Optical flow evaluation results |
Statistics:
Average
SD
R0.5
R1.0
R2.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
R0.5 endpoint error |
avg. |
Army (Hidden texture) GT im0 im1 |
Mequon (Hidden texture) GT im0 im1 |
Schefflera (Hidden texture) GT im0 im1 |
Wooden (Hidden texture) GT im0 im1 |
Grove (Synthetic) GT im0 im1 |
Urban (Synthetic) GT im0 im1 |
Yosemite (Synthetic) GT im0 im1 |
Teddy (Stereo) GT im0 im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
OFLAF [77] | 10.8 | 1.67 4 | 9.54 5 | 0.81 11 | 4.12 7 | 23.1 5 | 2.26 15 | 3.43 1 | 11.8 1 | 1.47 7 | 2.31 8 | 15.3 5 | 0.67 8 | 18.1 2 | 27.2 3 | 8.68 5 | 12.6 35 | 27.0 11 | 6.93 29 | 0.78 18 | 1.08 29 | 3.37 24 | 11.6 8 | 25.9 3 | 16.2 15 |
MDP-Flow2 [68] | 12.5 | 1.76 8 | 9.93 9 | 0.86 13 | 3.26 2 | 20.6 2 | 1.44 3 | 4.04 3 | 13.6 3 | 1.26 5 | 3.09 26 | 21.8 30 | 0.88 19 | 22.4 15 | 32.2 12 | 14.3 14 | 9.15 12 | 23.6 3 | 5.83 10 | 2.18 40 | 0.32 17 | 4.78 37 | 10.8 5 | 26.3 4 | 15.0 9 |
NNF-Local [87] | 13.1 | 1.75 7 | 9.66 6 | 0.87 14 | 4.56 14 | 27.6 16 | 2.46 19 | 4.52 4 | 15.6 7 | 2.18 16 | 2.57 15 | 18.4 15 | 0.86 16 | 18.8 5 | 29.2 5 | 8.22 3 | 9.37 15 | 24.2 6 | 5.22 7 | 0.95 20 | 2.02 62 | 1.90 13 | 10.6 4 | 31.8 24 | 8.21 2 |
NN-field [71] | 15.4 | 2.01 19 | 11.0 20 | 1.10 27 | 5.74 26 | 30.7 31 | 3.21 27 | 4.57 5 | 15.7 8 | 2.22 18 | 1.81 2 | 15.7 7 | 0.54 5 | 19.0 6 | 29.4 6 | 8.42 4 | 10.5 21 | 20.3 1 | 3.83 1 | 1.43 26 | 2.03 63 | 3.72 25 | 10.1 2 | 31.1 19 | 6.81 1 |
PMMST [114] | 17.3 | 1.43 2 | 8.08 2 | 0.38 1 | 6.05 32 | 28.6 20 | 4.40 40 | 6.13 17 | 19.1 16 | 4.02 39 | 2.21 5 | 11.7 1 | 1.09 27 | 21.2 9 | 30.5 9 | 13.2 11 | 9.59 17 | 23.8 4 | 5.71 9 | 2.28 43 | 1.95 57 | 4.36 31 | 11.8 9 | 29.1 8 | 13.1 6 |
WLIF-Flow [93] | 20.9 | 1.80 10 | 9.97 10 | 0.94 16 | 6.24 35 | 28.7 22 | 4.52 42 | 5.74 12 | 18.5 11 | 3.13 25 | 3.03 25 | 19.9 22 | 1.01 24 | 21.9 10 | 32.0 11 | 14.1 12 | 12.4 32 | 27.2 12 | 6.44 13 | 3.40 64 | 0.07 7 | 8.69 62 | 11.4 7 | 26.8 5 | 15.7 12 |
ComponentFusion [96] | 21.1 | 1.73 6 | 9.92 8 | 0.77 8 | 3.75 5 | 22.3 4 | 2.27 16 | 5.02 9 | 17.1 10 | 2.21 17 | 2.87 19 | 19.3 20 | 0.93 20 | 24.1 19 | 35.1 22 | 18.6 34 | 12.4 32 | 39.0 71 | 8.29 55 | 2.41 44 | 0.13 15 | 4.73 36 | 11.9 11 | 30.0 15 | 15.5 11 |
Correlation Flow [75] | 22.0 | 1.96 17 | 10.9 18 | 0.66 5 | 4.21 9 | 25.5 12 | 1.35 2 | 6.69 29 | 20.7 24 | 0.94 2 | 1.68 1 | 13.3 2 | 0.48 4 | 25.4 27 | 36.9 29 | 16.3 24 | 13.5 52 | 32.5 35 | 7.88 49 | 2.82 53 | 1.63 44 | 10.8 70 | 11.3 6 | 29.7 11 | 9.89 4 |
NNF-EAC [103] | 23.5 | 1.95 16 | 10.5 15 | 1.10 27 | 4.29 11 | 25.1 10 | 2.20 12 | 5.06 10 | 16.6 9 | 1.81 11 | 3.94 52 | 23.4 39 | 1.63 52 | 22.5 16 | 32.5 15 | 14.7 16 | 11.3 25 | 25.8 8 | 6.81 23 | 2.71 50 | 2.13 65 | 4.63 35 | 12.4 14 | 30.2 17 | 16.5 16 |
Layers++ [37] | 24.5 | 1.85 13 | 10.1 11 | 1.03 23 | 6.26 36 | 27.9 19 | 4.58 44 | 4.88 8 | 15.2 5 | 3.65 33 | 2.26 7 | 14.4 3 | 0.68 9 | 17.8 1 | 25.4 1 | 12.2 8 | 13.3 46 | 28.3 16 | 6.81 23 | 4.53 73 | 2.71 82 | 7.34 53 | 13.2 22 | 29.7 11 | 19.2 40 |
LME [70] | 24.5 | 1.89 15 | 10.6 16 | 0.75 6 | 3.53 3 | 21.3 3 | 1.83 8 | 7.04 40 | 18.6 14 | 8.24 71 | 3.10 28 | 23.0 37 | 0.86 16 | 24.8 25 | 35.5 24 | 17.9 31 | 10.1 19 | 30.1 26 | 6.46 14 | 2.67 49 | 1.51 41 | 5.54 41 | 12.8 16 | 30.9 18 | 17.7 27 |
RNLOD-Flow [121] | 26.6 | 1.68 5 | 9.49 4 | 0.75 6 | 5.76 27 | 30.6 30 | 3.18 25 | 6.58 26 | 21.1 28 | 2.92 22 | 2.61 16 | 17.5 12 | 0.74 11 | 22.0 11 | 32.8 16 | 14.9 19 | 11.5 27 | 28.0 15 | 7.37 37 | 5.53 87 | 4.17 95 | 15.2 93 | 11.8 9 | 27.7 7 | 15.1 10 |
nLayers [57] | 26.8 | 1.40 1 | 7.64 1 | 0.64 3 | 8.47 67 | 30.5 29 | 7.07 79 | 6.80 35 | 20.0 20 | 5.79 63 | 2.13 4 | 14.7 4 | 0.78 14 | 18.3 3 | 26.0 2 | 12.2 8 | 12.9 41 | 25.6 7 | 6.84 25 | 1.93 36 | 2.24 69 | 3.35 23 | 14.5 34 | 32.0 27 | 20.9 49 |
HAST [109] | 28.1 | 1.57 3 | 8.65 3 | 0.60 2 | 5.82 30 | 24.9 9 | 3.84 32 | 3.85 2 | 12.5 2 | 0.41 1 | 2.82 18 | 18.8 17 | 0.58 6 | 18.7 4 | 27.9 4 | 8.00 1 | 15.9 87 | 32.6 36 | 9.69 78 | 9.89 112 | 4.87 104 | 36.9 119 | 8.55 1 | 22.0 1 | 9.33 3 |
FC-2Layers-FF [74] | 28.8 | 1.81 11 | 9.71 7 | 1.07 26 | 6.99 44 | 33.9 45 | 4.71 45 | 4.71 6 | 15.0 4 | 3.63 32 | 2.67 17 | 18.3 14 | 0.87 18 | 20.6 8 | 29.7 7 | 14.5 15 | 13.3 46 | 28.4 17 | 7.26 34 | 5.67 91 | 1.82 52 | 14.9 89 | 12.9 19 | 29.4 9 | 18.4 34 |
SVFilterOh [111] | 29.7 | 2.18 29 | 11.4 24 | 0.78 9 | 5.94 31 | 29.2 24 | 3.13 23 | 4.85 7 | 15.2 5 | 2.01 13 | 2.35 9 | 17.4 10 | 0.63 7 | 20.4 7 | 30.1 8 | 8.12 2 | 14.7 79 | 29.5 22 | 8.51 62 | 10.3 113 | 3.98 93 | 31.3 111 | 12.0 12 | 26.9 6 | 13.4 7 |
TC/T-Flow [76] | 29.8 | 2.19 31 | 11.8 31 | 1.21 36 | 5.00 17 | 29.4 25 | 1.89 9 | 5.57 11 | 18.5 11 | 1.28 6 | 3.63 41 | 23.7 42 | 1.24 34 | 24.1 19 | 35.4 23 | 15.2 21 | 7.02 2 | 25.8 8 | 5.43 8 | 3.79 68 | 2.13 65 | 19.3 102 | 14.6 37 | 36.2 40 | 17.9 29 |
AGIF+OF [85] | 30.5 | 1.99 18 | 10.9 18 | 1.16 32 | 8.96 72 | 37.8 65 | 6.95 74 | 6.31 20 | 20.4 21 | 3.86 37 | 2.89 20 | 19.1 18 | 0.93 20 | 22.1 12 | 32.4 13 | 14.8 17 | 12.9 41 | 28.6 19 | 6.79 22 | 3.48 67 | 0.08 13 | 8.67 61 | 12.8 16 | 29.9 14 | 17.5 23 |
TC-Flow [46] | 30.8 | 2.04 20 | 11.0 20 | 0.94 16 | 3.69 4 | 23.4 6 | 1.68 5 | 5.96 16 | 19.9 19 | 1.06 3 | 3.73 44 | 23.6 41 | 1.24 34 | 25.7 31 | 38.0 34 | 14.8 17 | 8.99 11 | 34.6 45 | 5.03 6 | 2.82 53 | 2.47 75 | 15.9 97 | 16.0 44 | 38.1 46 | 22.0 53 |
HBM-GC [105] | 31.5 | 2.10 24 | 10.8 17 | 0.94 16 | 7.69 57 | 31.9 38 | 6.10 66 | 6.21 19 | 18.5 11 | 3.82 35 | 2.22 6 | 15.5 6 | 0.78 14 | 22.1 12 | 31.8 10 | 14.2 13 | 13.3 46 | 24.1 5 | 7.49 41 | 8.91 109 | 1.87 53 | 21.4 106 | 12.7 15 | 31.1 19 | 16.7 19 |
ALD-Flow [66] | 33.1 | 2.22 33 | 11.8 31 | 1.02 22 | 4.33 12 | 24.7 7 | 2.04 11 | 6.35 22 | 20.9 25 | 1.56 8 | 3.67 42 | 24.0 46 | 1.10 28 | 25.8 32 | 37.5 33 | 15.8 23 | 8.24 5 | 32.7 38 | 4.68 3 | 3.06 58 | 2.62 81 | 16.6 99 | 15.6 43 | 39.3 48 | 19.8 44 |
ProbFlowFields [128] | 35.2 | 3.29 69 | 17.1 72 | 1.88 83 | 6.54 38 | 29.8 26 | 5.50 56 | 7.69 47 | 23.8 45 | 6.90 66 | 3.09 26 | 17.1 9 | 1.28 36 | 27.8 39 | 39.5 40 | 19.2 40 | 6.56 1 | 27.2 12 | 5.00 5 | 0.09 3 | 0.03 3 | 0.86 7 | 17.1 51 | 39.4 49 | 17.5 23 |
