Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
A95 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] | 6.7 | 5.00 3 | 9.68 12 | 2.00 2 | 6.88 22 | 11.0 10 | 2.08 1 | 5.69 4 | 9.00 2 | 1.73 1 | 8.21 4 | 12.0 4 | 5.07 2 | 17.4 3 | 23.4 3 | 5.07 10 | 9.29 6 | 22.6 3 | 3.74 20 | 8.66 9 | 37.1 11 | 2.45 1 | 13.9 13 | 21.3 13 | 2.16 1 |
MDP-Flow2 [68] | 8.9 | 4.97 2 | 9.42 7 | 2.00 2 | 6.68 9 | 11.0 10 | 2.08 1 | 5.69 4 | 9.04 7 | 1.73 1 | 8.19 1 | 12.0 4 | 5.10 22 | 17.5 5 | 23.5 6 | 5.07 10 | 9.95 32 | 24.7 32 | 3.74 20 | 8.60 6 | 36.4 3 | 2.45 1 | 13.9 13 | 21.5 15 | 2.16 1 |
NNF-Local [87] | 17.7 | 5.07 11 | 10.1 25 | 2.00 2 | 6.40 1 | 10.0 3 | 2.08 1 | 5.69 4 | 9.00 2 | 1.73 1 | 8.66 35 | 14.5 77 | 5.10 22 | 17.6 8 | 23.8 15 | 5.07 10 | 10.4 66 | 25.8 62 | 3.74 20 | 8.66 9 | 37.5 17 | 2.45 1 | 13.9 13 | 21.6 18 | 2.16 1 |
PH-Flow [101] | 18.5 | 5.20 38 | 10.7 55 | 2.00 2 | 6.45 3 | 10.3 5 | 2.08 1 | 5.69 4 | 9.38 13 | 1.73 1 | 8.19 1 | 11.9 1 | 5.07 2 | 17.7 21 | 24.0 26 | 5.03 6 | 10.6 80 | 26.5 81 | 3.70 1 | 8.68 12 | 38.8 47 | 2.45 1 | 14.0 20 | 21.7 22 | 2.16 1 |
NN-field [71] | 18.7 | 5.07 11 | 10.4 41 | 2.00 2 | 6.45 3 | 10.0 3 | 2.08 1 | 5.97 49 | 9.00 2 | 1.73 1 | 8.76 48 | 15.0 87 | 5.10 22 | 17.6 8 | 23.7 11 | 5.07 10 | 10.1 44 | 25.0 40 | 3.74 20 | 8.54 4 | 36.9 8 | 2.45 1 | 13.9 13 | 21.6 18 | 2.16 1 |
NNF-EAC [103] | 20.9 | 5.35 73 | 10.0 21 | 2.08 59 | 7.05 32 | 11.6 23 | 2.08 1 | 6.00 50 | 9.35 10 | 1.73 1 | 8.35 7 | 12.4 9 | 5.23 77 | 17.7 21 | 23.9 23 | 5.07 10 | 9.47 7 | 22.9 4 | 3.70 1 | 8.83 23 | 37.0 10 | 2.45 1 | 14.0 20 | 21.6 18 | 2.16 1 |
IROF++ [58] | 22.8 | 5.23 57 | 10.8 64 | 2.00 2 | 6.88 22 | 11.5 21 | 2.08 1 | 6.00 50 | 10.0 28 | 1.73 1 | 8.19 1 | 11.9 1 | 5.07 2 | 17.9 41 | 24.4 49 | 5.10 29 | 9.49 9 | 24.2 24 | 3.74 20 | 9.09 53 | 37.2 14 | 2.45 1 | 14.0 20 | 22.1 36 | 2.16 1 |
SepConv-v1 [127] | 23.1 | 3.87 1 | 8.50 1 | 1.73 1 | 7.05 32 | 11.4 17 | 2.16 61 | 3.46 1 | 6.56 1 | 2.00 78 | 8.58 30 | 12.6 17 | 5.26 92 | 17.5 5 | 23.6 7 | 4.97 2 | 8.35 1 | 22.4 2 | 3.70 1 | 8.08 2 | 33.3 1 | 2.52 96 | 12.8 1 | 19.1 1 | 2.38 104 |
DF-Auto [115] | 25.9 | 5.03 8 | 8.87 2 | 2.16 85 | 7.72 63 | 13.1 59 | 2.38 93 | 5.69 4 | 9.20 9 | 1.73 1 | 8.68 37 | 12.5 13 | 5.10 22 | 17.4 3 | 23.4 3 | 5.16 54 | 9.47 7 | 24.0 17 | 3.74 20 | 8.98 37 | 38.4 37 | 2.45 1 | 14.0 20 | 21.8 26 | 2.16 1 |
DeepFlow2 [108] | 26.5 | 5.07 11 | 9.85 17 | 2.08 59 | 7.53 58 | 13.1 59 | 2.16 61 | 5.69 4 | 10.0 28 | 1.73 1 | 8.83 65 | 13.4 45 | 5.10 22 | 17.6 8 | 23.7 11 | 5.20 61 | 9.24 4 | 23.0 5 | 3.74 20 | 9.00 40 | 37.9 27 | 2.45 1 | 13.9 13 | 21.5 15 | 2.16 1 |
COFM [59] | 28.2 | 5.07 11 | 10.7 55 | 2.00 2 | 6.86 21 | 11.4 17 | 2.08 1 | 5.69 4 | 9.75 20 | 1.73 1 | 8.35 7 | 12.5 13 | 5.07 2 | 18.1 63 | 24.7 67 | 5.03 6 | 11.0 100 | 27.5 104 | 3.70 1 | 8.06 1 | 39.1 51 | 2.45 1 | 14.4 64 | 22.7 63 | 2.16 1 |
WLIF-Flow [93] | 28.8 | 5.10 29 | 10.2 31 | 2.00 2 | 7.00 31 | 11.9 34 | 2.08 1 | 5.69 4 | 9.68 16 | 1.73 1 | 8.29 5 | 12.2 6 | 5.23 77 | 17.8 31 | 24.0 26 | 5.10 29 | 10.6 80 | 26.6 85 | 3.83 95 | 8.83 23 | 37.5 17 | 2.45 1 | 14.1 33 | 21.9 33 | 2.16 1 |
LME [70] | 29.5 | 5.07 11 | 10.1 25 | 2.00 2 | 7.05 32 | 12.0 37 | 2.16 61 | 5.69 4 | 10.7 77 | 1.73 1 | 8.35 7 | 12.8 26 | 5.10 22 | 18.0 50 | 24.4 49 | 5.29 123 | 10.2 52 | 25.3 49 | 3.74 20 | 8.70 13 | 36.4 3 | 2.45 1 | 14.0 20 | 21.7 22 | 2.16 1 |
DeepFlow [86] | 29.7 | 5.07 11 | 9.63 11 | 2.08 59 | 7.44 54 | 13.0 53 | 2.16 61 | 5.74 42 | 10.0 28 | 1.73 1 | 8.96 79 | 13.0 29 | 5.20 51 | 17.6 8 | 23.8 15 | 5.20 61 | 9.15 3 | 23.2 7 | 3.87 103 | 8.81 20 | 35.6 2 | 2.45 1 | 13.7 5 | 21.1 7 | 2.16 1 |
Layers++ [37] | 30.0 | 5.10 29 | 10.1 25 | 2.08 59 | 6.45 3 | 9.88 1 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.37 14 | 12.7 22 | 5.10 22 | 18.1 63 | 24.9 84 | 5.10 29 | 10.7 88 | 28.3 115 | 3.74 20 | 8.76 14 | 38.0 31 | 2.45 1 | 14.1 33 | 21.9 33 | 2.16 1 |
ProbFlowFields [128] | 30.2 | 5.03 8 | 10.7 55 | 2.00 2 | 6.68 9 | 11.3 14 | 2.08 1 | 5.69 4 | 9.47 14 | 1.73 1 | 8.52 27 | 13.3 44 | 5.20 51 | 18.2 83 | 24.9 84 | 5.23 106 | 10.5 71 | 26.2 76 | 3.74 20 | 8.60 6 | 37.7 22 | 2.45 1 | 13.8 8 | 21.6 18 | 2.16 1 |
SuperFlow [81] | 30.4 | 5.00 3 | 9.35 4 | 2.16 85 | 7.85 68 | 13.1 59 | 2.38 93 | 6.00 50 | 9.47 14 | 2.00 78 | 8.70 41 | 12.7 22 | 5.20 51 | 17.6 8 | 23.7 11 | 5.20 61 | 9.27 5 | 23.9 15 | 3.70 1 | 8.81 20 | 37.6 20 | 2.45 1 | 13.8 8 | 21.2 10 | 2.16 1 |
