Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A50
A75
A95
Error type: endpoint angle interpolation normalized interpolation |
R10.0 angle error |
avg. |
Army (Hidden texture) GT im0 im1 |
Mequon (Hidden texture) GT im0 im1 |
Schefflera (Hidden texture) GT im0 im1 |
Wooden (Hidden texture) GT im0 im1 |
Grove (Synthetic) GT im0 im1 |
Urban (Synthetic) GT im0 im1 |
Yosemite (Synthetic) GT im0 im1 |
Teddy (Stereo) GT im0 im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
NNF-Local [87] | 8.6 | 3.83 4 | 16.9 9 | 1.87 7 | 2.64 7 | 16.1 11 | 1.33 7 | 3.02 3 | 10.7 3 | 1.33 13 | 2.79 15 | 18.9 21 | 1.11 16 | 4.82 1 | 6.85 1 | 1.73 2 | 4.13 4 | 14.6 3 | 2.27 2 | 0.52 20 | 5.08 48 | 0.00 1 | 0.28 3 | 1.04 3 | 0.04 2 |
OFLAF [77] | 9.1 | 3.84 5 | 17.2 11 | 1.99 12 | 2.48 5 | 14.1 5 | 1.41 8 | 2.96 2 | 10.1 2 | 1.17 9 | 2.36 8 | 14.7 7 | 0.82 9 | 5.15 3 | 7.90 7 | 2.15 4 | 6.43 32 | 18.2 12 | 4.98 18 | 0.27 2 | 2.42 4 | 0.07 16 | 0.79 9 | 1.88 7 | 1.81 22 |
MDP-Flow2 [68] | 10.8 | 3.86 7 | 17.2 11 | 1.90 9 | 2.06 1 | 12.6 1 | 1.04 2 | 3.22 5 | 11.0 4 | 1.16 8 | 3.27 26 | 21.7 31 | 1.19 20 | 6.35 16 | 8.86 13 | 3.12 10 | 5.40 14 | 15.7 4 | 5.11 20 | 0.38 12 | 3.75 25 | 0.02 3 | 0.49 5 | 1.80 6 | 0.13 6 |
NN-field [71] | 12.4 | 4.31 17 | 18.6 22 | 2.22 21 | 3.13 15 | 18.3 25 | 1.79 18 | 3.16 4 | 11.1 5 | 1.40 14 | 2.08 5 | 16.7 10 | 0.78 7 | 5.28 4 | 7.44 3 | 2.25 5 | 2.53 1 | 8.92 1 | 0.92 1 | 0.89 39 | 6.39 72 | 0.02 3 | 0.27 2 | 0.98 2 | 0.04 2 |
PMMST [114] | 13.6 | 4.02 10 | 16.5 7 | 1.46 1 | 3.86 31 | 16.9 17 | 3.33 45 | 3.91 10 | 12.6 9 | 2.82 38 | 2.18 7 | 9.47 1 | 1.30 26 | 5.68 9 | 7.88 6 | 2.78 7 | 5.25 12 | 13.7 2 | 4.29 10 | 0.53 22 | 5.11 49 | 0.02 3 | 0.26 1 | 0.94 1 | 0.04 2 |
nLayers [57] | 22.3 | 4.08 13 | 16.2 5 | 2.80 37 | 4.71 54 | 19.3 32 | 3.82 73 | 4.64 18 | 15.2 18 | 3.96 58 | 1.99 3 | 13.2 2 | 0.80 8 | 5.34 6 | 7.57 5 | 3.22 12 | 5.85 26 | 16.8 7 | 4.64 13 | 0.87 37 | 3.68 23 | 0.96 50 | 0.84 10 | 2.94 17 | 0.75 8 |
ComponentFusion [96] | 23.2 | 4.03 11 | 17.7 15 | 2.19 20 | 2.17 4 | 13.1 3 | 1.26 5 | 3.86 9 | 13.2 11 | 1.58 16 | 2.85 18 | 18.0 14 | 1.03 14 | 6.68 23 | 9.59 22 | 4.14 32 | 8.35 69 | 27.3 68 | 8.34 80 | 0.60 24 | 4.03 30 | 0.52 39 | 0.76 8 | 2.22 11 | 1.09 10 |