IROF++ [58] | 35.5 | 2.18 29 | 11.5 27 | 1.33 43 | 7.91 58 | 36.5 60 | 5.96 63 | 6.71 31 | 21.7 34 | 4.85 56 | 3.62 40 | 22.8 33 | 1.63 52 | 24.2 22 | 34.9 21 | 17.1 28 | 13.3 46 | 33.4 41 | 7.82 47 | 0.55 15 | 1.09 30 | 1.01 9 | 12.8 16 | 32.9 31 | 16.7 19 |
FESL [72] | 36.2 | 1.86 14 | 10.2 12 | 0.99 19 | 10.4 88 | 39.3 76 | 7.94 87 | 6.79 34 | 21.2 30 | 4.35 46 | 2.39 10 | 16.2 8 | 0.76 13 | 24.2 22 | 34.7 19 | 19.2 40 | 12.6 35 | 27.7 14 | 7.10 33 | 3.35 62 | 2.20 68 | 8.03 57 | 14.5 34 | 31.2 21 | 17.6 26 |
FMOF [94] | 36.5 | 2.09 22 | 11.2 23 | 1.44 56 | 9.20 74 | 37.9 66 | 6.96 75 | 6.14 18 | 19.5 17 | 3.82 35 | 2.52 13 | 17.4 10 | 0.73 10 | 24.1 19 | 34.8 20 | 17.7 30 | 13.5 52 | 28.4 17 | 6.99 30 | 4.64 76 | 1.63 44 | 14.5 85 | 14.5 34 | 32.7 29 | 17.2 22 |
Classic+CPF [83] | 37.1 | 2.16 27 | 11.6 28 | 1.42 54 | 8.04 60 | 36.6 61 | 5.76 60 | 6.70 30 | 21.8 36 | 3.86 37 | 3.02 24 | 21.2 28 | 1.14 30 | 23.6 18 | 34.2 18 | 17.0 27 | 13.4 51 | 29.1 20 | 7.03 32 | 4.58 75 | 1.50 40 | 13.6 82 | 12.9 19 | 29.7 11 | 17.5 23 |
MLDP_OF [89] | 37.4 | 2.46 45 | 13.6 48 | 1.14 31 | 4.43 13 | 27.8 18 | 1.99 10 | 6.80 35 | 21.7 34 | 1.89 12 | 2.52 13 | 19.6 21 | 0.75 12 | 28.2 40 | 40.4 43 | 19.2 40 | 11.8 29 | 29.6 23 | 9.40 74 | 8.30 107 | 2.15 67 | 31.7 113 | 13.3 23 | 33.4 34 | 15.9 13 |
PH-Flow [101] | 38.0 | 2.30 38 | 12.2 35 | 1.45 58 | 7.61 55 | 35.2 50 | 5.81 61 | 5.92 15 | 19.0 15 | 4.67 54 | 3.52 36 | 22.1 31 | 1.49 46 | 23.4 17 | 33.9 17 | 16.3 24 | 12.4 32 | 29.4 21 | 6.87 26 | 4.88 80 | 2.25 71 | 14.0 83 | 12.2 13 | 30.1 16 | 16.6 17 |
Efficient-NL [60] | 39.3 | 2.41 43 | 11.8 31 | 1.55 69 | 8.28 63 | 35.4 53 | 5.90 62 | 6.72 32 | 20.9 25 | 3.78 34 | 2.95 23 | 19.1 18 | 1.20 32 | 22.1 12 | 32.4 13 | 15.3 22 | 14.6 77 | 31.0 30 | 8.05 53 | 3.32 60 | 2.40 74 | 7.02 49 | 13.6 27 | 29.6 10 | 18.2 31 |
PMF [73] | 39.7 | 2.30 38 | 12.8 41 | 1.01 20 | 5.64 25 | 31.4 35 | 2.51 20 | 6.83 37 | 22.5 41 | 1.72 10 | 3.26 29 | 21.1 26 | 0.94 22 | 24.3 24 | 36.7 28 | 9.56 6 | 14.4 73 | 40.0 77 | 8.40 59 | 7.45 104 | 8.62 121 | 24.8 107 | 10.4 3 | 25.6 2 | 12.7 5 |
Aniso-Texture [82] | 40.2 | 1.84 12 | 10.4 14 | 0.81 11 | 4.68 15 | 24.7 7 | 3.74 30 | 8.07 51 | 23.8 45 | 3.23 28 | 2.10 3 | 18.4 15 | 0.46 2 | 29.0 51 | 41.0 48 | 22.9 55 | 12.7 37 | 32.7 38 | 8.37 58 | 6.63 99 | 5.87 112 | 14.8 88 | 16.4 45 | 35.2 38 | 24.2 63 |
OAR-Flow [125] | 40.4 | 2.96 63 | 15.1 63 | 1.58 71 | 6.72 41 | 31.3 34 | 4.10 37 | 9.12 59 | 27.1 56 | 4.72 55 | 3.73 44 | 23.9 44 | 1.17 31 | 28.3 42 | 40.8 45 | 17.6 29 | 8.30 6 | 33.5 43 | 4.69 4 | 0.25 7 | 0.17 16 | 2.56 18 | 17.5 55 | 40.5 51 | 22.6 56 |
Sparse-NonSparse [56] | 41.4 | 2.11 25 | 11.7 29 | 1.39 49 | 7.47 54 | 35.1 49 | 5.75 59 | 6.48 24 | 21.2 30 | 4.34 44 | 3.52 36 | 22.9 34 | 1.38 41 | 26.1 35 | 37.3 32 | 19.6 47 | 13.5 52 | 31.2 32 | 7.42 38 | 5.02 84 | 1.18 34 | 13.5 81 | 13.5 25 | 31.7 22 | 18.8 38 |
Ramp [62] | 42.2 | 2.21 32 | 12.1 34 | 1.45 58 | 7.45 53 | 35.5 55 | 5.63 58 | 6.33 21 | 20.6 23 | 4.23 41 | 3.43 33 | 22.5 32 | 1.38 41 | 25.8 32 | 37.0 30 | 19.3 44 | 13.5 52 | 30.3 27 | 7.45 39 | 4.89 81 | 1.97 59 | 15.1 92 | 13.1 21 | 31.9 25 | 18.0 30 |
NL-TV-NCC [25] | 42.4 | 2.25 35 | 11.7 29 | 0.78 9 | 6.94 43 | 35.5 55 | 2.54 21 | 6.48 24 | 21.1 28 | 1.08 4 | 2.48 12 | 21.5 29 | 0.46 2 | 31.5 64 | 46.7 81 | 16.7 26 | 17.3 91 | 41.0 86 | 10.2 81 | 4.41 72 | 0.10 14 | 10.1 67 | 18.4 56 | 43.2 57 | 18.2 31 |
LSM [39] | 42.6 | 2.24 34 | 12.4 37 | 1.39 49 | 7.37 51 | 35.4 53 | 5.47 55 | 6.61 27 | 21.6 33 | 4.24 42 | 3.46 35 | 23.8 43 | 1.30 38 | 25.8 32 | 37.0 30 | 19.3 44 | 13.7 58 | 32.1 34 | 7.36 36 | 5.34 86 | 1.11 32 | 14.5 85 | 13.7 30 | 32.3 28 | 18.2 31 |
OFH [38] | 42.7 | 2.82 58 | 13.9 51 | 2.01 84 | 4.91 16 | 28.6 20 | 2.33 17 | 8.97 58 | 28.0 61 | 2.88 21 | 4.00 55 | 27.0 56 | 1.43 44 | 31.0 61 | 44.5 68 | 22.7 53 | 10.5 21 | 41.8 88 | 6.88 27 | 0.03 1 | 0.02 1 | 0.27 3 | 17.1 51 | 46.4 70 | 19.2 40 |
Sparse Occlusion [54] | 43.4 | 2.14 26 | 11.4 24 | 1.03 23 | 7.32 49 | 31.0 32 | 6.11 67 | 7.29 44 | 22.9 43 | 2.48 20 | 3.29 30 | 22.9 34 | 1.03 25 | 26.9 37 | 39.4 38 | 14.9 19 | 13.0 43 | 33.3 40 | 7.63 44 | 7.80 105 | 8.76 124 | 12.2 77 | 14.8 39 | 34.8 37 | 16.9 21 |
Classic+NL [31] | 43.5 | 2.08 21 | 11.4 24 | 1.35 45 | 7.33 50 | 35.9 58 | 5.30 52 | 6.47 23 | 21.0 27 | 4.53 51 | 3.59 38 | 22.9 34 | 1.49 46 | 25.4 27 | 36.3 26 | 19.4 46 | 13.8 61 | 31.1 31 | 7.57 42 | 5.78 93 | 2.32 73 | 15.0 90 | 13.5 25 | 31.9 25 | 18.7 37 |
IROF-TV [53] | 45.9 | 2.51 48 | 13.5 46 | 1.41 52 | 8.08 61 | 38.7 73 | 6.19 69 | 6.97 39 | 22.3 38 | 4.43 48 | 4.23 58 | 28.8 64 | 1.72 57 | 28.3 42 | 39.9 41 | 22.6 52 | 13.8 61 | 40.0 77 | 8.01 51 | 0.23 6 | 0.39 21 | 0.67 5 | 13.7 30 | 33.6 35 | 17.8 28 |
RFlow [90] | 46.2 | 2.42 44 | 13.5 46 | 1.16 32 | 3.98 6 | 25.2 11 | 1.81 7 | 8.89 57 | 27.5 58 | 3.13 25 | 3.45 34 | 26.8 54 | 1.60 50 | 30.5 59 | 43.6 59 | 24.5 63 | 14.2 68 | 38.1 65 | 7.94 50 | 3.36 63 | 1.65 47 | 8.47 60 | 16.9 50 | 42.3 53 | 20.5 48 |
TV-L1-MCT [64] | 46.4 | 2.09 22 | 11.1 22 | 1.39 49 | 9.67 77 | 39.0 75 | 7.35 80 | 7.11 42 | 22.3 38 | 4.27 43 | 2.94 22 | 20.7 25 | 1.13 29 | 28.4 44 | 39.4 38 | 25.8 70 | 16.0 89 | 35.0 48 | 9.27 71 | 1.27 24 | 0.57 23 | 7.24 51 | 14.8 39 | 33.2 33 | 23.3 60 |
COFM [59] | 47.0 | 2.51 48 | 13.9 51 | 1.42 54 | 5.54 21 | 28.9 23 | 3.40 28 | 7.79 49 | 23.6 44 | 4.53 51 | 2.90 21 | 18.2 13 | 0.95 23 | 29.1 52 | 40.8 45 | 25.4 67 | 15.5 85 | 30.7 29 | 9.39 73 | 4.69 77 | 1.23 35 | 15.4 96 | 16.8 49 | 37.1 41 | 21.8 52 |
S2D-Matching [84] | 47.1 | 2.39 41 | 13.0 42 | 1.52 66 | 7.22 47 | 35.6 57 | 5.13 50 | 7.63 46 | 24.4 48 | 4.38 47 | 3.30 31 | 20.5 24 | 1.35 40 | 25.3 26 | 36.0 25 | 19.2 40 | 14.1 65 | 31.5 33 | 7.77 46 | 6.21 96 | 2.24 69 | 16.9 100 | 13.6 27 | 31.7 22 | 19.3 42 |
Occlusion-TV-L1 [63] | 48.9 | 2.47 46 | 13.1 43 | 1.12 29 | 6.32 37 | 32.2 40 | 4.45 41 | 9.86 64 | 28.3 62 | 4.44 49 | 3.86 50 | 26.7 53 | 1.43 44 | 31.9 70 | 44.3 65 | 27.1 76 | 11.3 25 | 35.3 52 | 10.4 83 | 0.47 13 | 1.16 33 | 0.67 5 | 19.8 64 | 46.6 72 | 22.9 58 |