CombBMOF [113] | 30.7 | 5.35 73 | 10.5 47 | 2.00 2 | 6.83 19 | 11.4 17 | 2.08 1 | 5.80 45 | 10.0 28 | 1.73 1 | 8.83 65 | 14.4 72 | 5.10 22 | 17.9 41 | 24.3 43 | 5.07 10 | 9.88 26 | 24.1 20 | 3.70 1 | 10.7 114 | 38.3 34 | 2.45 1 | 14.0 20 | 21.9 33 | 2.16 1 |
nLayers [57] | 30.8 | 5.16 36 | 10.5 47 | 2.00 2 | 6.66 8 | 10.9 9 | 2.08 1 | 5.69 4 | 9.00 2 | 1.73 1 | 8.49 26 | 13.0 29 | 5.10 22 | 18.3 93 | 25.2 103 | 5.20 61 | 10.4 66 | 25.6 56 | 3.74 20 | 8.66 9 | 38.5 41 | 2.45 1 | 14.2 48 | 22.4 53 | 2.16 1 |
Aniso. Huber-L1 [22] | 31.7 | 5.26 59 | 10.0 21 | 2.08 59 | 8.81 91 | 14.5 94 | 2.16 61 | 6.00 50 | 9.75 20 | 1.73 1 | 8.72 44 | 13.0 29 | 5.16 43 | 17.6 8 | 23.8 15 | 5.10 29 | 9.87 25 | 23.2 7 | 3.70 1 | 9.26 65 | 37.8 24 | 2.45 1 | 13.8 8 | 21.0 5 | 2.16 1 |
IROF-TV [53] | 31.9 | 5.20 38 | 10.7 55 | 2.08 59 | 7.05 32 | 11.9 34 | 2.08 1 | 6.00 50 | 10.3 55 | 1.73 1 | 8.37 14 | 12.6 17 | 5.16 43 | 17.8 31 | 24.1 34 | 5.23 106 | 10.1 44 | 25.0 40 | 3.70 1 | 9.04 47 | 39.1 51 | 2.45 1 | 13.7 5 | 21.0 5 | 2.16 1 |
Brox et al. [5] | 32.2 | 5.20 38 | 9.83 14 | 2.00 2 | 7.62 62 | 12.6 44 | 2.16 61 | 6.00 50 | 10.2 51 | 2.00 78 | 8.76 48 | 12.6 17 | 5.07 2 | 17.5 5 | 23.6 7 | 5.16 54 | 10.1 44 | 25.3 49 | 3.74 20 | 9.00 40 | 40.1 64 | 2.45 1 | 13.8 8 | 21.3 13 | 2.16 1 |
FMOF [94] | 32.3 | 5.42 90 | 11.0 71 | 2.00 2 | 6.76 14 | 11.0 10 | 2.08 1 | 6.00 50 | 10.3 55 | 1.73 1 | 8.83 65 | 14.1 65 | 5.10 22 | 17.8 31 | 24.1 34 | 5.07 10 | 10.0 42 | 25.6 56 | 3.74 20 | 8.58 5 | 37.7 22 | 2.45 1 | 14.3 55 | 22.4 53 | 2.16 1 |
Sparse-NonSparse [56] | 32.6 | 5.20 38 | 10.7 55 | 2.00 2 | 6.78 15 | 11.6 23 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.43 22 | 12.5 13 | 5.07 2 | 18.1 63 | 24.7 67 | 5.10 29 | 10.5 71 | 26.7 88 | 3.74 20 | 8.76 14 | 42.1 91 | 2.45 1 | 14.3 55 | 23.0 78 | 2.16 1 |
TV-L1-MCT [64] | 32.9 | 5.48 103 | 11.4 94 | 2.00 2 | 7.35 43 | 13.1 59 | 2.08 1 | 5.48 2 | 10.3 55 | 1.73 1 | 8.35 7 | 12.4 9 | 5.07 2 | 18.3 93 | 25.3 107 | 5.10 29 | 9.49 9 | 23.5 10 | 3.79 76 | 8.81 20 | 39.2 54 | 2.45 1 | 13.7 5 | 21.1 7 | 2.16 1 |
FlowFields [110] | 33.1 | 5.10 29 | 11.1 81 | 2.00 2 | 6.88 22 | 11.5 21 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.76 48 | 14.9 83 | 5.20 51 | 18.0 50 | 24.4 49 | 5.16 54 | 10.3 59 | 25.8 62 | 3.74 20 | 8.76 14 | 37.8 24 | 2.45 1 | 14.1 33 | 22.5 56 | 2.16 1 |
ComponentFusion [96] | 34.2 | 5.07 11 | 11.2 87 | 2.00 2 | 6.81 18 | 11.6 23 | 2.08 1 | 5.72 41 | 9.81 24 | 1.73 1 | 8.37 14 | 13.2 41 | 5.07 2 | 18.1 63 | 24.7 67 | 5.10 29 | 9.90 27 | 24.9 38 | 3.74 20 | 9.20 62 | 44.1 109 | 2.45 1 | 14.2 48 | 23.3 90 | 2.16 1 |
MDP-Flow [26] | 34.4 | 5.03 8 | 9.95 19 | 2.00 2 | 6.68 9 | 11.3 14 | 2.08 1 | 5.69 4 | 9.04 7 | 1.73 1 | 8.89 74 | 13.7 51 | 5.20 51 | 17.8 31 | 24.2 41 | 5.20 61 | 11.3 112 | 27.9 110 | 3.74 20 | 9.27 69 | 39.3 56 | 2.45 1 | 14.1 33 | 22.3 49 | 2.16 1 |
CLG-TV [48] | 36.5 | 5.20 38 | 9.49 8 | 2.08 59 | 8.43 82 | 14.3 88 | 2.16 61 | 6.00 50 | 10.1 47 | 2.00 78 | 8.76 48 | 13.1 37 | 5.20 51 | 17.6 8 | 23.8 15 | 5.10 29 | 9.59 16 | 23.1 6 | 3.74 20 | 9.20 62 | 38.4 37 | 2.45 1 | 14.0 20 | 21.5 15 | 2.16 1 |
2DHMM-SAS [92] | 36.5 | 5.42 90 | 11.2 87 | 2.00 2 | 7.90 70 | 13.7 72 | 2.08 1 | 5.60 3 | 9.85 25 | 1.73 1 | 8.35 7 | 12.2 6 | 5.10 22 | 18.0 50 | 24.6 65 | 5.10 29 | 9.93 30 | 25.7 59 | 3.74 20 | 8.96 32 | 39.8 62 | 2.45 1 | 14.4 64 | 23.0 78 | 2.16 1 |
PGM-C [120] | 37.1 | 5.07 11 | 10.9 69 | 2.00 2 | 6.93 25 | 11.6 23 | 2.08 1 | 6.00 50 | 10.3 55 | 1.73 1 | 8.76 48 | 15.2 89 | 5.16 43 | 18.0 50 | 24.7 67 | 5.20 61 | 9.97 37 | 24.8 36 | 3.74 20 | 9.00 40 | 40.1 64 | 2.45 1 | 14.1 33 | 22.7 63 | 2.16 1 |
FlowFields+ [130] | 37.3 | 5.10 29 | 11.1 81 | 2.00 2 | 6.78 15 | 11.3 14 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.70 41 | 14.9 83 | 5.16 43 | 18.2 83 | 24.9 84 | 5.20 61 | 10.4 66 | 26.3 79 | 3.74 20 | 8.79 18 | 38.6 45 | 2.45 1 | 14.1 33 | 22.7 63 | 2.16 1 |
ALD-Flow [66] | 38.2 | 5.20 38 | 10.7 55 | 2.08 59 | 7.35 43 | 12.9 49 | 2.16 61 | 6.00 50 | 10.1 47 | 1.73 1 | 8.39 19 | 13.0 29 | 5.16 43 | 17.9 41 | 24.3 43 | 5.20 61 | 9.56 13 | 23.5 10 | 3.79 76 | 8.79 18 | 36.8 7 | 2.45 1 | 14.5 75 | 23.0 78 | 2.16 1 |
CPM-Flow [116] | 38.3 | 5.07 11 | 10.9 69 | 2.00 2 | 6.95 27 | 11.6 23 | 2.08 1 | 5.80 45 | 10.0 28 | 1.73 1 | 9.00 82 | 15.9 104 | 5.20 51 | 18.1 63 | 24.7 67 | 5.20 61 | 9.81 20 | 24.3 25 | 3.79 76 | 9.26 65 | 38.3 34 | 2.45 1 | 14.0 20 | 22.2 42 | 2.16 1 |