LME [70] | 23.5 | 3.70 3 | 16.1 4 | 1.69 2 | 2.13 2 | 13.0 2 | 1.19 4 | 5.91 44 | 15.4 19 | 7.43 85 | 3.23 22 | 22.4 35 | 1.19 20 | 6.60 22 | 9.12 16 | 4.39 41 | 6.11 28 | 20.8 21 | 6.60 50 | 0.52 20 | 4.96 46 | 0.07 16 | 1.09 14 | 3.28 24 | 1.86 24 |
SVFilterOh [111] | 24.1 | 4.36 19 | 15.9 3 | 2.01 15 | 3.04 13 | 16.3 13 | 1.78 17 | 3.31 6 | 11.3 6 | 1.20 10 | 2.02 4 | 13.6 4 | 0.57 2 | 5.94 12 | 8.69 12 | 2.12 3 | 6.61 34 | 19.3 14 | 6.32 46 | 5.10 97 | 12.9 110 | 10.0 109 | 0.75 7 | 2.20 10 | 1.32 12 |
FC-2Layers-FF [74] | 24.7 | 4.03 11 | 16.3 6 | 2.39 28 | 4.23 40 | 20.9 41 | 3.21 42 | 3.40 8 | 11.4 7 | 2.64 32 | 2.74 13 | 17.1 11 | 1.03 14 | 5.73 10 | 8.29 10 | 3.31 14 | 7.49 46 | 20.5 20 | 6.66 54 | 1.30 54 | 6.84 76 | 0.34 33 | 0.64 6 | 1.78 5 | 1.20 11 |
NNF-EAC [103] | 25.3 | 4.32 18 | 18.6 22 | 2.18 19 | 2.69 8 | 15.1 7 | 1.64 13 | 3.93 11 | 13.1 10 | 1.27 11 | 4.17 58 | 23.0 44 | 1.95 55 | 7.09 31 | 9.97 29 | 3.89 28 | 6.33 30 | 17.4 9 | 5.53 23 | 0.55 23 | 5.18 50 | 0.02 3 | 1.60 39 | 4.32 40 | 1.93 27 |
HAST [109] | 26.8 | 2.98 1 | 12.9 1 | 1.71 3 | 3.63 28 | 15.0 6 | 2.78 34 | 2.46 1 | 8.38 1 | 0.25 1 | 2.84 17 | 18.0 14 | 0.67 4 | 5.02 2 | 7.35 2 | 1.66 1 | 8.83 77 | 22.4 35 | 8.37 81 | 6.13 103 | 12.0 105 | 18.0 116 | 0.31 4 | 1.13 4 | 0.03 1 |
WLIF-Flow [93] | 28.0 | 3.97 9 | 17.0 10 | 2.12 17 | 3.53 22 | 18.5 27 | 2.37 28 | 4.60 17 | 15.1 16 | 2.34 28 | 3.40 29 | 20.3 27 | 1.50 31 | 7.69 54 | 11.4 63 | 4.79 54 | 6.67 35 | 17.8 11 | 5.53 23 | 0.40 15 | 3.68 23 | 0.07 16 | 1.59 38 | 3.82 34 | 2.63 44 |
RNLOD-Flow [121] | 28.9 | 3.58 2 | 15.7 2 | 1.83 6 | 3.60 26 | 19.9 35 | 2.06 22 | 5.53 38 | 18.1 40 | 2.42 30 | 2.75 14 | 17.7 12 | 1.01 13 | 6.01 13 | 9.09 15 | 3.98 29 | 7.21 40 | 20.0 16 | 6.87 63 | 2.59 75 | 9.67 88 | 1.95 67 | 1.06 13 | 2.66 14 | 1.79 21 |
FESL [72] | 29.3 | 3.91 8 | 16.6 8 | 2.13 18 | 5.68 77 | 23.5 58 | 4.23 78 | 5.17 29 | 16.8 25 | 2.99 40 | 2.41 10 | 15.8 8 | 0.89 12 | 5.76 11 | 8.62 11 | 4.05 30 | 5.81 23 | 17.6 10 | 5.32 22 | 1.09 47 | 5.68 63 | 1.21 57 | 1.35 23 | 2.89 16 | 1.72 19 |
Layers++ [37] | 29.4 | 4.39 20 | 17.8 16 | 3.14 45 | 3.70 29 | 18.0 22 | 2.84 35 | 3.37 7 | 11.5 8 | 2.65 33 | 2.38 9 | 14.1 6 | 0.82 9 | 5.33 5 | 7.52 4 | 3.78 26 | 7.58 49 | 22.0 31 | 6.13 40 | 1.81 70 | 7.08 78 | 0.54 40 | 1.45 30 | 2.46 13 | 4.56 80 |