Complementary OF [21] | 49.0 | 2.69 55 | 15.0 61 | 1.33 43 | 4.19 8 | 26.9 14 | 1.70 6 | 7.15 43 | 24.4 48 | 3.09 24 | 3.86 50 | 26.1 50 | 1.41 43 | 33.2 76 | 44.6 70 | 29.7 87 | 13.3 46 | 40.7 85 | 7.00 31 | 0.74 17 | 0.03 3 | 7.12 50 | 23.9 85 | 53.1 91 | 33.9 91 |
ACK-Prior [27] | 49.1 | 2.16 27 | 12.4 37 | 0.64 3 | 4.26 10 | 25.9 13 | 1.33 1 | 5.91 14 | 20.4 21 | 1.67 9 | 2.39 10 | 20.4 23 | 0.33 1 | 30.0 56 | 41.1 49 | 24.4 62 | 19.2 102 | 40.3 82 | 12.2 94 | 14.4 122 | 6.30 115 | 40.9 122 | 21.0 69 | 43.6 59 | 27.5 77 |
CostFilter [40] | 49.2 | 2.65 52 | 14.9 59 | 1.01 20 | 5.51 20 | 31.6 36 | 2.23 14 | 7.39 45 | 24.1 47 | 3.06 23 | 3.82 48 | 26.1 50 | 1.08 26 | 25.4 27 | 38.9 37 | 10.2 7 | 15.1 82 | 42.7 91 | 8.52 63 | 8.99 110 | 10.3 126 | 29.5 110 | 14.4 33 | 37.2 42 | 16.1 14 |
MDP-Flow [26] | 49.4 | 2.33 40 | 13.4 45 | 1.20 34 | 5.61 24 | 26.9 14 | 4.88 47 | 6.76 33 | 22.6 42 | 5.72 62 | 4.13 56 | 29.5 69 | 1.92 61 | 28.7 47 | 40.8 45 | 23.2 58 | 12.8 39 | 36.7 57 | 8.04 52 | 2.54 46 | 2.96 84 | 4.43 33 | 19.4 63 | 44.6 63 | 26.0 72 |
2DHMM-SAS [92] | 51.1 | 2.28 37 | 12.3 36 | 1.46 60 | 8.45 66 | 38.1 68 | 6.02 65 | 8.34 53 | 24.4 48 | 5.21 58 | 3.73 44 | 23.4 39 | 1.62 51 | 25.5 30 | 36.6 27 | 18.8 35 | 14.5 74 | 33.4 41 | 8.46 61 | 5.07 85 | 2.05 64 | 15.3 94 | 13.3 23 | 32.9 31 | 18.5 36 |
SimpleFlow [49] | 51.6 | 2.39 41 | 12.6 40 | 1.60 73 | 9.03 73 | 38.3 69 | 7.38 81 | 8.52 55 | 25.7 52 | 5.41 59 | 4.36 63 | 25.5 49 | 2.48 70 | 26.8 36 | 38.0 34 | 21.6 49 | 14.0 64 | 29.7 24 | 7.65 45 | 2.77 52 | 1.97 59 | 6.48 46 | 14.3 32 | 32.8 30 | 19.7 43 |
Steered-L1 [118] | 52.7 | 1.78 9 | 10.2 12 | 0.92 15 | 2.76 1 | 19.0 1 | 1.44 3 | 5.78 13 | 19.7 18 | 2.10 14 | 3.99 54 | 27.5 59 | 1.53 49 | 31.3 63 | 43.3 57 | 27.6 78 | 14.6 77 | 39.2 73 | 9.88 79 | 14.6 123 | 5.70 110 | 47.1 123 | 22.4 76 | 48.1 76 | 29.3 82 |
AggregFlow [97] | 54.1 | 3.49 77 | 17.6 76 | 1.74 75 | 10.4 88 | 42.0 87 | 6.99 76 | 11.4 74 | 30.6 67 | 9.73 80 | 3.75 47 | 21.1 26 | 1.52 48 | 28.9 50 | 41.8 53 | 18.2 32 | 7.46 3 | 22.8 2 | 4.30 2 | 1.95 37 | 2.54 77 | 4.24 29 | 20.5 66 | 42.7 56 | 25.8 70 |
TF+OM [100] | 54.5 | 2.89 62 | 14.7 57 | 1.35 45 | 5.44 19 | 27.6 16 | 3.94 33 | 10.2 65 | 26.3 53 | 12.8 90 | 3.61 39 | 24.6 48 | 1.28 36 | 29.8 55 | 40.5 44 | 25.7 68 | 12.7 37 | 34.9 47 | 6.11 11 | 5.62 90 | 4.89 105 | 14.0 83 | 21.5 71 | 46.5 71 | 23.8 62 |
EPPM w/o HM [88] | 56.5 | 3.53 79 | 16.6 68 | 1.44 56 | 5.80 28 | 35.3 52 | 2.22 13 | 8.01 50 | 26.3 53 | 2.45 19 | 4.38 64 | 28.0 60 | 1.77 59 | 27.0 38 | 40.0 42 | 13.0 10 | 18.6 97 | 44.4 100 | 10.8 86 | 10.5 115 | 2.30 72 | 37.7 120 | 13.6 27 | 35.6 39 | 13.9 8 |
DeepFlow2 [108] | 56.9 | 3.18 67 | 16.9 71 | 1.48 62 | 6.68 40 | 33.7 44 | 4.15 38 | 10.7 69 | 31.1 68 | 7.69 69 | 5.96 82 | 31.1 77 | 3.33 81 | 28.5 45 | 41.3 50 | 19.1 37 | 9.45 16 | 34.7 46 | 6.60 17 | 1.60 29 | 1.66 49 | 10.4 68 | 23.5 80 | 47.9 75 | 30.2 85 |
CombBMOF [113] | 57.2 | 2.67 53 | 14.4 54 | 1.05 25 | 7.17 45 | 33.9 45 | 4.00 34 | 6.89 38 | 21.4 32 | 4.18 40 | 5.20 75 | 28.8 64 | 3.04 79 | 28.2 40 | 41.7 52 | 18.5 33 | 21.8 106 | 39.5 74 | 20.1 110 | 4.02 69 | 4.61 102 | 6.08 43 | 17.1 51 | 37.5 43 | 24.5 66 |
Adaptive [20] | 57.4 | 2.49 47 | 13.2 44 | 1.13 30 | 7.17 45 | 34.5 48 | 4.97 48 | 10.2 65 | 28.7 64 | 4.34 44 | 4.31 62 | 28.2 61 | 1.66 54 | 34.5 83 | 48.1 87 | 28.2 80 | 14.3 71 | 36.1 54 | 8.24 54 | 4.04 70 | 4.49 101 | 7.32 52 | 14.7 38 | 34.7 36 | 18.9 39 |
ComplOF-FED-GPU [35] | 59.9 | 2.87 61 | 15.6 65 | 1.35 45 | 6.14 33 | 33.6 43 | 3.15 24 | 8.26 52 | 27.4 57 | 3.30 29 | 4.29 59 | 28.2 61 | 1.71 56 | 33.1 75 | 47.9 86 | 24.1 61 | 14.7 79 | 45.7 103 | 9.19 69 | 3.33 61 | 1.48 39 | 15.0 90 | 18.8 59 | 48.4 78 | 22.0 53 |
TCOF [69] | 60.4 | 3.05 65 | 15.4 64 | 1.75 76 | 8.12 62 | 38.6 71 | 5.20 51 | 13.8 86 | 34.5 81 | 13.2 92 | 8.75 98 | 29.0 66 | 8.90 103 | 33.8 79 | 47.3 83 | 23.1 57 | 9.33 14 | 25.9 10 | 6.64 19 | 2.59 47 | 1.95 57 | 6.38 45 | 15.3 42 | 39.1 47 | 18.4 34 |
ROF-ND [107] | 61.3 | 3.29 69 | 14.7 57 | 1.29 40 | 7.42 52 | 31.8 37 | 2.42 18 | 7.10 41 | 22.1 37 | 2.13 15 | 3.68 43 | 23.2 38 | 2.87 77 | 31.1 62 | 43.7 60 | 23.6 60 | 19.3 104 | 38.5 67 | 10.7 85 | 8.90 108 | 2.99 85 | 24.8 107 | 21.9 73 | 48.6 79 | 22.7 57 |
BriefMatch [124] | 61.4 | 2.27 36 | 12.5 39 | 1.23 38 | 6.23 34 | 32.1 39 | 3.54 29 | 6.68 28 | 22.3 38 | 3.16 27 | 3.32 32 | 23.9 44 | 1.23 33 | 30.8 60 | 43.3 57 | 26.8 73 | 23.9 109 | 43.6 95 | 21.0 112 | 11.0 118 | 4.44 100 | 33.1 116 | 21.5 71 | 44.8 64 | 29.2 81 |
DeepFlow [86] | 62.0 | 3.36 72 | 17.3 73 | 1.54 68 | 7.91 58 | 35.2 50 | 5.35 53 | 12.1 78 | 33.0 76 | 10.5 86 | 6.24 84 | 32.1 79 | 3.55 83 | 28.8 48 | 42.3 54 | 18.8 35 | 9.77 18 | 37.4 61 | 6.90 28 | 1.30 25 | 0.37 18 | 9.70 66 | 27.4 95 | 52.7 87 | 35.8 93 |
Classic++ [32] | 62.0 | 2.59 51 | 13.9 51 | 1.51 65 | 6.79 42 | 32.3 41 | 5.37 54 | 9.15 60 | 27.8 60 | 5.54 60 | 4.29 59 | 29.0 66 | 1.77 59 | 30.2 58 | 43.9 61 | 22.8 54 | 14.8 81 | 40.0 77 | 8.36 57 | 6.82 100 | 4.17 95 | 16.5 98 | 16.5 46 | 39.5 50 | 19.8 44 |
TV-L1-improved [17] | 63.1 | 2.56 50 | 13.6 48 | 1.20 34 | 5.80 28 | 30.0 28 | 4.04 35 | 9.84 63 | 28.4 63 | 4.60 53 | 4.16 57 | 27.0 56 | 1.66 54 | 31.5 64 | 45.4 75 | 23.0 56 | 17.5 92 | 45.5 102 | 13.7 99 | 7.01 102 | 4.32 99 | 20.5 104 | 17.1 51 | 42.5 55 | 20.4 47 |
Bartels [41] | 64.3 | 3.26 68 | 16.7 70 | 1.37 48 | 5.33 18 | 29.8 26 | 3.18 25 | 8.40 54 | 26.9 55 | 4.45 50 | 4.40 65 | 26.9 55 | 2.16 63 | 32.7 72 | 45.4 75 | 28.4 83 | 14.3 71 | 38.1 65 | 12.9 95 | 8.20 106 | 3.82 91 | 31.3 111 | 18.4 56 | 43.7 61 | 23.3 60 |
S2F-IF [123] | 64.8 | 4.50 93 | 23.8 98 | 2.14 90 | 8.86 69 | 42.8 91 | 6.52 70 | 11.0 70 | 34.0 80 | 9.17 75 | 4.86 68 | 29.2 68 | 2.39 68 | 35.6 89 | 51.0 100 | 26.9 74 | 8.49 8 | 36.6 56 | 6.30 12 | 0.60 16 | 0.03 3 | 2.49 17 | 23.6 81 | 52.7 87 | 25.9 71 |
