78 | 4.08 38 | 31.6 66 | 49.2 57 | 3.56 67 |
TI-DOFE [24] | 78.8 | 12.7 106 | 27.6 89 | 3.87 124 | 22.2 127 | 25.3 111 | 6.66 123 | 14.1 92 | 25.3 60 | 4.36 104 | 27.7 117 | 38.7 99 | 9.06 113 | 42.7 25 | 53.6 24 | 10.1 29 | 26.8 28 | 48.8 58 | 4.97 19 | 38.3 77 | 76.0 46 | 4.24 106 | 31.9 74 | 44.7 18 | 3.87 123 |
ROF-ND [107] | 81.7 | 12.4 98 | 24.4 48 | 2.83 17 | 17.9 74 | 23.9 79 | 4.08 61 | 12.0 61 | 26.6 71 | 3.00 2 | 29.5 121 | 48.9 124 | 8.72 109 | 45.4 80 | 58.6 88 | 11.1 93 | 31.1 117 | 53.4 109 | 5.26 81 | 38.9 87 | 74.2 39 | 4.20 96 | 38.0 118 | 60.3 121 | 3.56 67 |
NL-TV-NCC [25] | 83.0 | 13.7 116 | 27.3 85 | 2.94 48 | 18.5 80 | 24.7 101 | 4.04 56 | 15.0 95 | 29.0 89 | 3.70 82 | 25.6 110 | 46.4 122 | 7.94 85 | 42.0 13 | 51.9 11 | 10.4 61 | 30.6 113 | 51.9 104 | 5.29 87 | 41.9 111 | 81.7 83 | 4.40 110 | 31.3 59 | 48.6 51 | 3.79 121 |
TriangleFlow [30] | 83.4 | 12.5 102 | 25.9 73 | 3.11 73 | 18.8 85 | 24.3 90 | 4.24 66 | 13.2 88 | 29.7 97 | 3.46 79 | 21.2 81 | 35.4 71 | 7.94 85 | 44.4 59 | 57.7 68 | 9.95 7 | 29.4 97 | 48.6 55 | 5.07 46 | 43.9 120 | 99.9 124 | 4.43 114 | 42.1 126 | 69.7 129 | 3.56 67 |
Complementary OF [21] | 83.7 | 12.4 98 | 34.5 119 | 2.83 17 | 16.4 51 | 23.5 72 | 3.79 40 | 30.7 121 | 32.2 108 | 7.05 123 | 19.9 62 | 43.9 118 | 7.44 17 | 46.9 118 | 60.4 114 | 10.7 76 | 28.1 58 | 47.7 45 | 5.23 77 | 41.1 105 | 80.3 74 | 4.12 81 | 42.0 125 | 62.0 123 | 3.56 67 |
Correlation Flow [75] | 84.0 | 12.6 105 | 28.0 92 | 2.71 2 | 20.0 107 | 25.8 118 | 4.36 71 | 11.3 27 | 22.3 33 | 3.00 2 | 20.7 77 | 38.6 98 | 7.72 71 | 45.7 86 | 59.0 94 | 10.3 52 | 33.4 123 | 60.4 121 | 5.45 103 | 45.6 124 | 99.9 124 | 4.40 110 | 33.4 100 | 54.9 108 | 3.56 67 |
LocallyOriented [52] | 84.6 | 12.2 82 | 28.1 93 | 3.27 99 | 20.5 118 | 25.9 119 | 5.07 94 | 14.3 94 | 30.0 100 | 3.37 67 | 24.2 107 | 41.7 112 | 7.66 59 | 44.7 65 | 57.1 64 | 10.1 29 | 28.8 79 | 47.4 39 | 5.48 111 | 42.4 112 | 80.6 76 | 4.12 81 | 32.4 87 | 51.2 77 | 3.56 67 |
IAOF2 [51] | 85.4 | 12.7 106 | 28.7 96 | 3.32 101 | 20.4 116 | 25.9 119 | 4.76 84 | 12.7 83 | 31.7 106 | 3.11 62 | 22.4 95 | 35.8 76 | 8.06 94 | 45.9 94 | 59.6 102 | 10.8 79 | 29.9 102 | 51.5 98 | 5.10 62 | 39.0 88 | 79.7 70 | 4.08 38 | 31.2 56 | 49.0 56 | 3.56 67 |