ALD-Flow [66] | 30.5 | 4.22 14 | 18.2 19 | 1.93 11 | 3.20 18 | 16.8 16 | 1.59 12 | 5.21 30 | 17.4 32 | 1.13 7 | 3.70 37 | 22.9 42 | 1.26 22 | 6.54 21 | 9.31 18 | 3.14 11 | 5.25 12 | 21.5 26 | 4.98 18 | 0.88 38 | 4.67 38 | 4.48 92 | 2.69 59 | 6.66 58 | 4.79 81 |
TC/T-Flow [76] | 31.3 | 4.57 24 | 20.6 30 | 2.00 13 | 3.45 21 | 18.7 28 | 1.52 10 | 4.30 13 | 14.3 12 | 0.67 3 | 3.97 53 | 23.1 45 | 1.80 46 | 6.35 16 | 9.50 21 | 3.36 17 | 4.48 6 | 15.7 4 | 4.78 15 | 1.30 54 | 6.94 77 | 5.07 95 | 2.08 51 | 5.10 48 | 2.83 49 |
PMF [73] | 31.8 | 4.65 26 | 18.3 21 | 2.34 24 | 3.37 19 | 18.2 24 | 1.92 20 | 4.20 12 | 14.6 14 | 1.01 6 | 3.24 24 | 18.6 18 | 1.11 16 | 5.50 7 | 8.09 8 | 2.43 6 | 6.99 38 | 24.8 51 | 6.27 44 | 6.87 106 | 17.3 121 | 8.77 108 | 0.91 11 | 2.06 8 | 2.06 30 |
Correlation Flow [75] | 32.1 | 4.57 24 | 20.5 29 | 1.87 7 | 2.71 9 | 16.2 12 | 1.16 3 | 5.74 42 | 17.9 38 | 0.66 2 | 1.91 1 | 13.5 3 | 0.85 11 | 8.00 63 | 12.0 73 | 4.57 44 | 8.69 72 | 23.8 44 | 8.93 86 | 0.84 34 | 4.74 39 | 0.96 50 | 1.38 26 | 3.81 33 | 1.91 26 |
Efficient-NL [60] | 33.1 | 4.24 15 | 17.4 13 | 2.24 22 | 4.30 41 | 21.8 44 | 2.75 32 | 5.26 33 | 16.9 27 | 2.67 34 | 3.43 31 | 21.0 29 | 1.74 41 | 6.02 14 | 9.16 17 | 3.31 14 | 7.84 58 | 21.7 28 | 6.26 43 | 1.36 57 | 6.79 75 | 1.03 53 | 1.48 33 | 3.08 20 | 1.77 20 |
AGIF+OF [85] | 33.4 | 4.39 20 | 18.0 18 | 2.80 37 | 5.10 65 | 23.7 61 | 3.70 66 | 5.06 25 | 16.8 25 | 3.11 41 | 3.29 27 | 20.1 25 | 1.45 30 | 6.45 19 | 9.31 18 | 4.62 46 | 6.77 37 | 19.7 15 | 5.86 32 | 0.37 11 | 3.60 21 | 0.25 29 | 1.79 45 | 3.68 30 | 3.12 58 |
TC-Flow [46] | 34.7 | 4.27 16 | 19.0 25 | 1.91 10 | 2.85 10 | 16.6 15 | 1.45 9 | 5.05 24 | 16.9 27 | 0.80 5 | 4.05 54 | 23.9 53 | 1.74 41 | 6.73 24 | 9.68 24 | 2.93 9 | 5.83 24 | 22.9 39 | 5.68 29 | 1.39 59 | 4.87 44 | 7.32 104 | 2.46 56 | 6.13 55 | 4.49 77 |
OAR-Flow [125] | 36.2 | 5.41 45 | 21.6 41 | 2.61 31 | 4.96 61 | 22.3 47 | 2.88 36 | 7.90 59 | 23.8 58 | 4.19 62 | 4.45 65 | 22.7 41 | 1.90 50 | 7.03 29 | 10.1 32 | 3.39 18 | 5.10 10 | 22.3 33 | 4.56 12 | 0.29 4 | 2.64 8 | 0.17 25 | 1.58 37 | 4.89 47 | 1.68 17 |