HAST [109] | 39.1 | 5.07 11 | 10.5 47 | 2.00 2 | 6.68 9 | 10.7 8 | 2.08 1 | 6.00 50 | 10.3 55 | 1.73 1 | 8.29 5 | 12.4 9 | 5.00 1 | 18.4 103 | 25.3 107 | 5.03 6 | 11.0 100 | 30.7 124 | 3.70 1 | 8.60 6 | 41.8 86 | 2.45 1 | 14.9 101 | 23.9 103 | 2.16 1 |
Second-order prior [8] | 39.1 | 5.20 38 | 9.83 14 | 2.08 59 | 8.43 82 | 14.5 94 | 2.08 1 | 6.35 93 | 11.0 94 | 2.00 78 | 8.83 65 | 13.8 58 | 5.07 2 | 17.7 21 | 23.8 15 | 5.07 10 | 9.70 18 | 24.1 20 | 3.74 20 | 9.33 72 | 38.4 37 | 2.45 1 | 14.0 20 | 21.8 26 | 2.16 1 |
CBF [12] | 39.7 | 5.00 3 | 9.40 6 | 2.08 59 | 7.77 66 | 13.0 53 | 2.16 61 | 6.00 50 | 9.68 16 | 1.73 1 | 8.68 37 | 12.5 13 | 5.35 107 | 17.6 8 | 23.4 3 | 5.20 61 | 9.85 24 | 24.3 25 | 3.74 20 | 9.11 56 | 39.3 56 | 2.52 96 | 14.0 20 | 21.1 7 | 2.38 104 |
S2F-IF [123] | 39.8 | 5.10 29 | 11.6 103 | 2.00 2 | 6.78 15 | 11.4 17 | 2.08 1 | 5.69 4 | 10.3 55 | 1.73 1 | 8.74 45 | 15.2 89 | 5.07 2 | 18.3 93 | 25.1 99 | 5.20 61 | 10.5 71 | 26.1 71 | 3.74 20 | 9.02 45 | 38.5 41 | 2.45 1 | 14.1 33 | 22.6 57 | 2.16 1 |
Local-TV-L1 [65] | 40.1 | 5.20 38 | 9.38 5 | 2.16 85 | 8.96 97 | 14.5 94 | 2.38 93 | 5.69 4 | 9.35 10 | 1.73 1 | 8.70 41 | 13.0 29 | 5.45 112 | 17.6 8 | 23.8 15 | 5.16 54 | 9.54 12 | 24.0 17 | 4.08 124 | 8.76 14 | 37.2 14 | 2.45 1 | 13.6 4 | 20.9 4 | 2.31 86 |
Ramp [62] | 40.4 | 5.29 66 | 10.8 64 | 2.00 2 | 6.83 19 | 11.6 23 | 2.08 1 | 5.69 4 | 10.1 47 | 1.73 1 | 8.35 7 | 12.2 6 | 5.07 2 | 18.1 63 | 24.7 67 | 5.10 29 | 10.9 95 | 27.8 109 | 3.79 76 | 8.83 23 | 43.0 102 | 2.45 1 | 14.5 75 | 23.2 86 | 2.16 1 |
SIOF [67] | 40.8 | 5.42 90 | 10.4 41 | 2.08 59 | 8.83 92 | 15.0 107 | 2.38 93 | 5.69 4 | 10.4 74 | 1.73 1 | 8.68 37 | 13.1 37 | 5.20 51 | 17.3 2 | 23.2 2 | 5.07 10 | 9.83 21 | 23.6 12 | 3.74 20 | 9.00 40 | 36.9 8 | 2.45 1 | 14.3 55 | 22.1 36 | 2.31 86 |
p-harmonic [29] | 41.1 | 5.07 11 | 9.98 20 | 2.00 2 | 8.68 88 | 14.4 90 | 2.16 61 | 6.00 50 | 10.7 77 | 1.91 74 | 9.20 90 | 13.7 51 | 5.20 51 | 17.8 31 | 24.0 26 | 5.10 29 | 9.90 27 | 23.7 13 | 3.74 20 | 9.61 91 | 38.5 41 | 2.45 1 | 14.0 20 | 21.7 22 | 2.16 1 |
LDOF [28] | 42.5 | 5.35 73 | 9.83 14 | 2.16 85 | 7.94 71 | 12.1 39 | 2.52 109 | 6.00 50 | 10.3 55 | 2.00 78 | 8.91 77 | 13.6 50 | 5.23 77 | 17.6 8 | 23.6 7 | 5.20 61 | 9.49 9 | 24.5 29 | 3.74 20 | 8.96 32 | 37.9 27 | 2.45 1 | 14.0 20 | 21.8 26 | 2.16 1 |
Kuang [131] | 42.9 | 5.20 38 | 11.2 87 | 2.00 2 | 7.16 39 | 12.0 37 | 2.08 1 | 6.00 50 | 10.7 77 | 1.73 1 | 8.83 65 | 15.3 93 | 5.20 51 | 18.1 63 | 24.5 56 | 5.20 61 | 10.1 44 | 25.4 52 | 3.70 1 | 9.56 88 | 39.5 60 | 2.45 1 | 14.0 20 | 22.2 42 | 2.16 1 |
DPOF [18] | 43.2 | 5.35 73 | 11.7 105 | 2.08 59 | 6.56 7 | 10.4 6 | 2.08 1 | 6.00 50 | 9.71 19 | 1.91 74 | 8.76 48 | 14.4 72 | 5.20 51 | 17.7 21 | 24.1 34 | 5.07 10 | 10.3 59 | 26.7 88 | 3.70 1 | 9.33 72 | 39.1 51 | 2.45 1 | 14.4 64 | 22.8 69 | 2.16 1 |
ComplOF-FED-GPU [35] | 43.4 | 5.20 38 | 11.1 81 | 2.00 2 | 7.19 40 | 12.6 44 | 2.08 1 | 6.35 93 | 10.0 28 | 2.00 78 | 8.68 37 | 14.0 64 | 5.10 22 | 17.9 41 | 24.5 56 | 5.10 29 | 9.97 37 | 25.1 43 | 3.74 20 | 9.40 77 | 38.8 47 | 2.45 1 | 14.5 75 | 23.2 86 | 2.16 1 |
OFLAF [77] | 44.0 | 5.07 11 | 10.6 52 | 2.00 2 | 6.48 6 | 10.5 7 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.37 14 | 12.6 17 | 5.07 2 | 18.4 103 | 25.4 113 | 5.20 61 | 10.9 95 | 27.4 102 | 3.74 20 | 9.59 90 | 44.9 113 | 2.45 1 | 15.1 106 | 24.1 105 | 2.16 1 |
AGIF+OF [85] | 44.1 | 5.42 90 | 11.1 81 | 2.00 2 | 6.98 28 | 11.8 31 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.43 22 | 12.8 26 | 5.07 2 | 18.5 110 | 25.2 103 | 5.20 61 | 10.8 93 | 27.6 105 | 3.74 20 | 8.98 37 | 37.9 27 | 2.45 1 | 14.7 91 | 23.4 94 | 2.16 1 |
LSM [39] | 44.5 | 5.35 73 | 11.5 99 | 2.00 2 | 6.98 28 | 11.9 34 | 2.08 1 | 5.80 45 | 10.7 77 | 1.73 1 | 8.58 30 | 13.4 45 | 5.07 2 | 18.1 63 | 24.9 84 | 5.10 29 | 10.6 80 | 27.1 96 | 3.74 20 | 8.83 23 | 42.2 93 | 2.45 1 | 14.4 64 | 23.0 78 | 2.16 1 |
FC-2Layers-FF [74] | 44.5 | 5.26 59 | 11.0 71 | 2.00 2 | 6.40 1 | 9.88 1 | 2.08 1 | 5.69 4 | 10.3 55 | 1.73 1 | 8.39 19 | 12.8 26 | 5.10 22 | 18.2 83 | 25.0 93 | 5.20 61 | 11.0 100 | 28.1 112 | 3.79 76 | 8.91 30 | 42.8 97 | 2.45 1 | 14.5 75 | 23.0 78 | 2.16 1 |