Aniso-Texture [82] | 86.3 | 11.5 24 | 24.1 37 | 2.83 17 | 20.2 111 | 26.0 122 | 4.97 92 | 20.0 114 | 24.4 54 | 3.37 67 | 26.9 113 | 50.7 125 | 9.11 114 | 46.1 98 | 60.5 116 | 11.4 123 | 32.7 122 | 62.2 126 | 5.94 125 | 37.3 65 | 80.2 72 | 4.04 8 | 34.1 108 | 55.0 109 | 3.42 9 |
ACK-Prior [27] | 88.2 | 12.5 102 | 29.7 103 | 2.83 17 | 16.1 45 | 22.7 52 | 4.00 54 | 25.6 117 | 27.7 76 | 5.72 117 | 22.4 95 | 36.0 78 | 10.7 119 | 45.7 86 | 59.3 96 | 11.4 123 | 31.8 120 | 50.6 82 | 5.35 98 | 38.8 86 | 79.9 71 | 4.16 90 | 33.5 101 | 51.7 85 | 3.70 104 |
Rannacher [23] | 88.8 | 11.7 38 | 28.7 96 | 3.16 98 | 20.4 116 | 26.3 126 | 5.07 94 | 19.0 113 | 26.0 64 | 4.80 108 | 19.8 58 | 38.1 93 | 7.79 78 | 44.5 61 | 57.4 66 | 10.1 29 | 29.0 84 | 50.3 75 | 5.20 70 | 42.6 115 | 97.0 120 | 4.40 110 | 33.7 104 | 55.9 112 | 3.70 104 |
Learning Flow [11] | 90.1 | 12.1 75 | 24.6 53 | 3.27 99 | 19.7 101 | 25.2 110 | 5.00 93 | 39.7 129 | 47.7 130 | 7.68 125 | 24.6 109 | 35.0 68 | 8.19 98 | 45.2 77 | 58.6 88 | 10.5 71 | 28.4 67 | 48.0 48 | 5.45 103 | 38.4 79 | 77.8 64 | 4.40 110 | 32.6 94 | 48.4 47 | 3.92 125 |
2bit-BM-tele [98] | 90.8 | 11.7 38 | 27.0 84 | 3.79 120 | 20.2 111 | 26.3 126 | 5.07 94 | 12.0 61 | 23.2 44 | 4.00 97 | 21.2 81 | 36.1 79 | 8.16 97 | 45.3 78 | 58.0 74 | 10.3 52 | 34.0 126 | 61.8 123 | 5.92 124 | 54.1 131 | 99.9 124 | 5.72 129 | 29.8 32 | 47.4 37 | 3.74 118 |
FOLKI [16] | 91.4 | 13.0 110 | 30.9 111 | 4.97 129 | 22.2 127 | 24.9 107 | 9.00 129 | 17.3 105 | 33.0 112 | 7.00 120 | 33.4 126 | 38.7 99 | 17.0 127 | 44.3 55 | 55.8 49 | 10.4 61 | 27.6 45 | 49.7 64 | 5.48 111 | 36.2 52 | 74.2 39 | 4.80 122 | 30.4 45 | 44.9 21 | 4.08 127 |
SimpleFlow [49] | 92.4 | 12.0 62 | 24.0 35 | 2.94 48 | 18.5 80 | 24.4 93 | 4.24 66 | 32.7 124 | 39.0 121 | 5.69 115 | 18.0 25 | 36.2 83 | 7.55 38 | 46.9 118 | 60.8 117 | 11.1 93 | 31.4 119 | 58.1 119 | 5.35 98 | 49.4 128 | 99.9 124 | 5.16 127 | 40.0 122 | 63.0 126 | 3.46 36 |
SILK [79] | 92.5 | 13.3 114 | 30.7 110 | 3.83 123 | 22.0 126 | 25.3 111 | 7.16 124 | 34.7 128 | 40.0 123 | 7.77 127 | 26.6 112 | 36.6 85 | 8.60 107 | 45.1 74 | 57.9 72 | 10.0 17 | 28.4 67 | 50.9 92 | 6.03 127 | 34.8 19 | 71.8 21 | 4.51 118 | 31.4 60 | 48.0 45 | 3.74 118 |