SIOF [67] | 65.4 | 2.67 53 | 13.6 48 | 1.23 38 | 7.65 56 | 37.9 66 | 4.78 46 | 14.2 89 | 32.9 75 | 15.4 94 | 6.36 85 | 34.7 85 | 3.84 85 | 34.0 80 | 45.8 78 | 33.2 91 | 13.5 52 | 35.7 53 | 10.5 84 | 1.99 38 | 0.99 27 | 4.21 28 | 20.5 66 | 45.6 66 | 30.7 87 |
F-TV-L1 [15] | 66.5 | 3.34 71 | 17.3 73 | 1.80 80 | 9.99 85 | 38.6 71 | 7.03 77 | 13.2 84 | 32.6 74 | 7.82 70 | 5.85 81 | 32.9 80 | 2.91 78 | 31.5 64 | 45.0 72 | 25.2 65 | 15.1 82 | 38.7 68 | 8.99 67 | 2.19 41 | 3.29 88 | 3.03 21 | 15.1 41 | 38.0 45 | 16.6 17 |
CRTflow [80] | 67.0 | 3.53 79 | 18.6 80 | 1.79 78 | 6.54 38 | 34.0 47 | 4.08 36 | 10.5 67 | 31.6 71 | 5.02 57 | 4.95 73 | 30.6 73 | 2.31 64 | 30.1 57 | 44.2 64 | 19.1 37 | 24.2 110 | 50.1 109 | 26.0 116 | 1.80 34 | 0.92 26 | 6.63 47 | 22.7 77 | 52.1 85 | 30.0 84 |
PGM-C [120] | 67.8 | 4.80 99 | 24.9 105 | 2.34 98 | 9.79 78 | 42.4 88 | 7.86 85 | 11.3 73 | 34.5 81 | 9.49 76 | 5.28 78 | 34.6 84 | 2.54 73 | 34.5 83 | 49.1 93 | 26.5 71 | 9.26 13 | 37.2 58 | 6.72 21 | 0.42 11 | 0.07 7 | 1.85 12 | 23.7 82 | 53.0 90 | 25.6 69 |
FlowFields [110] | 68.8 | 4.67 95 | 24.4 101 | 2.22 92 | 9.80 79 | 44.3 95 | 7.67 83 | 11.8 76 | 36.4 88 | 10.1 83 | 4.90 70 | 30.5 72 | 2.63 75 | 36.4 92 | 51.6 103 | 28.9 85 | 8.76 10 | 38.7 68 | 6.48 15 | 0.85 19 | 0.03 3 | 2.71 19 | 23.3 79 | 53.7 95 | 22.3 55 |
TriangleFlow [30] | 69.0 | 2.81 57 | 14.9 59 | 1.22 37 | 7.27 48 | 37.1 63 | 3.76 31 | 9.83 62 | 30.2 66 | 3.34 30 | 3.84 49 | 27.1 58 | 1.72 57 | 39.4 106 | 53.7 108 | 34.8 96 | 21.8 106 | 43.5 94 | 16.0 102 | 4.72 79 | 7.40 118 | 8.30 59 | 18.5 58 | 44.3 62 | 21.5 51 |
FlowFields+ [130] | 69.1 | 4.68 96 | 24.5 102 | 2.22 92 | 9.86 82 | 44.7 97 | 7.63 82 | 12.1 78 | 37.3 91 | 10.3 85 | 4.92 72 | 30.3 71 | 2.61 74 | 36.3 91 | 51.6 103 | 28.3 82 | 8.62 9 | 38.7 68 | 6.57 16 | 0.41 9 | 0.02 1 | 1.92 14 | 23.7 82 | 53.6 94 | 25.5 68 |
Rannacher [23] | 69.6 | 3.03 64 | 16.1 66 | 1.59 72 | 8.35 64 | 36.9 62 | 6.87 73 | 11.1 71 | 31.8 72 | 6.71 65 | 4.88 69 | 29.7 70 | 2.34 65 | 31.7 69 | 45.9 79 | 23.3 59 | 16.8 90 | 44.0 97 | 10.3 82 | 4.89 81 | 2.57 79 | 12.1 76 | 16.7 48 | 41.9 52 | 19.9 46 |
SRR-TVOF-NL [91] | 69.7 | 3.16 66 | 16.2 67 | 1.49 63 | 8.87 70 | 38.5 70 | 5.57 57 | 12.3 80 | 33.4 77 | 8.53 72 | 3.96 53 | 26.6 52 | 1.34 39 | 32.8 73 | 44.6 70 | 27.2 77 | 13.8 61 | 39.0 71 | 8.34 56 | 5.55 89 | 5.38 109 | 17.8 101 | 22.0 74 | 43.3 58 | 25.2 67 |
CPM-Flow [116] | 69.9 | 4.79 98 | 24.9 105 | 2.32 96 | 9.83 80 | 42.4 88 | 7.89 86 | 11.2 72 | 33.9 79 | 9.50 77 | 5.25 76 | 34.3 82 | 2.50 72 | 34.7 86 | 49.3 96 | 26.7 72 | 10.3 20 | 37.5 63 | 7.62 43 | 0.42 11 | 0.07 7 | 1.82 11 | 24.5 87 | 54.2 96 | 26.8 75 |
LocallyOriented [52] | 70.1 | 4.06 87 | 20.2 88 | 1.87 82 | 12.1 92 | 47.6 100 | 8.49 90 | 15.9 93 | 39.1 98 | 11.1 88 | 5.10 74 | 28.6 63 | 2.84 76 | 34.0 80 | 47.4 84 | 25.7 68 | 11.8 29 | 32.6 36 | 7.84 48 | 1.10 21 | 1.51 41 | 6.95 48 | 20.3 65 | 46.8 73 | 23.1 59 |
EpicFlow [102] | 70.4 | 4.80 99 | 24.9 105 | 2.33 97 | 9.90 83 | 42.9 92 | 7.95 88 | 11.8 76 | 35.7 86 | 9.56 78 | 5.26 77 | 34.4 83 | 2.49 71 | 34.6 85 | 49.2 95 | 27.0 75 | 10.8 24 | 37.5 63 | 7.33 35 | 0.41 9 | 0.07 7 | 1.80 10 | 24.1 86 | 53.5 93 | 26.4 73 |
Aniso. Huber-L1 [22] | 70.6 | 2.84 60 | 14.5 55 | 1.46 60 | 14.0 94 | 42.6 90 | 12.9 93 | 13.4 85 | 31.3 69 | 13.0 91 | 6.50 86 | 35.2 87 | 4.19 88 | 29.7 54 | 42.4 55 | 21.8 51 | 14.5 74 | 35.0 48 | 8.43 60 | 5.54 88 | 3.18 87 | 12.8 79 | 16.6 47 | 37.7 44 | 20.9 49 |
Kuang [131] | 71.6 | 4.54 94 | 24.0 99 | 2.07 86 | 9.42 75 | 45.2 98 | 6.53 71 | 12.5 81 | 38.7 96 | 8.97 74 | 4.91 71 | 31.0 76 | 2.36 67 | 37.7 98 | 53.5 107 | 29.5 86 | 12.8 39 | 42.9 93 | 9.24 70 | 0.53 14 | 0.07 7 | 2.71 19 | 18.9 60 | 47.6 74 | 24.3 64 |
Dynamic MRF [7] | 71.9 | 3.39 73 | 18.9 83 | 1.30 41 | 5.60 23 | 33.5 42 | 2.81 22 | 9.67 61 | 31.3 69 | 3.54 31 | 4.64 67 | 33.7 81 | 2.39 68 | 38.0 99 | 51.2 101 | 34.9 97 | 19.2 102 | 51.8 112 | 15.2 101 | 3.41 65 | 0.37 18 | 20.9 105 | 25.1 89 | 52.2 86 | 31.7 89 |
DPOF [18] | 74.1 | 4.03 85 | 21.8 92 | 2.11 87 | 9.50 76 | 40.4 79 | 5.97 64 | 8.88 56 | 27.5 58 | 6.05 64 | 4.29 59 | 30.8 74 | 2.08 62 | 31.5 64 | 45.1 73 | 21.6 49 | 15.9 87 | 37.3 60 | 9.53 76 | 15.3 124 | 1.61 43 | 47.3 124 | 22.1 75 | 46.3 69 | 28.5 78 |
CBF [12] | 76.5 | 2.82 58 | 15.0 61 | 1.32 42 | 18.0 99 | 40.4 79 | 21.6 101 | 10.6 68 | 29.2 65 | 9.72 79 | 6.57 87 | 34.8 86 | 4.55 90 | 31.5 64 | 44.0 63 | 24.5 63 | 14.5 74 | 35.0 48 | 8.92 66 | 10.9 117 | 6.02 113 | 26.2 109 | 20.7 68 | 43.6 59 | 27.2 76 |
Brox et al. [5] | 76.7 | 3.55 82 | 18.8 82 | 1.64 74 | 10.1 87 | 39.6 77 | 8.97 91 | 11.7 75 | 33.4 77 | 8.96 73 | 6.57 87 | 36.4 89 | 3.41 82 | 38.2 101 | 47.6 85 | 45.3 113 | 13.5 52 | 42.4 90 | 9.63 77 | 0.27 8 | 0.99 27 | 0.47 4 | 31.0 101 | 56.4 102 | 43.3 105 |
Fusion [6] | 76.7 | 3.40 74 | 19.1 84 | 2.16 91 | 5.57 22 | 31.1 33 | 4.53 43 | 7.70 48 | 25.2 51 | 7.53 68 | 5.78 80 | 35.6 88 | 4.10 87 | 36.6 93 | 47.1 82 | 38.8 102 | 14.2 68 | 41.9 89 | 13.2 96 | 6.84 101 | 5.31 107 | 11.7 74 | 24.8 88 | 51.1 84 | 31.6 88 |
Local-TV-L1 [65] | 77.7 | 4.05 86 | 19.4 86 | 2.51 100 | 17.1 98 | 43.6 94 | 15.9 96 | 19.8 100 | 37.3 91 | 23.3 97 | 9.20 101 | 43.3 97 | 6.89 100 | 28.6 46 | 41.3 50 | 20.2 48 | 14.1 65 | 35.1 51 | 8.67 64 | 1.24 22 | 0.62 24 | 3.94 26 | 33.5 108 | 57.2 103 | 49.6 112 |
CLG-TV [48] | 78.3 | 2.80 56 | 14.6 56 | 1.41 52 | 14.0 94 | 40.7 82 | 14.1 95 | 12.7 82 | 32.0 73 | 11.0 87 | 8.13 94 | 47.7 105 | 5.99 96 | 32.0 71 | 45.2 74 | 25.2 65 | 14.1 65 | 40.1 81 | 10.9 87 | 6.45 97 | 5.82 111 | 10.4 68 | 19.0 61 | 42.4 54 | 26.6 74 |
LDOF [28] | 80.1 | 4.09 89 | 20.0 87 | 2.31 95 | 9.96 84 | 41.8 85 | 7.06 78 | 14.1 87 | 37.0 89 | 10.1 83 | 8.41 95 | 43.3 97 | 4.97 91 | 34.4 82 | 46.2 80 | 32.5 89 | 12.2 31 | 41.0 86 | 8.88 65 | 1.63 31 | 2.00 61 | 5.79 42 | 29.9 96 | 56.0 100 | 38.8 100 |
p-harmonic [29] | 80.1 | 3.47 76 | 19.1 84 | 2.29 94 | 8.40 65 | 35.9 58 | 6.80 72 | 12.8 83 | 34.6 83 | 9.84 82 | 9.04 99 | 47.6 104 | 6.72 98 | 37.1 95 | 48.7 91 | 39.6 103 | 13.1 44 | 44.0 97 | 11.2 88 | 3.43 66 | 2.50 76 | 6.33 44 | 21.2 70 | 45.2 65 | 30.5 86 |