Classic+NL [31] | 44.9 | 5.35 73 | 11.0 71 | 2.08 59 | 6.98 28 | 11.7 29 | 2.08 1 | 5.69 4 | 10.2 51 | 1.73 1 | 8.43 22 | 12.4 9 | 5.20 51 | 18.1 63 | 24.8 77 | 5.10 29 | 10.6 80 | 26.8 91 | 3.79 76 | 8.83 23 | 42.9 98 | 2.45 1 | 14.4 64 | 22.9 76 | 2.16 1 |
RFlow [90] | 45.0 | 5.07 11 | 10.2 31 | 2.08 59 | 8.58 86 | 14.7 100 | 2.08 1 | 6.00 50 | 10.3 55 | 1.73 1 | 8.91 77 | 14.4 72 | 5.20 51 | 17.7 21 | 23.9 23 | 5.10 29 | 9.95 32 | 25.4 52 | 3.70 1 | 9.13 58 | 40.4 70 | 2.45 1 | 14.3 55 | 22.6 57 | 2.31 86 |
OAR-Flow [125] | 45.0 | 5.20 38 | 10.7 55 | 2.08 59 | 7.44 54 | 13.0 53 | 2.16 61 | 5.74 42 | 10.0 28 | 1.73 1 | 8.35 7 | 13.0 29 | 5.10 22 | 18.1 63 | 24.9 84 | 5.23 106 | 10.2 52 | 24.7 32 | 3.74 20 | 9.54 87 | 39.4 59 | 2.45 1 | 14.4 64 | 22.7 63 | 2.16 1 |
RNLOD-Flow [121] | 46.0 | 5.20 38 | 11.0 71 | 2.00 2 | 7.53 58 | 13.4 65 | 2.08 1 | 6.00 50 | 11.0 94 | 1.73 1 | 8.52 27 | 13.0 29 | 5.07 2 | 18.2 83 | 25.0 93 | 5.10 29 | 10.6 80 | 26.9 93 | 3.74 20 | 8.96 32 | 38.4 37 | 2.45 1 | 14.9 101 | 23.5 96 | 2.16 1 |
TF+OM [100] | 46.2 | 5.00 3 | 10.2 31 | 2.08 59 | 6.93 25 | 11.7 29 | 2.16 61 | 5.69 4 | 10.5 75 | 1.73 1 | 8.81 60 | 14.6 78 | 5.20 51 | 18.0 50 | 24.4 49 | 5.20 61 | 9.95 32 | 26.1 71 | 3.79 76 | 9.09 53 | 41.0 76 | 2.45 1 | 14.1 33 | 21.8 26 | 2.38 104 |
TC/T-Flow [76] | 46.7 | 5.45 98 | 11.5 99 | 2.00 2 | 7.42 51 | 13.0 53 | 2.08 1 | 5.69 4 | 9.76 22 | 1.73 1 | 8.60 33 | 13.7 51 | 5.16 43 | 18.3 93 | 24.9 84 | 5.20 61 | 10.1 44 | 24.9 38 | 3.74 20 | 9.75 94 | 42.6 94 | 2.45 1 | 14.5 75 | 22.6 57 | 2.16 1 |
F-TV-L1 [15] | 46.9 | 5.35 73 | 10.3 38 | 2.16 85 | 8.83 92 | 14.6 99 | 2.16 61 | 6.00 50 | 10.3 55 | 2.00 78 | 8.76 48 | 13.2 41 | 5.26 92 | 17.6 8 | 23.8 15 | 5.03 6 | 9.57 15 | 23.2 7 | 3.79 76 | 9.18 61 | 37.6 20 | 2.45 1 | 13.8 8 | 21.2 10 | 2.31 86 |
EpicFlow [102] | 47.6 | 5.07 11 | 11.0 71 | 2.00 2 | 7.39 47 | 12.9 49 | 2.08 1 | 5.80 45 | 10.3 55 | 1.73 1 | 8.85 72 | 15.5 98 | 5.20 51 | 18.1 63 | 24.8 77 | 5.20 61 | 10.2 52 | 25.1 43 | 3.74 20 | 9.33 72 | 40.4 70 | 2.45 1 | 14.5 75 | 24.1 105 | 2.16 1 |
TC-Flow [46] | 48.5 | 5.07 11 | 10.8 64 | 2.00 2 | 7.39 47 | 13.2 64 | 2.16 61 | 6.00 50 | 10.3 55 | 1.73 1 | 8.66 35 | 13.7 51 | 5.23 77 | 18.2 83 | 25.0 93 | 5.20 61 | 10.2 52 | 24.5 29 | 3.79 76 | 9.04 47 | 38.1 32 | 2.45 1 | 14.5 75 | 23.5 96 | 2.16 1 |
S2D-Matching [84] | 48.6 | 5.35 73 | 11.2 87 | 2.00 2 | 7.75 65 | 13.5 68 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.37 14 | 12.6 17 | 5.20 51 | 18.3 93 | 25.2 103 | 5.07 10 | 11.0 100 | 27.7 108 | 3.79 76 | 9.09 53 | 40.3 68 | 2.45 1 | 14.4 64 | 23.0 78 | 2.16 1 |
Fusion [6] | 50.8 | 5.20 38 | 10.4 41 | 2.00 2 | 7.14 38 | 11.8 31 | 2.08 1 | 5.74 42 | 9.68 16 | 1.73 1 | 9.33 93 | 14.2 66 | 5.20 51 | 18.3 93 | 24.7 67 | 5.07 10 | 11.6 116 | 28.1 112 | 3.70 1 | 9.63 92 | 41.4 81 | 2.45 1 | 15.3 117 | 24.2 108 | 2.16 1 |
Modified CLG [34] | 51.0 | 5.07 11 | 9.49 8 | 2.16 85 | 9.42 110 | 14.2 86 | 2.65 113 | 6.00 50 | 11.5 103 | 2.00 78 | 9.15 87 | 14.3 68 | 5.10 22 | 17.7 21 | 23.9 23 | 5.10 29 | 10.1 44 | 24.7 32 | 3.74 20 | 9.31 71 | 37.5 17 | 2.45 1 | 14.1 33 | 21.8 26 | 2.31 86 |
Classic++ [32] | 51.6 | 5.20 38 | 10.3 38 | 2.08 59 | 7.94 71 | 13.8 74 | 2.08 1 | 6.00 50 | 10.1 47 | 1.73 1 | 8.89 74 | 13.7 51 | 5.23 77 | 18.0 50 | 24.5 56 | 5.10 29 | 10.3 59 | 25.8 62 | 3.87 103 | 9.13 58 | 40.1 64 | 2.45 1 | 14.2 48 | 22.2 42 | 2.31 86 |
Sparse Occlusion [54] | 52.9 | 5.26 59 | 10.5 47 | 2.08 59 | 8.04 73 | 14.4 90 | 2.08 1 | 6.00 50 | 10.0 28 | 1.73 1 | 8.83 65 | 13.7 51 | 5.20 51 | 18.1 63 | 24.7 67 | 5.20 61 | 11.0 100 | 26.5 81 | 3.74 20 | 9.42 78 | 42.0 90 | 2.45 1 | 14.4 64 | 22.8 69 | 2.16 1 |
AggregFlow [97] | 53.0 | 5.45 98 | 13.8 121 | 2.08 59 | 7.44 54 | 13.1 59 | 2.16 61 | 5.69 4 | 9.95 27 | 1.73 1 | 9.15 87 | 16.1 105 | 5.10 22 | 18.0 50 | 24.5 56 | 5.20 61 | 9.90 27 | 24.6 31 | 3.83 95 | 8.98 37 | 40.7 73 | 2.45 1 | 14.4 64 | 23.0 78 | 2.16 1 |
FESL [72] | 53.9 | 5.42 90 | 11.0 71 | 2.00 2 | 7.05 32 | 11.8 31 | 2.08 1 | 5.69 4 | 10.7 77 | 1.73 1 | 8.81 60 | 13.5 48 | 5.20 51 | 18.4 103 | 25.1 99 | 5.20 61 | 11.0 100 | 27.0 95 | 3.74 20 | 9.06 51 | 42.9 98 | 2.45 1 | 14.8 96 | 23.7 100 | 2.16 1 |
BlockOverlap [61] | 54.1 | 5.20 38 | 9.29 3 | 2.16 85 | 8.74 90 | 14.1 81 | 2.65 113 | 6.00 50 | 9.35 10 | 2.00 78 | 8.52 27 | 11.9 1 | 5.60 119 | 17.8 31 | 24.0 26 | 5.32 125 | 9.83 21 | 25.0 40 | 4.04 120 | 8.83 23 | 37.1 11 | 2.52 96 | 13.5 3 | 20.6 3 | 2.38 104 |