StereoFlow [44] | 94.0 | 22.8 131 | 48.3 129 | 3.74 119 | 20.5 118 | 26.8 129 | 5.07 94 | 11.3 27 | 29.3 94 | 3.37 67 | 20.1 66 | 37.0 87 | 7.62 52 | 59.3 129 | 75.2 129 | 10.8 79 | 39.3 131 | 71.4 130 | 5.45 103 | 35.8 40 | 73.9 35 | 4.08 38 | 35.7 115 | 55.1 111 | 3.70 104 |
StereoOF-V1MT [119] | 95.8 | 13.7 116 | 32.7 115 | 3.00 60 | 18.7 83 | 23.6 73 | 4.80 87 | 21.8 116 | 28.0 80 | 5.07 111 | 31.6 122 | 40.6 108 | 9.57 116 | 46.5 106 | 58.9 93 | 11.5 129 | 29.2 91 | 50.2 70 | 6.45 130 | 42.4 112 | 94.7 116 | 4.80 122 | 31.4 60 | 48.3 46 | 3.46 36 |
Shiralkar [42] | 96.4 | 13.2 113 | 31.6 113 | 3.00 60 | 19.7 101 | 24.5 96 | 4.65 81 | 17.0 103 | 30.7 102 | 4.08 103 | 32.1 124 | 53.1 127 | 8.04 90 | 46.3 103 | 59.7 104 | 10.3 52 | 28.4 67 | 50.2 70 | 5.45 103 | 45.5 123 | 95.2 118 | 4.24 106 | 39.2 121 | 62.6 124 | 3.42 9 |
Dynamic MRF [7] | 98.3 | 12.1 75 | 26.8 83 | 2.94 48 | 18.0 77 | 23.9 79 | 4.16 64 | 18.3 110 | 30.7 102 | 5.00 109 | 28.9 118 | 39.8 102 | 10.5 118 | 45.9 94 | 58.6 88 | 11.2 100 | 30.9 115 | 56.0 117 | 5.80 123 | 43.0 116 | 90.3 107 | 4.65 120 | 33.7 104 | 51.8 87 | 3.70 104 |
Adaptive flow [45] | 98.8 | 13.4 115 | 25.8 72 | 4.51 126 | 21.8 125 | 25.4 114 | 7.26 125 | 13.7 90 | 27.5 75 | 4.69 106 | 24.1 106 | 35.2 70 | 8.76 111 | 47.3 122 | 61.5 122 | 10.2 47 | 33.8 125 | 61.9 124 | 5.45 103 | 35.9 44 | 73.2 32 | 4.20 96 | 34.7 112 | 54.7 106 | 3.70 104 |
UnFlow [129] | 100.2 | 14.9 122 | 40.2 125 | 3.11 73 | 18.5 80 | 23.4 68 | 5.48 105 | 15.3 96 | 31.3 105 | 4.36 104 | 22.8 100 | 38.0 92 | 8.45 104 | 48.3 125 | 63.0 125 | 10.9 86 | 32.4 121 | 62.0 125 | 5.72 118 | 35.4 29 | 71.2 15 | 4.32 108 | 45.5 129 | 66.0 128 | 3.87 123 |
SPSA-learn [13] | 103.4 | 12.3 91 | 33.7 118 | 3.37 105 | 19.2 91 | 23.6 73 | 5.45 104 | 30.0 120 | 39.7 122 | 7.00 120 | 26.9 113 | 41.3 110 | 8.41 103 | 46.7 112 | 60.1 108 | 10.2 47 | 29.4 97 | 50.6 82 | 5.20 70 | 53.7 130 | 99.9 124 | 8.43 131 | 51.4 130 | 72.0 130 | 3.51 51 |
HCIC-L [99] | 105.0 | 21.0 130 | 41.8 126 | 5.07 130 | 20.2 111 | 26.1 125 | 5.80 108 | 16.3 100 | 42.3 125 | 4.00 97 | 31.7 123 | 51.0 126 | 8.50 105 | 44.7 65 | 55.5 46 | 10.4 61 | 35.2 128 | 69.8 129 | 5.07 46 | 39.9 98 | 91.2 111 | 4.16 90 | 40.4 124 | 58.0 116 | 3.65 101 |