DF-Auto [115] | 80.5 | 4.71 97 | 22.2 93 | 2.11 87 | 21.1 102 | 49.4 102 | 21.6 101 | 20.3 101 | 39.8 100 | 31.0 103 | 7.62 91 | 37.5 91 | 5.08 93 | 33.6 77 | 43.9 61 | 33.3 92 | 8.36 7 | 29.8 25 | 7.48 40 | 2.60 48 | 5.21 106 | 2.22 15 | 32.4 104 | 53.1 91 | 43.2 104 |
TriFlow [95] | 81.9 | 3.53 79 | 17.9 77 | 1.77 77 | 11.0 91 | 37.3 64 | 10.6 92 | 16.7 96 | 35.8 87 | 25.3 99 | 4.44 66 | 30.9 75 | 2.34 65 | 35.0 88 | 44.3 65 | 35.7 98 | 10.7 23 | 30.4 28 | 6.68 20 | 33.4 127 | 9.63 125 | 90.0 129 | 30.3 99 | 55.2 99 | 36.8 96 |
FlowNetS+ft+v [112] | 84.3 | 3.75 84 | 18.5 79 | 2.13 89 | 10.0 86 | 38.8 74 | 8.25 89 | 16.3 94 | 37.5 94 | 20.0 95 | 7.89 92 | 37.0 90 | 5.17 94 | 36.9 94 | 48.2 88 | 35.7 98 | 11.6 28 | 40.0 77 | 9.13 68 | 4.56 74 | 4.02 94 | 14.6 87 | 23.8 84 | 51.0 82 | 31.9 90 |
SuperFlow [81] | 84.5 | 3.40 74 | 16.6 68 | 1.81 81 | 15.3 96 | 41.5 83 | 15.9 96 | 17.0 97 | 35.2 85 | 27.6 100 | 10.0 103 | 43.1 96 | 8.60 102 | 36.1 90 | 44.3 65 | 46.7 114 | 13.1 44 | 39.8 76 | 11.3 89 | 2.49 45 | 4.24 98 | 4.26 30 | 30.0 97 | 54.7 97 | 40.8 102 |
Second-order prior [8] | 85.8 | 3.49 77 | 18.6 80 | 1.79 78 | 9.83 80 | 40.6 81 | 7.83 84 | 14.1 87 | 39.0 97 | 9.82 81 | 6.20 83 | 31.4 78 | 3.83 84 | 34.7 86 | 49.4 97 | 27.6 78 | 18.7 98 | 52.1 113 | 11.4 90 | 9.18 111 | 3.60 90 | 20.1 103 | 19.1 62 | 48.2 77 | 24.4 65 |
Learning Flow [11] | 85.9 | 3.56 83 | 18.2 78 | 1.56 70 | 8.71 68 | 41.5 83 | 6.17 68 | 14.5 90 | 37.8 95 | 11.8 89 | 7.92 93 | 41.1 95 | 5.02 92 | 40.9 109 | 51.7 105 | 42.4 105 | 15.4 84 | 47.2 105 | 11.4 90 | 2.73 51 | 6.19 114 | 7.64 56 | 23.0 78 | 49.9 80 | 28.9 80 |
Ad-TV-NDC [36] | 87.8 | 10.3 115 | 20.2 88 | 18.1 124 | 38.1 114 | 53.0 108 | 43.3 116 | 28.0 110 | 45.6 106 | 35.7 107 | 20.6 110 | 48.9 108 | 23.8 111 | 29.1 52 | 42.5 56 | 19.1 37 | 13.7 58 | 36.1 54 | 9.46 75 | 2.03 39 | 1.43 38 | 4.38 32 | 41.4 116 | 65.3 114 | 57.0 118 |
CNN-flow-warp+ref [117] | 88.4 | 4.85 101 | 24.6 103 | 2.62 102 | 13.2 93 | 41.8 85 | 12.9 93 | 17.7 99 | 39.6 99 | 25.0 98 | 8.67 97 | 44.8 100 | 5.78 95 | 38.1 100 | 48.2 88 | 43.5 108 | 13.7 58 | 40.4 83 | 9.32 72 | 1.80 34 | 1.29 37 | 9.16 63 | 33.2 105 | 57.7 105 | 42.9 103 |
StereoOF-V1MT [119] | 89.8 | 4.08 88 | 23.0 94 | 1.49 63 | 10.4 88 | 53.3 109 | 4.35 39 | 16.3 94 | 49.5 111 | 5.71 61 | 7.37 90 | 48.5 106 | 4.03 86 | 46.7 113 | 62.9 116 | 42.9 107 | 21.9 108 | 64.7 119 | 17.0 103 | 1.58 28 | 1.87 53 | 9.43 65 | 33.2 105 | 66.2 115 | 36.5 95 |
BlockOverlap [61] | 92.0 | 4.14 92 | 17.3 73 | 3.50 105 | 23.3 103 | 43.1 93 | 25.5 105 | 21.0 102 | 37.2 90 | 27.8 101 | 13.1 104 | 39.0 93 | 13.7 106 | 28.8 48 | 38.6 36 | 28.2 80 | 18.7 98 | 37.2 58 | 13.3 97 | 12.6 120 | 6.40 117 | 40.8 121 | 26.8 93 | 45.8 67 | 43.3 105 |
Shiralkar [42] | 93.7 | 4.11 90 | 23.3 95 | 1.52 66 | 8.88 71 | 44.5 96 | 5.07 49 | 14.5 90 | 41.9 102 | 6.96 67 | 7.32 89 | 44.7 99 | 4.37 89 | 38.8 105 | 55.2 111 | 33.1 90 | 26.7 115 | 60.7 114 | 18.5 108 | 10.4 114 | 3.38 89 | 32.9 115 | 26.7 92 | 61.6 109 | 29.5 83 |
SegOF [10] | 94.1 | 6.07 109 | 25.2 108 | 3.62 107 | 36.7 112 | 55.3 110 | 41.7 114 | 26.1 106 | 43.8 104 | 39.2 110 | 15.2 106 | 45.4 101 | 12.3 104 | 46.5 112 | 56.0 112 | 57.5 118 | 18.2 96 | 49.9 108 | 14.9 100 | 0.19 4 | 0.71 25 | 0.86 7 | 31.1 102 | 52.9 89 | 35.9 94 |
StereoFlow [44] | 94.8 | 28.4 128 | 55.1 129 | 37.7 128 | 81.1 129 | 92.6 129 | 77.8 128 | 65.0 127 | 82.9 129 | 51.1 123 | 69.6 129 | 90.7 129 | 65.5 126 | 52.7 120 | 67.5 120 | 44.9 112 | 8.13 4 | 33.5 43 | 6.60 17 | 0.05 2 | 0.37 18 | 0.17 2 | 32.2 103 | 54.8 98 | 40.4 101 |
HBpMotionGpu [43] | 95.4 | 5.00 102 | 21.6 91 | 2.81 104 | 31.1 109 | 49.5 103 | 35.0 109 | 26.3 108 | 45.3 105 | 37.1 109 | 9.18 100 | 39.3 94 | 7.65 101 | 33.7 78 | 45.6 77 | 32.2 88 | 15.7 86 | 37.4 61 | 9.89 80 | 5.71 92 | 4.19 97 | 12.5 78 | 33.4 107 | 56.3 101 | 47.8 110 |
SPSA-learn [13] | 96.4 | 5.52 106 | 25.3 110 | 4.12 109 | 25.2 106 | 50.0 104 | 26.8 106 | 25.1 105 | 45.7 107 | 36.7 108 | 19.0 107 | 54.2 110 | 20.8 108 | 38.6 102 | 48.4 90 | 44.4 110 | 17.9 94 | 45.3 101 | 17.6 105 | 1.60 29 | 0.54 22 | 5.27 40 | 39.6 113 | 57.9 106 | 53.3 115 |
2bit-BM-tele [98] | 96.8 | 5.17 104 | 23.4 96 | 3.54 106 | 16.3 97 | 40.3 78 | 16.7 98 | 15.2 92 | 34.6 83 | 14.2 93 | 8.49 96 | 37.6 92 | 6.75 99 | 32.8 73 | 44.5 68 | 28.6 84 | 24.3 111 | 43.9 96 | 22.5 114 | 15.6 125 | 8.72 123 | 50.0 126 | 26.2 90 | 50.8 81 | 37.5 98 |
FlowNet2 [122] | 97.6 | 7.84 111 | 30.7 111 | 2.58 101 | 41.4 116 | 65.2 116 | 44.4 117 | 29.6 112 | 48.0 109 | 46.8 118 | 5.31 79 | 24.0 46 | 3.06 80 | 47.8 114 | 64.8 119 | 36.3 101 | 17.8 93 | 44.3 99 | 13.4 98 | 2.93 56 | 8.71 122 | 5.22 38 | 30.2 98 | 61.7 110 | 28.8 79 |
IAOF2 [51] | 98.2 | 4.13 91 | 20.4 90 | 2.02 85 | 18.0 99 | 45.9 99 | 18.0 99 | 17.1 98 | 37.3 91 | 21.4 96 | 46.4 120 | 57.8 112 | 56.1 123 | 37.4 97 | 48.8 92 | 35.9 100 | 25.5 112 | 42.7 91 | 20.4 111 | 6.62 98 | 3.04 86 | 15.3 94 | 26.8 93 | 51.0 82 | 37.9 99 |
Black & Anandan [4] | 98.9 | 5.52 106 | 25.2 108 | 4.71 111 | 24.4 105 | 52.8 106 | 24.4 104 | 26.8 109 | 48.3 110 | 34.4 105 | 20.9 111 | 60.4 113 | 22.4 110 | 38.7 104 | 49.7 98 | 42.8 106 | 18.9 100 | 49.4 106 | 17.1 104 | 1.78 33 | 2.57 79 | 3.30 22 | 36.0 109 | 57.3 104 | 49.5 111 |
Filter Flow [19] | 99.1 | 5.13 103 | 23.5 97 | 2.40 99 | 20.5 101 | 51.3 105 | 19.6 100 | 23.3 104 | 42.6 103 | 35.3 106 | 27.2 113 | 48.8 107 | 28.3 113 | 39.4 106 | 49.1 93 | 44.6 111 | 17.9 94 | 40.5 84 | 11.8 93 | 7.39 103 | 7.67 120 | 11.5 73 | 26.6 91 | 46.0 68 | 33.9 91 |
Modified CLG [34] | 101.1 | 7.42 110 | 31.9 113 | 5.50 112 | 31.7 110 | 52.9 107 | 37.6 112 | 28.4 111 | 50.8 112 | 40.4 112 | 20.3 109 | 60.5 114 | 21.3 109 | 39.5 108 | 51.2 101 | 42.2 104 | 14.2 68 | 45.8 104 | 11.5 92 | 3.24 59 | 1.70 51 | 9.31 64 | 40.3 114 | 65.1 113 | 54.7 117 |
IAOF [50] | 102.1 | 5.70 108 | 24.0 99 | 3.65 108 | 30.0 108 | 48.7 101 | 33.9 108 | 26.2 107 | 47.8 108 | 29.5 102 | 28.0 114 | 51.3 109 | 32.9 114 | 37.3 96 | 50.2 99 | 34.4 95 | 26.2 113 | 50.9 111 | 18.0 107 | 5.85 94 | 1.63 44 | 11.7 74 | 36.3 110 | 59.4 108 | 51.9 113 |