PMF [73] | 54.2 | 5.20 38 | 11.4 94 | 2.00 2 | 7.35 43 | 12.4 42 | 2.08 1 | 6.00 50 | 12.0 110 | 1.73 1 | 8.76 48 | 14.4 72 | 5.07 2 | 18.4 103 | 25.0 93 | 5.10 29 | 10.2 52 | 25.8 62 | 3.87 103 | 9.04 47 | 41.3 80 | 2.45 1 | 15.2 115 | 24.5 112 | 2.16 1 |
Classic+CPF [83] | 54.6 | 5.35 73 | 11.3 92 | 2.00 2 | 7.07 37 | 12.1 39 | 2.08 1 | 5.69 4 | 10.5 75 | 1.73 1 | 8.43 22 | 12.7 22 | 5.07 2 | 18.7 119 | 25.7 122 | 5.20 61 | 11.2 109 | 28.7 118 | 3.74 20 | 9.42 78 | 42.9 98 | 2.45 1 | 15.1 106 | 24.2 108 | 2.16 1 |
TCOF [69] | 55.2 | 5.35 73 | 10.7 55 | 2.00 2 | 9.27 104 | 15.4 114 | 2.16 61 | 5.69 4 | 10.2 51 | 1.73 1 | 8.74 45 | 13.1 37 | 5.23 77 | 17.7 21 | 23.8 15 | 5.07 10 | 10.7 88 | 26.6 85 | 3.70 1 | 10.0 102 | 44.7 112 | 2.45 1 | 14.6 86 | 22.9 76 | 2.38 104 |
FlowNetS+ft+v [112] | 55.5 | 5.26 59 | 10.1 25 | 2.16 85 | 9.11 101 | 14.5 94 | 2.45 104 | 6.00 50 | 10.3 55 | 2.00 78 | 8.96 79 | 13.5 48 | 5.26 92 | 17.8 31 | 24.1 34 | 5.23 106 | 9.76 19 | 23.9 15 | 3.74 20 | 9.38 76 | 41.6 84 | 2.45 1 | 14.1 33 | 22.2 42 | 2.16 1 |
OFH [38] | 56.2 | 5.35 73 | 11.0 71 | 2.08 59 | 8.06 76 | 13.7 72 | 2.08 1 | 6.00 50 | 11.6 104 | 1.73 1 | 8.58 30 | 13.9 62 | 5.07 2 | 18.2 83 | 24.9 84 | 5.16 54 | 10.3 59 | 25.1 43 | 3.74 20 | 9.88 98 | 42.7 96 | 2.45 1 | 14.8 96 | 24.7 113 | 2.16 1 |
SVFilterOh [111] | 56.2 | 5.20 38 | 10.6 52 | 2.00 2 | 6.73 13 | 11.0 10 | 2.08 1 | 6.00 50 | 10.0 28 | 1.73 1 | 8.76 48 | 13.8 58 | 5.26 92 | 18.4 103 | 25.3 107 | 5.26 116 | 10.6 80 | 28.0 111 | 3.74 20 | 8.45 3 | 39.2 54 | 2.52 96 | 14.7 91 | 23.3 90 | 2.31 86 |
CRTflow [80] | 56.9 | 5.29 66 | 10.5 47 | 2.16 85 | 8.43 82 | 14.5 94 | 2.16 61 | 6.35 93 | 11.1 100 | 2.00 78 | 8.64 34 | 13.0 29 | 5.29 101 | 18.0 50 | 24.5 56 | 5.20 61 | 9.68 17 | 23.8 14 | 3.74 20 | 9.00 40 | 40.9 75 | 2.45 1 | 14.1 33 | 22.2 42 | 2.31 86 |
EPPM w/o HM [88] | 57.5 | 5.23 57 | 12.6 113 | 2.00 2 | 7.39 47 | 13.0 53 | 2.08 1 | 6.35 93 | 14.0 124 | 1.91 74 | 8.83 65 | 15.3 93 | 5.10 22 | 18.0 50 | 24.5 56 | 5.10 29 | 10.5 71 | 27.6 105 | 3.74 20 | 9.11 56 | 41.9 87 | 2.45 1 | 14.5 75 | 23.2 86 | 2.16 1 |
SRR-TVOF-NL [91] | 57.5 | 5.45 98 | 12.1 111 | 2.08 59 | 7.77 66 | 13.5 68 | 2.16 61 | 6.00 50 | 10.3 55 | 1.73 1 | 9.26 91 | 14.7 80 | 5.07 2 | 18.1 63 | 24.6 65 | 5.10 29 | 10.4 66 | 26.6 85 | 3.70 1 | 9.42 78 | 38.5 41 | 2.45 1 | 15.1 106 | 23.9 103 | 2.16 1 |
Efficient-NL [60] | 57.6 | 5.35 73 | 10.7 55 | 2.00 2 | 7.42 51 | 13.0 53 | 2.08 1 | 6.35 93 | 10.7 77 | 2.00 78 | 8.81 60 | 13.4 45 | 5.10 22 | 18.1 63 | 24.7 67 | 5.10 29 | 11.2 109 | 27.6 105 | 3.70 1 | 9.47 82 | 43.6 107 | 2.45 1 | 15.1 106 | 23.8 102 | 2.16 1 |
2D-CLG [1] | 58.0 | 5.16 36 | 10.0 21 | 2.16 85 | 9.90 115 | 14.2 86 | 2.83 120 | 6.35 93 | 10.7 77 | 2.00 78 | 10.0 107 | 15.2 89 | 5.10 22 | 17.7 21 | 24.1 34 | 5.20 61 | 10.1 44 | 24.1 20 | 3.74 20 | 9.81 95 | 43.6 107 | 2.45 1 | 14.1 33 | 21.8 26 | 2.16 1 |
MLDP_OF [89] | 58.2 | 5.32 70 | 11.1 81 | 2.00 2 | 7.55 61 | 13.6 70 | 2.08 1 | 5.69 4 | 10.0 28 | 1.73 1 | 8.76 48 | 13.1 37 | 5.26 92 | 18.0 50 | 24.5 56 | 5.20 61 | 11.0 100 | 26.9 93 | 4.08 124 | 9.26 65 | 38.2 33 | 2.52 96 | 14.4 64 | 22.6 57 | 2.38 104 |
Steered-L1 [118] | 58.4 | 5.07 11 | 9.81 13 | 2.00 2 | 7.35 43 | 12.8 48 | 2.16 61 | 6.35 93 | 10.3 55 | 2.00 78 | 9.31 92 | 14.3 68 | 5.35 107 | 18.2 83 | 24.7 67 | 5.07 10 | 10.2 52 | 25.7 59 | 3.79 76 | 9.33 72 | 40.4 70 | 2.45 1 | 14.6 86 | 22.8 69 | 2.31 86 |
Occlusion-TV-L1 [63] | 60.0 | 5.20 38 | 10.2 31 | 2.08 59 | 8.89 94 | 15.3 112 | 2.16 61 | 6.00 50 | 10.3 55 | 2.00 78 | 9.15 87 | 15.4 95 | 5.26 92 | 17.6 8 | 23.7 11 | 5.10 29 | 9.98 39 | 25.5 55 | 3.87 103 | 10.3 107 | 39.3 56 | 2.52 96 | 14.1 33 | 22.3 49 | 2.16 1 |
IAOF [50] | 60.2 | 5.60 108 | 11.0 71 | 2.16 85 | 12.0 129 | 16.9 130 | 2.52 109 | 5.69 4 | 11.0 94 | 2.00 78 | 9.76 104 | 14.3 68 | 5.20 51 | 17.7 21 | 24.0 26 | 5.07 10 | 10.0 42 | 25.2 47 | 3.74 20 | 9.47 82 | 41.4 81 | 2.45 1 | 14.2 48 | 22.1 36 | 2.16 1 |
Complementary OF [21] | 62.0 | 5.20 38 | 12.0 109 | 2.00 2 | 7.19 40 | 12.9 49 | 2.08 1 | 6.68 110 | 10.8 90 | 2.00 78 | 8.76 48 | 14.6 78 | 5.16 43 | 18.2 83 | 25.2 103 | 5.10 29 | 10.3 59 | 25.9 66 | 3.74 20 | 9.97 101 | 42.6 94 | 2.45 1 | 15.6 120 | 28.0 125 | 2.16 1 |
Ad-TV-NDC [36] | 62.4 | 5.66 110 | 9.88 18 | 2.52 124 | 10.1 118 | 15.1 108 | 2.71 116 | 6.00 50 | 10.7 77 | 1.73 1 | 9.49 100 | 14.2 66 | 5.35 107 | 17.7 21 | 24.0 26 | 5.20 61 | 9.56 13 | 24.0 17 | 3.87 103 | 9.56 88 | 38.6 45 | 2.45 1 | 13.9 13 | 21.2 10 | 2.38 104 |