Classic+CPF [83] | 36.3 | 4.77 30 | 19.7 27 | 2.99 40 | 4.59 46 | 23.3 56 | 3.08 40 | 5.24 31 | 17.2 30 | 2.81 37 | 3.32 28 | 21.3 30 | 1.57 35 | 6.51 20 | 9.49 20 | 4.24 37 | 7.39 43 | 21.5 26 | 6.27 44 | 1.02 42 | 5.33 54 | 1.40 59 | 1.47 32 | 3.19 22 | 2.47 42 |
COFM [59] | 39.1 | 4.75 29 | 20.2 28 | 2.63 33 | 3.40 20 | 18.3 25 | 2.14 24 | 6.19 48 | 19.3 46 | 4.00 59 | 3.04 20 | 18.8 19 | 1.11 16 | 7.45 44 | 10.1 32 | 7.01 85 | 8.80 75 | 20.9 22 | 6.68 55 | 1.41 60 | 3.66 22 | 2.76 79 | 1.22 17 | 2.28 12 | 3.72 68 |
PH-Flow [101] | 39.2 | 5.11 37 | 21.0 32 | 3.62 59 | 4.59 46 | 22.4 48 | 3.37 49 | 4.37 14 | 14.5 13 | 3.45 46 | 3.93 50 | 22.5 37 | 2.07 62 | 6.34 15 | 9.00 14 | 3.74 24 | 7.28 42 | 21.7 28 | 6.39 48 | 1.61 65 | 5.58 61 | 1.58 62 | 1.15 16 | 2.12 9 | 3.39 63 |
IROF++ [58] | 39.3 | 4.68 27 | 19.4 26 | 2.70 34 | 4.66 50 | 23.1 52 | 3.42 54 | 5.25 32 | 17.2 30 | 3.79 54 | 3.95 51 | 23.2 46 | 2.05 59 | 6.97 27 | 9.84 27 | 4.64 47 | 7.99 62 | 24.6 48 | 7.05 67 | 0.44 17 | 4.30 35 | 0.00 1 | 1.37 25 | 3.26 23 | 2.83 49 |
HBM-GC [105] | 39.4 | 5.82 52 | 18.2 19 | 2.00 13 | 4.47 45 | 18.7 28 | 3.80 72 | 4.39 15 | 15.1 16 | 1.73 20 | 2.42 11 | 13.8 5 | 0.72 6 | 6.77 25 | 9.60 23 | 4.08 31 | 7.61 51 | 19.0 13 | 5.76 30 | 4.61 93 | 12.6 107 | 2.83 81 | 2.39 54 | 5.72 51 | 5.01 85 |
ProbFlowFields [128] | 39.8 | 8.29 81 | 31.1 80 | 5.73 95 | 3.54 23 | 18.0 22 | 2.75 32 | 6.07 47 | 18.9 45 | 5.22 65 | 3.54 34 | 17.7 12 | 1.91 51 | 7.66 53 | 10.8 49 | 4.59 45 | 5.06 9 | 20.0 16 | 5.58 27 | 0.38 12 | 3.08 14 | 0.07 16 | 1.70 42 | 4.56 43 | 2.41 41 |
Sparse-NonSparse [56] | 41.0 | 4.98 33 | 20.8 31 | 4.09 68 | 4.63 49 | 22.9 49 | 3.41 53 | 5.02 23 | 16.7 24 | 3.47 49 | 3.89 46 | 22.6 40 | 1.91 51 | 7.17 34 | 10.2 35 | 4.30 39 | 7.66 53 | 22.3 33 | 6.80 59 | 0.69 29 | 3.53 20 | 0.89 47 | 1.52 35 | 3.56 29 | 2.97 54 |
CostFilter [40] | 41.0 | 5.29 43 | 22.0 43 | 2.85 39 | 3.54 23 | 17.7 20 | 2.16 25 | 4.64 18 | 16.0 20 | 1.75 21 | 3.68 36 | 22.5 37 | 1.27 24 | 5.67 8 | 8.14 9 | 2.85 8 | 7.76 55 | 25.9 58 | 6.80 59 | 6.98 109 | 24.2 126 | 12.9 111 | 1.43 27 | 4.11 37 | 2.02 29 |
MLDP_OF [89] | 41.5 | 6.35 59 | 26.0 59 | 3.41 50 | 2.97 12 | 16.4 14 | 1.76 16 | 5.47 36 | 17.8 36 | 1.30 12 | 2.79 15 | 19.7 23 | 1.12 19 | 7.13 33 | 10.0 30 | 3.75 25 | 7.49 46 | 21.4 25 | 9.75 92 | 5.04 95 | 6.22 69 | 17.0 115 | 1.79 45 | 4.28 39 | 2.14 32 |