GraphCuts [14] | 104.0 | 5.45 105 | 24.7 104 | 2.64 103 | 24.3 104 | 55.8 112 | 21.9 103 | 21.4 103 | 40.8 101 | 32.4 104 | 9.25 102 | 46.4 102 | 6.31 97 | 38.6 102 | 51.7 105 | 33.8 93 | 28.8 118 | 39.7 75 | 18.7 109 | 12.1 119 | 2.87 83 | 35.1 118 | 38.5 111 | 58.4 107 | 53.9 116 |
2D-CLG [1] | 104.5 | 14.0 119 | 40.7 120 | 8.09 117 | 45.8 118 | 59.5 113 | 54.5 121 | 36.8 118 | 60.4 119 | 47.3 119 | 48.9 122 | 75.1 123 | 54.2 122 | 44.9 110 | 54.8 109 | 52.5 115 | 19.0 101 | 50.3 110 | 17.8 106 | 1.26 23 | 0.07 7 | 4.43 33 | 47.4 121 | 71.2 121 | 59.9 122 |
GroupFlow [9] | 104.9 | 8.95 114 | 33.2 114 | 7.07 114 | 43.6 117 | 70.7 121 | 45.5 118 | 32.7 114 | 59.8 118 | 42.4 115 | 13.2 105 | 46.6 103 | 12.4 105 | 51.1 117 | 70.0 122 | 34.2 94 | 30.8 120 | 62.8 116 | 33.8 121 | 1.54 27 | 2.56 78 | 4.14 27 | 39.0 112 | 67.0 117 | 47.4 109 |
UnFlow [129] | 106.0 | 22.1 126 | 43.6 123 | 7.44 116 | 52.6 122 | 73.8 125 | 54.3 120 | 47.7 124 | 74.9 127 | 47.5 120 | 26.4 112 | 68.7 118 | 24.7 112 | 64.5 125 | 75.5 126 | 65.6 125 | 28.5 117 | 67.0 123 | 27.1 118 | 0.19 4 | 1.87 53 | 0.05 1 | 30.4 100 | 62.4 111 | 36.8 96 |
Nguyen [33] | 107.0 | 8.19 112 | 31.4 112 | 4.40 110 | 54.9 123 | 55.7 111 | 70.2 124 | 33.6 116 | 54.6 113 | 43.3 116 | 43.5 119 | 60.9 115 | 50.5 120 | 45.1 111 | 54.9 110 | 54.2 116 | 21.1 105 | 49.4 106 | 21.0 112 | 2.92 55 | 1.87 53 | 7.39 54 | 44.7 119 | 66.2 115 | 58.5 120 |
Horn & Schunck [3] | 108.2 | 8.56 113 | 35.5 115 | 7.11 115 | 29.4 107 | 65.4 117 | 28.1 107 | 33.4 115 | 64.4 121 | 41.2 114 | 30.6 115 | 67.2 117 | 33.6 115 | 49.1 116 | 61.3 113 | 55.5 117 | 26.4 114 | 64.7 119 | 26.1 117 | 3.02 57 | 3.95 92 | 2.44 16 | 48.8 122 | 75.0 123 | 58.8 121 |
SILK [79] | 110.2 | 10.7 116 | 35.7 116 | 14.6 121 | 37.7 113 | 64.2 114 | 42.5 115 | 32.3 113 | 59.3 116 | 40.6 113 | 19.9 108 | 56.8 111 | 20.4 107 | 51.6 119 | 62.6 115 | 59.6 121 | 27.2 116 | 63.0 117 | 23.2 115 | 4.92 83 | 1.68 50 | 13.1 80 | 46.9 120 | 71.6 122 | 61.7 124 |
TI-DOFE [24] | 113.7 | 21.2 124 | 43.7 124 | 34.5 127 | 64.6 127 | 71.9 124 | 76.5 127 | 47.1 123 | 75.6 128 | 53.7 124 | 57.3 124 | 76.4 124 | 65.6 127 | 51.5 118 | 63.9 117 | 60.0 122 | 30.4 119 | 65.8 122 | 33.2 119 | 2.24 42 | 1.65 47 | 5.22 38 | 59.1 126 | 82.1 128 | 71.2 127 |
Periodicity [78] | 114.0 | 11.0 117 | 41.5 121 | 5.85 113 | 35.3 111 | 64.5 115 | 36.8 111 | 51.0 125 | 55.5 114 | 61.7 126 | 49.6 123 | 81.4 126 | 48.4 119 | 66.0 127 | 83.6 129 | 59.0 119 | 46.1 125 | 76.4 127 | 43.0 125 | 1.67 32 | 5.33 108 | 8.13 58 | 48.8 122 | 78.9 125 | 57.5 119 |
Heeger++ [104] | 115.0 | 24.4 127 | 45.8 125 | 9.72 119 | 47.8 120 | 85.9 128 | 37.8 113 | 66.2 128 | 69.8 124 | 75.2 127 | 59.7 126 | 88.6 128 | 56.9 124 | 66.6 128 | 80.3 128 | 62.4 124 | 65.6 129 | 87.3 129 | 67.1 129 | 4.14 71 | 1.26 36 | 7.39 54 | 41.9 117 | 68.8 118 | 43.4 107 |
SLK [47] | 117.6 | 17.8 122 | 50.1 128 | 21.7 125 | 62.2 126 | 77.8 127 | 74.7 126 | 40.4 121 | 72.7 126 | 48.1 121 | 66.2 127 | 73.9 121 | 76.1 129 | 60.9 123 | 71.2 123 | 72.9 129 | 33.1 121 | 68.3 125 | 35.4 123 | 5.99 95 | 1.09 30 | 11.4 72 | 60.5 128 | 81.9 127 | 75.0 128 |
FFV1MT [106] | 118.1 | 22.0 125 | 42.2 122 | 9.20 118 | 41.0 115 | 76.9 126 | 36.1 110 | 66.5 129 | 71.9 125 | 79.2 128 | 58.5 125 | 87.7 127 | 57.1 125 | 64.8 126 | 76.5 127 | 70.3 128 | 64.8 128 | 85.8 128 | 65.3 128 | 4.70 78 | 4.86 103 | 11.3 71 | 41.9 117 | 68.8 118 | 43.4 107 |
Adaptive flow [45] | 119.1 | 16.0 120 | 36.3 117 | 17.5 123 | 57.9 124 | 67.3 118 | 64.2 123 | 38.7 120 | 59.2 115 | 48.8 122 | 39.9 117 | 69.2 119 | 44.2 118 | 49.0 115 | 62.0 114 | 43.6 109 | 39.1 124 | 62.2 115 | 34.3 122 | 34.2 128 | 23.4 128 | 82.8 127 | 40.6 115 | 64.9 112 | 51.9 113 |
FOLKI [16] | 120.3 | 13.4 118 | 45.9 126 | 16.0 122 | 48.5 121 | 67.4 119 | 57.8 122 | 36.6 117 | 66.2 122 | 40.3 111 | 32.2 116 | 66.9 116 | 37.2 116 | 52.9 121 | 64.2 118 | 60.1 123 | 34.7 122 | 65.7 121 | 40.2 124 | 12.9 121 | 7.56 119 | 33.8 117 | 55.3 125 | 78.0 124 | 70.7 126 |
PGAM+LK [55] | 122.3 | 17.6 121 | 48.4 127 | 26.7 126 | 45.8 118 | 71.8 123 | 49.9 119 | 38.3 119 | 67.6 123 | 44.6 117 | 42.8 118 | 79.5 125 | 42.6 117 | 56.5 122 | 69.9 121 | 59.0 119 | 37.8 123 | 70.5 126 | 33.6 120 | 23.5 126 | 15.0 127 | 48.8 125 | 54.6 124 | 80.9 126 | 61.1 123 |
Pyramid LK [2] | 122.8 | 19.8 123 | 36.7 118 | 40.3 129 | 61.8 125 | 68.8 120 | 74.6 125 | 43.5 122 | 63.7 120 | 58.2 125 | 46.9 121 | 72.7 120 | 54.1 121 | 61.5 124 | 74.5 125 | 65.8 126 | 51.3 126 | 64.1 118 | 50.1 126 | 10.8 116 | 6.30 115 | 31.9 114 | 68.2 129 | 84.9 129 | 84.8 129 |
HCIC-L [99] | 125.5 | 29.6 129 | 37.7 119 | 11.4 120 | 77.3 128 | 71.7 122 | 90.9 129 | 63.0 126 | 59.4 117 | 83.6 129 | 66.9 128 | 74.8 122 | 69.8 128 | 68.1 129 | 74.1 124 | 66.1 127 | 54.4 127 | 67.4 124 | 52.5 127 | 58.9 129 | 43.5 129 | 89.4 128 | 59.4 127 | 70.0 120 | 67.4 125 |
AdaConv-v1 [126] | 130.0 | 82.5 130 | 78.4 130 | 94.0 130 | 98.6 130 | 99.3 130 | 97.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 97.4 130 | 96.9 130 | 99.7 130 | 100.0 130 | 99.9 130 | 99.8 130 | 93.4 130 | 95.5 130 | 93.4 130 | 86.5 130 | 85.7 130 | 99.4 130 | 99.9 130 | 99.9 130 | 99.9 130 |
SepConv-v1 [127] | 130.0 | 82.5 130 | 78.4 130 | 94.0 130 | 98.6 130 | 99.3 130 | 97.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 97.4 130 | 96.9 130 | 99.7 130 | 100.0 130 | 99.9 130 | 99.8 130 | 93.4 130 | 95.5 130 | 93.4 130 | 86.5 130 | 85.7 130 | 99.4 130 | 99.9 130 | 99.9 130 | 99.9 130 |
Method | time* | frames | color | Reference and notes | |
[1] 2D-CLG | 844 | 2 | gray | The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences. | |
[2] Pyramid LK | 12 | 2 | color | A modification of Bouguet's pyramidal implementation of Lucas-Kanade. | |
[3] Horn & Schunck | 49 | 2 | gray | A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data. | |
[4] Black & Anandan | 328 | 2 | gray | A modern Matlab implementation of the Black & Anandan method by Deqing Sun. | |
[5] Brox et al. | 18 | 2 | color | T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.) | |