Adaptive [20] | 63.0 | 5.32 70 | 10.3 38 | 2.16 85 | 9.29 107 | 15.4 114 | 2.16 61 | 6.00 50 | 10.7 77 | 1.73 1 | 8.81 60 | 13.8 58 | 5.20 51 | 17.9 41 | 24.3 43 | 5.07 10 | 10.4 66 | 26.0 67 | 3.79 76 | 9.83 96 | 44.6 110 | 2.45 1 | 14.5 75 | 22.8 69 | 2.31 86 |
Black & Anandan [4] | 64.4 | 5.45 98 | 10.1 25 | 2.16 85 | 10.2 121 | 15.3 112 | 2.45 104 | 6.68 110 | 11.3 101 | 2.00 78 | 10.2 108 | 15.6 99 | 5.20 51 | 17.8 31 | 24.0 26 | 5.16 54 | 9.83 21 | 24.7 32 | 3.74 20 | 10.2 106 | 41.9 87 | 2.45 1 | 14.2 48 | 21.8 26 | 2.16 1 |
CostFilter [40] | 64.5 | 5.32 70 | 13.2 118 | 2.00 2 | 7.33 42 | 12.3 41 | 2.08 1 | 6.06 89 | 13.5 123 | 1.73 1 | 8.96 79 | 16.1 105 | 5.07 2 | 18.6 115 | 25.6 121 | 5.16 54 | 9.98 39 | 24.8 36 | 4.04 120 | 9.20 62 | 43.5 106 | 2.45 1 | 15.1 106 | 24.9 115 | 2.16 1 |
HBM-GC [105] | 64.6 | 5.35 73 | 10.6 52 | 2.16 85 | 7.42 51 | 13.4 65 | 2.16 61 | 5.69 4 | 9.00 2 | 1.73 1 | 8.74 45 | 13.2 41 | 5.26 92 | 18.6 115 | 25.5 118 | 5.26 116 | 11.8 122 | 31.5 127 | 3.83 95 | 8.83 23 | 41.1 78 | 2.45 1 | 14.3 55 | 22.2 42 | 2.31 86 |
CNN-flow-warp+ref [117] | 64.6 | 5.00 3 | 9.59 10 | 2.16 85 | 8.35 80 | 13.6 70 | 2.16 61 | 6.35 93 | 11.8 109 | 2.00 78 | 10.6 113 | 15.4 95 | 5.48 116 | 17.8 31 | 24.3 43 | 5.23 106 | 9.95 32 | 24.3 25 | 3.83 95 | 9.83 96 | 44.6 110 | 2.45 1 | 14.2 48 | 22.3 49 | 2.16 1 |
BriefMatch [124] | 65.3 | 5.29 66 | 11.4 94 | 2.08 59 | 7.44 54 | 12.7 46 | 2.16 61 | 6.38 108 | 9.93 26 | 2.00 78 | 9.83 106 | 14.9 83 | 5.83 126 | 18.0 50 | 24.4 49 | 5.20 61 | 10.5 71 | 27.3 100 | 4.32 129 | 9.04 47 | 37.9 27 | 2.45 1 | 14.3 55 | 22.8 69 | 2.16 1 |
AdaConv-v1 [126] | 66.9 | 6.24 121 | 14.4 122 | 2.38 118 | 9.02 98 | 12.7 46 | 3.11 125 | 7.00 118 | 11.0 94 | 2.38 124 | 13.1 126 | 18.8 119 | 5.83 126 | 16.8 1 | 22.5 1 | 4.83 1 | 8.79 2 | 22.0 1 | 3.70 1 | 8.91 30 | 36.6 6 | 2.58 118 | 13.3 2 | 20.2 2 | 2.38 104 |
HBpMotionGpu [43] | 67.1 | 5.48 103 | 10.8 64 | 2.38 118 | 10.1 118 | 15.4 114 | 2.71 116 | 5.69 4 | 10.0 28 | 1.73 1 | 9.40 95 | 16.2 109 | 5.23 77 | 17.9 41 | 24.3 43 | 5.20 61 | 10.5 71 | 26.4 80 | 3.83 95 | 8.96 32 | 37.8 24 | 2.45 1 | 14.3 55 | 22.6 57 | 2.38 104 |
TriFlow [95] | 68.5 | 5.26 59 | 12.0 109 | 2.16 85 | 8.39 81 | 14.4 90 | 2.38 93 | 6.00 50 | 11.0 94 | 1.73 1 | 9.02 83 | 15.4 95 | 5.10 22 | 18.5 110 | 25.4 113 | 5.20 61 | 10.6 80 | 27.3 100 | 3.74 20 | 9.26 65 | 39.7 61 | 2.45 1 | 14.6 86 | 23.1 85 | 2.16 1 |
Nguyen [33] | 68.6 | 5.42 90 | 10.0 21 | 2.38 118 | 10.9 124 | 15.1 108 | 2.65 113 | 6.00 50 | 12.0 110 | 2.00 78 | 10.4 112 | 16.1 105 | 5.20 51 | 17.8 31 | 24.1 34 | 5.07 10 | 9.98 39 | 25.3 49 | 3.70 1 | 10.9 118 | 46.9 119 | 2.52 96 | 14.1 33 | 22.1 36 | 2.16 1 |
Aniso-Texture [82] | 69.9 | 5.07 11 | 10.2 31 | 2.00 2 | 8.89 94 | 15.2 111 | 2.16 61 | 6.35 93 | 10.3 55 | 1.73 1 | 9.04 84 | 16.1 105 | 5.29 101 | 18.3 93 | 24.9 84 | 5.23 106 | 11.8 122 | 30.0 122 | 3.83 95 | 9.06 51 | 40.2 67 | 2.45 1 | 14.7 91 | 23.5 96 | 2.16 1 |
TV-L1-improved [17] | 72.2 | 5.10 29 | 10.2 31 | 2.08 59 | 9.20 103 | 15.4 114 | 2.16 61 | 6.35 93 | 10.3 55 | 2.00 78 | 8.85 72 | 13.8 58 | 5.23 77 | 18.0 50 | 24.4 49 | 5.10 29 | 10.6 80 | 26.5 81 | 3.79 76 | 9.93 100 | 46.9 119 | 2.52 96 | 14.3 55 | 22.7 63 | 2.38 104 |
FlowNet2 [122] | 72.2 | 6.45 125 | 19.1 129 | 2.16 85 | 7.85 68 | 13.4 65 | 2.38 93 | 6.06 89 | 11.7 105 | 1.73 1 | 9.40 95 | 18.2 115 | 5.23 77 | 18.5 110 | 25.3 107 | 5.20 61 | 10.3 59 | 25.2 47 | 3.74 20 | 9.27 69 | 41.9 87 | 2.45 1 | 14.3 55 | 22.8 69 | 2.16 1 |
Bartels [41] | 73.3 | 5.35 73 | 11.4 94 | 2.16 85 | 7.72 63 | 14.0 80 | 2.38 93 | 6.00 50 | 10.3 55 | 2.00 78 | 9.11 86 | 15.0 87 | 5.69 121 | 17.6 8 | 23.6 7 | 5.45 129 | 10.7 88 | 27.2 97 | 4.55 131 | 8.96 32 | 36.4 3 | 2.65 127 | 14.1 33 | 22.1 36 | 2.38 104 |
GraphCuts [14] | 73.5 | 5.66 110 | 11.9 108 | 2.16 85 | 7.53 58 | 12.5 43 | 2.38 93 | 7.68 124 | 10.2 51 | 2.00 78 | 9.47 99 | 14.9 83 | 5.23 77 | 18.1 63 | 24.5 56 | 5.00 3 | 10.1 44 | 25.7 59 | 3.70 1 | 9.02 45 | 42.1 91 | 2.52 96 | 15.1 106 | 24.1 105 | 2.31 86 |
SimpleFlow [49] | 74.0 | 5.35 73 | 11.0 71 | 2.00 2 | 8.04 73 | 13.9 77 | 2.08 1 | 6.56 109 | 11.3 101 | 2.00 78 | 8.41 21 | 12.7 22 | 5.20 51 | 18.4 103 | 25.4 113 | 5.20 61 | 11.4 114 | 28.9 119 | 3.74 20 | 10.1 104 | 53.7 128 | 2.52 96 | 15.3 117 | 26.5 121 | 2.16 1 |