SegOF [10] | 105.4 | 12.3 91 | 33.1 116 | 3.11 73 | 17.9 74 | 23.8 77 | 4.51 76 | 29.0 119 | 34.3 115 | 6.16 118 | 32.8 125 | 78.9 131 | 8.33 99 | 48.1 124 | 63.6 126 | 11.2 100 | 28.5 74 | 54.3 113 | 5.72 118 | 44.6 121 | 99.9 124 | 4.97 125 | 37.9 117 | 61.4 122 | 3.51 51 |
FFV1MT [106] | 106.7 | 17.0 125 | 37.6 123 | 3.37 105 | 19.3 93 | 22.9 57 | 6.40 119 | 28.2 118 | 46.7 129 | 6.95 119 | 29.3 119 | 38.4 96 | 11.4 123 | 46.3 103 | 58.2 81 | 10.4 61 | 29.0 84 | 50.4 77 | 5.72 118 | 46.7 125 | 88.5 98 | 4.93 124 | 39.0 120 | 56.9 115 | 4.43 129 |
PGAM+LK [55] | 107.2 | 15.5 124 | 39.4 124 | 4.55 127 | 19.8 104 | 24.0 82 | 7.68 126 | 33.1 126 | 43.4 128 | 8.00 128 | 34.5 128 | 45.7 121 | 11.2 122 | 46.6 110 | 57.7 68 | 10.6 72 | 29.3 92 | 50.8 91 | 5.74 122 | 37.4 66 | 77.2 58 | 4.43 114 | 34.4 110 | 53.3 101 | 4.24 128 |
Heeger++ [104] | 107.4 | 19.8 128 | 44.7 127 | 3.11 73 | 18.9 87 | 22.8 54 | 6.45 120 | 33.0 125 | 35.2 116 | 7.16 124 | 29.3 119 | 38.4 96 | 11.4 123 | 51.5 127 | 65.2 127 | 11.3 116 | 28.4 67 | 46.9 32 | 6.78 131 | 47.9 127 | 84.5 92 | 4.69 121 | 40.1 123 | 58.8 119 | 3.70 104 |
SLK [47] | 109.0 | 13.9 119 | 29.9 105 | 3.79 120 | 20.0 107 | 22.8 54 | 6.22 115 | 32.0 123 | 33.7 113 | 7.72 126 | 33.4 126 | 46.4 122 | 16.1 126 | 48.5 126 | 61.7 123 | 10.3 52 | 28.4 67 | 47.9 47 | 5.72 118 | 43.2 117 | 97.9 121 | 4.97 125 | 38.7 119 | 59.8 120 | 4.04 126 |
Pyramid LK [2] | 116.8 | 14.4 121 | 37.3 122 | 4.93 128 | 23.7 129 | 25.3 111 | 9.98 131 | 42.2 130 | 35.7 117 | 12.3 130 | 56.2 131 | 64.2 129 | 35.8 131 | 65.6 130 | 83.9 130 | 10.6 72 | 28.1 58 | 46.1 25 | 5.48 111 | 45.2 122 | 99.9 124 | 5.89 130 | 53.6 131 | 75.1 131 | 5.42 130 |
GroupFlow [9] | 117.5 | 19.9 129 | 49.6 130 | 3.42 111 | 19.1 89 | 24.1 85 | 5.48 105 | 31.4 122 | 40.0 123 | 8.19 129 | 36.2 129 | 61.9 128 | 12.1 125 | 55.6 128 | 71.3 128 | 11.4 123 | 36.3 129 | 67.0 128 | 5.60 117 | 46.7 125 | 98.5 122 | 4.20 96 | 43.6 127 | 62.8 125 | 3.56 67 |
Periodicity [78] | 129.7 | 17.6 126 | 55.7 131 | 5.45 131 | 26.8 131 | 27.0 130 | 9.75 130 | 49.4 131 | 51.5 131 | 17.7 131 | 51.3 130 | 70.3 130 | 27.9 130 | 66.6 131 | 86.3 131 | 11.7 131 | 38.7 130 | 82.5 131 | 6.38 129 | 51.8 129 | 99.9 124 | 5.48 128 | 44.3 128 | 65.5 127 | 5.80 131 |
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. |