[6] Fusion | 2,666 | 2 | color | V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008. | |
[7] Dynamic MRF | 366 | 2 | gray | B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.) | |
[8] Second-order prior | 14 | 2 | gray | W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[9] GroupFlow | 600 | 2 | gray | X. Ren. Local Grouping for Optical Flow. CVPR 2008. | |
[10] SegOF | 60 | 2 | color | L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available. | |
[11] Learning Flow | 825 | 2 | gray | D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008. | |
[12] CBF | 69 | 2 | color | W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[13] SPSA-learn | 200 | 2 | color | Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008. | |
[14] GraphCuts | 1,200 | 2 | color | T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008. | |
[15] F-TV-L1 | 8 | 2 | gray | A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008. | |
[16] FOLKI | 1.4 | 2 | gray | G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005. | |
[17] TV-L1-improved | 2.9 | 2 | gray | A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision. | |
[18] DPOF | 287 | 2 | color | C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.) | |
[19] Filter Flow | 34,000 | 2 | color | S. Seitz and S. Baker. Filter flow. ICCV 2009. | |
[20] Adaptive | 9.2 | 2 | gray | A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009. | |
[21] Complementary OF | 44 | 2 | color | H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009. | |
[22] Aniso. Huber-L1 | 2 | 2 | gray | M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision. | |
[23] Rannacher | 0.12 | 2 | gray | J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009. | |
[24] TI-DOFE | 260 | 2 | gray | C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009. | |
[25] NL-TV-NCC | 20 | 2 | color | M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010. | |
[26] MDP-Flow | 188 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010. | |
[27] ACK-Prior | 5872 | 2 | color | K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010. | |
[28] LDOF | 122 | 2 | color | T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011. | |
[29] p-harmonic | 565 | 2 | gray | J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010. | |
[30] TriangleFlow | 4200 | 2 | gray | B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010. | |
[31] Classic+NL | 972 | 2 | color | D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code. | |
[32] Classic++ | 486 | 2 | gray | A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010. | |
[33] Nguyen | 33 | 2 | gray | D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011. | |
[34] Modified CLG | 133 | 2 | gray | R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010. | |
[35] ComplOF-FED-GPU | 0.97 | 2 | color | P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010. | |
[36] Ad-TV-NDC | 35 | 2 | gray | M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010. | |
[37] Layers++ | 18206 | 2 | color | D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010. | |
[38] OFH | 620 | 3 | color | H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011. | |
[39] LSM | 1615 | 2 | color | K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011. | |
[40] CostFilter | 55 | 2 | color | C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011. | |
[41] Bartels | 0.15 | 2 | gray | C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU. | |
[42] Shiralkar | 600 | 2 | gray | M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242. | |
[43] HBpMotionGpu | 1000 | 5 | gray | S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.) | |
[44] StereoFlow | 7200 | 2 | color | G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772. | |
[45] Adaptive flow | 121 | 2 | gray | T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011. | |
[46] TC-Flow | 2500 | 5 | color | S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011. | |
[47] SLK | 300 | 2 | gray | T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011. | |
[48] CLG-TV | 29 | 2 | gray | M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code. | |
[49] SimpleFlow | 1.7 | 2 | color | M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012. | |
[50] IAOF | 57 | 2 | gray | D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011. | |
[51] IAOF2 | 56 | 2 | gray | D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011. | |
[52] LocallyOriented | 9541 | 2 | gray | Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012. | |
[53] IROF-TV | 261 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop. | |
[54] Sparse Occlusion | 2312 | 2 | color | A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011. | |
[55] PGAM+LK | 0.37 | 2 | gray | A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010. | |
[56] Sparse-NonSparse | 713 | 2 | color | L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013. | |
[57] nLayers | 36150 | 4 | color | D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012. | |
[58] IROF++ | 187 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013. | |
[59] COFM | 600 | 3 | color | M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013. | |
[60] Efficient-NL | 400 | 2 | color | P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012. | |
[61] BlockOverlap | 2 | 2 | gray | M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012. | |
[62] Ramp | 1200 | 2 | color | A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012. | |
[63] Occlusion-TV-L1 | 538 | 3 | gray | C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012. | |
[64] TV-L1-MCT | 90 | 2 | color | M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012. | |
[65] Local-TV-L1 | 500 | 2 | gray | L. Raket. Local smoothness for global optical flow. ICIP 2012. | |
[66] ALD-Flow | 61 | 2 | color | M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012. | |
[67] SIOF | 234 | 2 | color | L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012. | |
[68] MDP-Flow2 | 342 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available. | |