Filter Flow [19] | 76.5 | 5.42 90 | 10.2 31 | 2.16 85 | 9.40 109 | 14.7 100 | 2.71 116 | 6.00 50 | 10.7 77 | 2.00 78 | 9.49 100 | 13.9 62 | 5.35 107 | 18.1 63 | 24.3 43 | 5.26 116 | 10.2 52 | 25.6 56 | 3.83 95 | 9.52 86 | 41.4 81 | 2.45 1 | 14.6 86 | 22.3 49 | 2.38 104 |
ROF-ND [107] | 77.1 | 5.74 113 | 10.4 41 | 2.00 2 | 8.04 73 | 14.1 81 | 2.16 61 | 6.06 89 | 10.7 77 | 1.73 1 | 10.6 113 | 19.9 124 | 5.26 92 | 18.1 63 | 24.8 77 | 5.20 61 | 11.7 119 | 28.6 116 | 3.74 20 | 11.1 120 | 41.0 76 | 2.52 96 | 15.3 117 | 25.3 117 | 2.16 1 |
Shiralkar [42] | 78.5 | 5.48 103 | 12.7 114 | 2.08 59 | 9.06 100 | 14.7 100 | 2.08 1 | 6.00 50 | 12.8 118 | 2.00 78 | 10.7 115 | 19.7 123 | 5.20 51 | 18.1 63 | 24.8 77 | 5.00 3 | 10.8 93 | 26.1 71 | 3.87 103 | 10.8 117 | 47.5 123 | 2.45 1 | 14.9 101 | 25.8 119 | 2.16 1 |
TriangleFlow [30] | 79.1 | 5.60 108 | 11.6 103 | 2.16 85 | 8.50 85 | 14.4 90 | 2.08 1 | 6.35 93 | 10.7 77 | 2.00 78 | 9.42 97 | 15.8 101 | 5.23 77 | 18.0 50 | 24.5 56 | 5.00 3 | 11.1 108 | 27.2 97 | 3.74 20 | 10.4 108 | 47.2 122 | 2.52 96 | 15.6 120 | 26.7 122 | 2.16 1 |
Correlation Flow [75] | 79.6 | 5.42 90 | 11.7 105 | 2.00 2 | 8.58 86 | 15.4 114 | 2.08 1 | 5.69 4 | 9.80 23 | 1.73 1 | 8.89 74 | 14.7 80 | 5.32 105 | 18.1 63 | 24.8 77 | 5.32 125 | 12.3 129 | 30.3 123 | 3.83 95 | 10.5 111 | 48.8 125 | 2.52 96 | 14.8 96 | 23.7 100 | 2.31 86 |
Rannacher [23] | 79.8 | 5.26 59 | 10.8 64 | 2.16 85 | 9.27 104 | 15.5 121 | 2.16 61 | 6.35 93 | 10.9 92 | 2.00 78 | 8.76 48 | 14.4 72 | 5.23 77 | 17.9 41 | 24.4 49 | 5.20 61 | 10.5 71 | 26.7 88 | 3.79 76 | 9.90 99 | 45.9 116 | 2.52 96 | 14.4 64 | 23.5 96 | 2.38 104 |
Horn & Schunck [3] | 82.2 | 5.48 103 | 10.4 41 | 2.16 85 | 10.5 123 | 15.4 114 | 2.52 109 | 6.68 110 | 12.0 110 | 2.00 78 | 11.5 121 | 17.6 114 | 5.23 77 | 17.9 41 | 24.0 26 | 5.20 61 | 9.93 30 | 24.1 20 | 3.79 76 | 11.1 120 | 42.9 98 | 2.52 96 | 14.5 75 | 22.2 42 | 2.38 104 |
IAOF2 [51] | 83.2 | 5.74 113 | 11.5 99 | 2.16 85 | 9.49 111 | 15.9 128 | 2.38 93 | 5.69 4 | 11.0 94 | 2.00 78 | 9.61 103 | 15.8 101 | 5.26 92 | 18.7 119 | 25.3 107 | 5.20 61 | 10.9 95 | 27.4 102 | 3.74 20 | 9.47 82 | 41.1 78 | 2.45 1 | 14.5 75 | 22.8 69 | 2.31 86 |
TI-DOFE [24] | 85.0 | 5.80 115 | 11.0 71 | 2.52 124 | 11.5 127 | 15.8 126 | 3.11 125 | 6.35 93 | 12.3 114 | 2.00 78 | 11.4 120 | 17.4 112 | 5.29 101 | 17.9 41 | 24.2 41 | 5.07 10 | 9.95 32 | 24.4 28 | 3.79 76 | 10.5 111 | 39.9 63 | 2.52 96 | 14.8 96 | 22.1 36 | 2.38 104 |
LocallyOriented [52] | 86.5 | 5.45 98 | 11.2 87 | 2.16 85 | 9.49 111 | 15.7 124 | 2.16 61 | 6.06 89 | 11.7 105 | 1.91 74 | 9.42 97 | 17.0 110 | 5.23 77 | 18.2 83 | 24.8 77 | 5.07 10 | 11.0 100 | 26.5 81 | 4.04 120 | 10.4 108 | 43.0 102 | 2.45 1 | 14.8 96 | 23.4 94 | 2.31 86 |
SegOF [10] | 87.0 | 5.10 29 | 11.4 94 | 2.16 85 | 8.29 78 | 13.9 77 | 2.38 93 | 7.00 118 | 12.1 113 | 2.00 78 | 9.81 105 | 21.0 125 | 5.20 51 | 18.2 83 | 25.1 99 | 5.20 61 | 10.9 95 | 26.1 71 | 3.79 76 | 10.4 108 | 48.4 124 | 2.58 118 | 14.7 91 | 25.1 116 | 2.16 1 |
SPSA-learn [13] | 87.6 | 5.29 66 | 10.4 41 | 2.16 85 | 9.04 99 | 14.1 81 | 2.45 104 | 6.68 110 | 11.7 105 | 2.00 78 | 10.3 111 | 15.8 101 | 5.10 22 | 18.4 103 | 25.3 107 | 5.20 61 | 10.5 71 | 26.8 91 | 3.74 20 | 12.3 128 | 58.4 130 | 2.71 130 | 17.6 128 | 35.0 130 | 2.16 1 |
2bit-BM-tele [98] | 89.8 | 5.35 73 | 10.1 25 | 2.16 85 | 8.91 96 | 15.4 114 | 2.45 104 | 6.00 50 | 10.0 28 | 2.00 78 | 9.04 84 | 14.3 68 | 5.60 119 | 18.3 93 | 24.9 84 | 5.35 128 | 11.7 119 | 31.3 126 | 4.24 128 | 12.0 127 | 58.7 131 | 2.83 131 | 13.9 13 | 21.7 22 | 2.45 129 |
StereoOF-V1MT [119] | 90.3 | 5.69 112 | 13.0 117 | 2.08 59 | 8.68 88 | 14.1 81 | 2.08 1 | 6.73 117 | 12.4 116 | 2.00 78 | 11.6 122 | 19.1 122 | 5.45 112 | 18.5 110 | 25.4 113 | 5.20 61 | 11.3 112 | 26.1 71 | 3.92 116 | 11.2 122 | 44.9 113 | 2.58 118 | 14.2 48 | 22.6 57 | 2.16 1 |
StereoFlow [44] | 90.6 | 8.68 131 | 20.4 131 | 2.45 122 | 10.3 122 | 16.1 129 | 2.71 116 | 6.00 50 | 10.7 77 | 1.73 1 | 8.81 60 | 13.7 51 | 5.16 43 | 22.6 129 | 31.6 129 | 5.26 116 | 14.3 131 | 35.7 131 | 3.79 76 | 9.13 58 | 38.8 47 | 2.45 1 | 15.6 120 | 25.3 117 | 2.31 86 |
ACK-Prior [27] | 91.5 | 5.35 73 | 11.7 105 | 2.00 2 | 7.39 47 | 12.9 49 | 2.08 1 | 6.68 110 | 10.8 90 | 2.00 78 | 9.54 102 | 15.7 100 | 5.32 105 | 18.7 119 | 25.5 118 | 5.29 123 | 11.9 125 | 29.5 120 | 3.87 103 | 10.1 104 | 41.7 85 | 2.52 96 | 16.1 123 | 24.8 114 | 2.38 104 |