FMOF [94] | 42.3 | 4.42 22 | 17.8 16 | 3.06 43 | 5.03 62 | 23.1 52 | 3.63 62 | 4.45 16 | 14.8 15 | 2.80 36 | 2.94 19 | 18.8 19 | 1.26 22 | 7.00 28 | 10.2 35 | 4.71 50 | 8.92 78 | 20.9 22 | 7.13 69 | 1.06 45 | 6.34 71 | 1.85 66 | 2.58 58 | 5.80 53 | 3.06 56 |
Classic+NL [31] | 42.3 | 5.07 36 | 21.0 32 | 4.22 72 | 4.70 53 | 23.4 57 | 3.27 43 | 4.98 22 | 16.5 22 | 3.48 50 | 3.75 40 | 22.5 37 | 1.68 38 | 7.21 37 | 10.2 35 | 4.32 40 | 7.82 56 | 22.4 35 | 6.71 56 | 1.47 61 | 6.39 72 | 1.18 56 | 1.12 15 | 2.87 15 | 2.27 36 |
LSM [39] | 42.5 | 5.00 35 | 21.2 38 | 3.93 65 | 4.62 48 | 22.9 49 | 3.37 49 | 5.13 27 | 17.1 29 | 3.26 44 | 3.80 41 | 22.9 42 | 1.87 48 | 6.92 26 | 9.78 25 | 4.41 43 | 7.71 54 | 22.4 35 | 6.74 57 | 1.00 41 | 4.76 41 | 1.16 55 | 1.68 41 | 3.94 35 | 2.90 53 |
Ramp [62] | 42.9 | 5.12 38 | 21.1 36 | 3.82 64 | 4.68 52 | 23.2 54 | 3.47 57 | 4.89 21 | 16.3 21 | 3.46 47 | 3.83 43 | 22.3 34 | 1.93 54 | 7.23 38 | 10.2 35 | 4.80 55 | 7.61 51 | 22.1 32 | 6.80 59 | 1.20 50 | 5.04 47 | 1.43 60 | 1.36 24 | 2.98 18 | 2.31 40 |
Aniso-Texture [82] | 44.4 | 3.84 5 | 17.5 14 | 1.76 4 | 2.88 11 | 15.9 9 | 2.11 23 | 7.10 56 | 20.9 51 | 2.30 24 | 1.97 2 | 16.5 9 | 0.57 2 | 8.24 69 | 11.9 70 | 5.22 68 | 8.82 76 | 26.6 65 | 6.77 58 | 8.34 115 | 16.2 120 | 1.43 60 | 2.42 55 | 5.55 49 | 2.84 51 |
NL-TV-NCC [25] | 44.7 | 5.44 46 | 21.7 42 | 2.24 22 | 4.00 35 | 21.9 45 | 1.69 14 | 5.27 34 | 17.8 36 | 0.67 3 | 2.52 12 | 19.1 22 | 0.67 4 | 8.37 72 | 12.5 82 | 5.12 67 | 11.5 96 | 32.0 92 | 9.19 89 | 0.86 35 | 4.93 45 | 1.35 58 | 2.16 52 | 6.46 56 | 1.63 14 |
S2D-Matching [84] | 44.9 | 4.97 32 | 21.3 40 | 3.55 56 | 4.74 55 | 23.6 59 | 3.35 47 | 6.50 50 | 20.9 51 | 3.46 47 | 3.49 32 | 20.4 28 | 1.60 36 | 7.07 30 | 10.0 30 | 4.22 35 | 7.82 56 | 23.1 40 | 6.87 63 | 1.78 69 | 5.90 66 | 2.12 69 | 1.30 20 | 3.14 21 | 2.74 46 |
TV-L1-MCT [64] | 46.4 | 4.69 28 | 18.9 24 | 3.60 58 | 5.64 76 | 25.6 73 | 4.21 76 | 5.53 38 | 18.1 40 | 3.23 42 | 3.04 20 | 19.9 24 | 1.35 27 | 7.49 45 | 10.6 43 | 4.91 61 | 8.34 67 | 22.8 38 | 7.50 76 | 0.79 33 | 2.61 6 | 3.57 86 | 1.73 44 | 3.45 27 | 3.26 61 |