[69] TCOF | 1421 | all | gray | J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013. | |
[70] LME | 476 | 2 | color | W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013. | |
[71] NN-field | 362 | 2 | color | L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[72] FESL | 3310 | 2 | color | W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013. | |
[73] PMF | 35 | 2 | color | J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013. | |
[74] FC-2Layers-FF | 2662 | 4 | color | D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013. | |
[75] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code. | |
[76] TC/T-Flow | 341 | 5 | color | M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013. | |
[77] OFLAF | 1530 | 2 | color | T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013. | |
[78] Periodicity | 8000 | 4 | color | G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013. | |
[79] SILK | 572 | 2 | gray | P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP. | |
[80] CRTflow | 13 | 3 | color | O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013. | |
[81] SuperFlow | 178 | 2 | color | Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507. | |
[82] Aniso-Texture | 300 | 2 | color | Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267. | |
[83] Classic+CPF | 640 | 2 | gray | Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013. | |
[84] S2D-Matching | 1200 | 2 | color | Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479. | |
[85] AGIF+OF | 438 | 2 | gray | Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015. | |
[86] DeepFlow | 13 | 2 | color | P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[87] NNF-Local | 673 | 2 | color | Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014. | |
[88] EPPM w/o HM | 2.5 | 2 | color | L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014. | |
[89] MLDP_OF | 165 | 2 | gray | M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014. | |
[90] RFlow | 20 | 2 | gray | S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014. | |
[91] SRR-TVOF-NL | 32 | all | color | P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014. | |
[92] 2DHMM-SAS | 157 | 2 | color | M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission. | |
[93] WLIF-Flow | 700 | 2 | color | Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014. | |
[94] FMOF | 215 | 2 | color | N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014. | |
[95] TriFlow | 150 | 2 | color | TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914. | |
[96] ComponentFusion | 6.5 | 2 | color | Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941. | |
[97] AggregFlow | 1642 | 2 | color | D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759. | |
[98] 2bit-BM-tele | 124 | 2 | gray | R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013. | |
[99] HCIC-L | 330 | 2 | color | Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114. | |
[100] TF+OM | 600 | 2 | color | R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015. | |
[101] PH-Flow | 800 | 2 | color | J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015. | |
[102] EpicFlow | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015. | |
[103] NNF-EAC | 380 | 2 | color | Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336. | |
[104] Heeger++ | 6600 | 5 | gray | Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238. | |
[105] HBM-GC | 330 | 2 | color | A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015. | |
[106] FFV1MT | 358 | 5 | gray | F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015. | |
[107] ROF-ND | 4 | 2 | color | S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015. | |
[108] DeepFlow2 | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015. | |
[109] HAST | 2667 | 2 | color | Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221. | |
[110] FlowFields | 15 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015. | |
[111] SVFilterOh | 1.56 | 2 | color | Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788. | |
[112] FlowNetS+ft+v | 0.5 | 2 | color | Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235. | |
[113] CombBMOF | 51 | 2 | color | M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.) | |
[114] PMMST | 182 | 2 | color | F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015. | |
[115] DF-Auto | 70 | 2 | color | N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015. | |
[116] CPM-Flow | 3 | 2 | color | Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241. | |
[117] CNN-flow-warp+ref | 1.4 | 3 | color | D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016. | |
[118] Steered-L1 | 804 | 2 | color | Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016. | |
[119] StereoOF-V1MT | 343 | 2 | gray | Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132. | |
[120] PGM-C | 5 | 2 | color | Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016. | |
[121] RNLOD-Flow | 1040 | 2 | gray | C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016. | |
[122] FlowNet2 | 0.091 | 2 | color | Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900. | |
[123] S2F-IF | 20 | 2 | color | Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765. | |
[124] BriefMatch | 0.068 | 2 | gray | G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62. | |
[125] OAR-Flow | 60 | 2 | color | Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20. | |
[126] AdaConv-v1 | 2.8 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017. | |
[127] SepConv-v1 | 0.2 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017. | |
[128] ProbFlowFields | 37 | 2 | color | A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017. | |
[129] UnFlow | 0.12 | 2 | color | Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018. | |
[130] FlowFields+ | 10.5 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017. | |
[131] Kuang | 9.9 | 2 | gray | F. Kuang. PatchMatch algorithms for motion estimation and stereo reconstruction. Master thesis, University of Stuttgart, 2017. |