UnFlow [129] | 92.2 | 5.97 117 | 15.5 123 | 2.16 85 | 9.13 102 | 14.1 81 | 2.38 93 | 6.68 110 | 13.0 120 | 2.00 78 | 9.35 94 | 17.1 111 | 5.23 77 | 18.6 115 | 25.8 124 | 5.20 61 | 11.5 115 | 29.5 120 | 3.74 20 | 9.66 93 | 37.4 16 | 2.45 1 | 16.9 127 | 28.1 126 | 2.38 104 |
Dynamic MRF [7] | 92.9 | 5.26 59 | 11.5 99 | 2.00 2 | 8.12 77 | 14.3 88 | 2.16 61 | 6.68 110 | 12.8 118 | 2.00 78 | 10.9 118 | 18.3 117 | 5.51 118 | 18.3 93 | 25.0 93 | 5.20 61 | 11.6 116 | 28.6 116 | 3.87 103 | 10.7 114 | 45.7 115 | 2.52 96 | 14.9 101 | 23.3 90 | 2.31 86 |
NL-TV-NCC [25] | 95.3 | 6.03 118 | 12.8 116 | 2.00 2 | 8.29 78 | 14.7 100 | 2.16 61 | 6.35 93 | 11.7 105 | 2.00 78 | 10.7 115 | 18.6 118 | 5.45 112 | 18.1 63 | 24.1 34 | 5.45 129 | 12.0 126 | 28.2 114 | 3.79 76 | 13.0 130 | 43.4 105 | 2.58 118 | 15.1 106 | 23.2 86 | 2.38 104 |
SILK [79] | 96.8 | 5.80 115 | 12.7 114 | 2.38 118 | 11.1 125 | 15.6 123 | 2.83 120 | 7.35 123 | 13.0 120 | 2.00 78 | 10.8 117 | 17.5 113 | 5.48 116 | 18.3 93 | 24.8 77 | 5.20 61 | 10.5 71 | 26.0 67 | 4.20 127 | 10.0 102 | 37.1 11 | 2.52 96 | 14.6 86 | 22.7 63 | 2.31 86 |
Learning Flow [11] | 98.2 | 5.57 107 | 11.1 81 | 2.16 85 | 9.27 104 | 15.1 108 | 2.16 61 | 7.00 118 | 13.3 122 | 2.00 78 | 10.2 108 | 15.2 89 | 5.45 112 | 18.5 110 | 25.1 99 | 5.32 125 | 10.7 88 | 26.2 76 | 3.87 103 | 10.6 113 | 40.8 74 | 2.52 96 | 15.1 106 | 23.3 90 | 2.38 104 |
FOLKI [16] | 105.4 | 6.14 120 | 12.4 112 | 3.11 128 | 11.5 127 | 15.5 121 | 3.32 128 | 7.00 118 | 14.7 126 | 2.38 124 | 13.5 127 | 18.2 115 | 6.27 129 | 18.6 115 | 25.0 93 | 5.23 106 | 10.3 59 | 25.1 43 | 4.04 120 | 11.0 119 | 38.3 34 | 2.58 118 | 14.7 91 | 22.4 53 | 2.38 104 |
Adaptive flow [45] | 105.6 | 6.24 121 | 11.3 92 | 2.71 126 | 11.2 126 | 15.7 124 | 3.42 129 | 6.35 93 | 10.9 92 | 2.00 78 | 10.2 108 | 14.7 80 | 5.72 122 | 18.7 119 | 25.4 113 | 5.23 106 | 11.7 119 | 30.8 125 | 3.87 103 | 9.42 78 | 38.8 47 | 2.58 118 | 14.9 101 | 24.3 110 | 2.38 104 |
GroupFlow [9] | 107.1 | 6.56 126 | 19.6 130 | 2.16 85 | 9.38 108 | 14.7 100 | 2.52 109 | 7.68 124 | 16.8 129 | 2.00 78 | 11.1 119 | 23.5 129 | 5.29 101 | 20.7 128 | 29.3 128 | 5.23 106 | 12.4 130 | 32.8 129 | 3.87 103 | 11.3 124 | 49.6 127 | 2.45 1 | 16.8 126 | 30.4 129 | 2.16 1 |
Heeger++ [104] | 110.0 | 7.16 129 | 18.5 128 | 2.16 85 | 9.75 113 | 13.8 74 | 2.45 104 | 9.35 128 | 16.1 128 | 2.38 124 | 13.0 124 | 18.9 120 | 5.74 123 | 19.8 127 | 27.4 127 | 5.23 106 | 12.2 127 | 26.0 67 | 3.92 116 | 13.5 131 | 46.5 117 | 2.52 96 | 16.1 123 | 27.4 123 | 2.16 1 |
SLK [47] | 113.2 | 6.03 118 | 13.6 119 | 2.45 122 | 10.1 118 | 13.8 74 | 2.89 122 | 7.68 124 | 12.4 116 | 2.38 124 | 13.8 129 | 21.0 125 | 5.77 125 | 19.1 126 | 26.4 126 | 5.20 61 | 11.2 109 | 26.2 76 | 3.87 103 | 11.8 125 | 46.9 119 | 2.58 118 | 15.2 115 | 26.1 120 | 2.38 104 |
FFV1MT [106] | 115.0 | 6.40 124 | 16.8 125 | 2.16 85 | 9.87 114 | 13.9 77 | 2.89 122 | 9.35 128 | 18.7 130 | 2.52 129 | 13.0 124 | 18.9 120 | 5.74 123 | 18.8 123 | 25.7 122 | 5.26 116 | 10.9 95 | 26.0 67 | 3.92 116 | 12.8 129 | 46.5 117 | 2.52 96 | 16.2 125 | 27.4 123 | 2.45 129 |
HCIC-L [99] | 116.5 | 7.62 130 | 17.7 127 | 3.16 129 | 9.98 116 | 14.8 106 | 3.16 127 | 7.14 122 | 14.0 124 | 2.00 78 | 12.4 123 | 21.5 128 | 5.35 107 | 18.9 125 | 25.5 118 | 5.26 116 | 11.8 122 | 31.9 128 | 3.87 103 | 9.47 82 | 43.2 104 | 2.58 118 | 18.7 130 | 30.1 128 | 2.38 104 |
PGAM+LK [55] | 116.7 | 6.56 126 | 16.0 124 | 2.71 126 | 10.0 117 | 14.7 100 | 3.00 124 | 7.75 127 | 15.7 127 | 2.38 124 | 13.7 128 | 21.1 127 | 6.27 129 | 18.8 123 | 25.8 124 | 5.26 116 | 11.6 116 | 27.2 97 | 4.08 124 | 10.7 114 | 40.3 68 | 2.58 118 | 15.1 106 | 24.4 111 | 2.38 104 |
Pyramid LK [2] | 118.3 | 6.24 121 | 13.7 120 | 3.16 129 | 12.7 130 | 15.8 126 | 3.79 130 | 11.8 130 | 12.3 114 | 3.00 130 | 25.5 131 | 41.4 130 | 7.14 131 | 22.9 130 | 33.6 130 | 5.20 61 | 10.7 88 | 25.4 52 | 3.92 116 | 11.2 122 | 49.2 126 | 2.65 127 | 19.6 131 | 37.8 131 | 2.38 104 |
Periodicity [78] | 129.4 | 6.81 128 | 17.5 126 | 3.27 131 | 15.3 131 | 16.9 130 | 4.24 131 | 13.7 131 | 22.7 131 | 4.36 131 | 18.0 130 | 41.4 130 | 6.16 128 | 23.9 131 | 34.4 131 | 5.60 131 | 12.2 127 | 34.5 130 | 4.51 130 | 11.8 125 | 55.6 129 | 2.65 127 | 17.9 129 | 29.7 127 | 2.71 131 |
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. |