MDP-Flow [26] | 46.5 | 5.65 50 | 24.7 55 | 4.93 86 | 3.70 29 | 17.6 19 | 3.40 52 | 5.47 36 | 18.7 44 | 4.66 63 | 3.87 44 | 24.3 56 | 1.88 49 | 7.12 32 | 9.89 28 | 5.00 65 | 6.17 29 | 25.9 58 | 4.66 14 | 0.61 25 | 5.65 62 | 0.05 13 | 3.28 71 | 8.39 71 | 3.45 66 |
AggregFlow [97] | 46.8 | 6.17 56 | 23.3 50 | 2.58 30 | 7.01 86 | 28.0 91 | 5.29 87 | 8.46 64 | 24.2 60 | 7.66 87 | 3.73 38 | 20.2 26 | 1.73 40 | 7.25 39 | 10.6 43 | 3.52 19 | 4.43 5 | 16.4 6 | 4.80 17 | 0.75 32 | 5.43 57 | 0.25 29 | 1.92 48 | 4.46 42 | 4.12 72 |
IROF-TV [53] | 47.8 | 5.22 41 | 22.6 48 | 3.59 57 | 4.80 57 | 24.2 65 | 3.73 71 | 5.71 41 | 18.4 43 | 3.64 52 | 4.19 59 | 25.7 70 | 1.92 53 | 7.63 52 | 10.7 46 | 5.26 69 | 9.22 82 | 30.2 82 | 6.60 50 | 0.30 6 | 2.86 10 | 0.02 3 | 1.32 22 | 3.76 32 | 2.27 36 |
CombBMOF [113] | 49.6 | 6.51 61 | 28.6 69 | 2.61 31 | 3.98 34 | 18.7 28 | 2.29 27 | 5.29 35 | 17.4 32 | 2.33 27 | 5.12 76 | 26.1 76 | 3.28 81 | 6.35 16 | 9.81 26 | 3.34 16 | 12.0 98 | 28.4 73 | 15.1 110 | 3.73 86 | 12.8 109 | 0.76 44 | 0.98 12 | 3.00 19 | 0.09 5 |
OFH [38] | 50.2 | 6.38 60 | 25.7 58 | 4.69 82 | 3.90 32 | 20.6 39 | 2.24 26 | 7.85 58 | 24.2 60 | 2.27 23 | 4.11 57 | 25.1 60 | 1.72 39 | 7.44 43 | 10.4 40 | 4.69 48 | 8.13 64 | 28.9 76 | 8.44 84 | 0.44 17 | 4.25 32 | 0.12 21 | 2.80 61 | 8.82 79 | 2.74 46 |
Adaptive [20] | 50.5 | 5.12 38 | 22.0 43 | 2.34 24 | 4.82 59 | 23.2 54 | 3.50 58 | 8.67 69 | 24.5 65 | 3.56 51 | 4.19 59 | 25.3 66 | 1.83 47 | 7.40 42 | 10.6 43 | 3.63 21 | 5.84 25 | 23.2 42 | 3.75 8 | 3.25 83 | 8.86 85 | 0.89 47 | 2.87 63 | 6.69 59 | 3.14 60 |
Sparse Occlusion [54] | 50.5 | 4.99 34 | 21.1 36 | 2.79 36 | 4.13 38 | 20.1 38 | 3.00 39 | 5.94 46 | 19.4 47 | 2.15 22 | 3.41 30 | 21.8 32 | 1.35 27 | 8.17 68 | 12.1 76 | 4.74 51 | 7.87 60 | 25.6 57 | 6.34 47 | 11.4 120 | 17.7 122 | 2.71 78 | 1.64 40 | 4.70 46 | 1.81 22 |
Occlusion-TV-L1 [63] | 50.8 | 5.23 42 | 22.2 45 | 2.36 27 | 4.40 43 | 21.2 42 | 3.39 51 | 8.46 64 | 24.8 66 | 3.83 56 | 3.92 48 | 24.8 58 | 1.74 41 | 9.11 84 | 13.1 94 | 5.75 75 | 4.65 7 | 23.9 45 | 3.52 6 | 1.27 53 | 3.13 16 | 0.44 36 | 3.56 77 | 8.92 80 | 3.28 62 |
RFlow [90] | 51.6 | 5.85 53 | 24.8 57 | 4.44 78 | 3.18 16 | 17.9 21 | 1.88 19 | 7.81 57 | 24.4 64 | 2.32 26 | 3.25 25 | 23.4 49 | 1.55 32 | 7.94 57 | 11.6 66 | 4.86 57 | 8.23 65 | 28.0 72 | 6.64 53 | 1.16 49 | 2.13 2 | 1.13 54 | 4.10 87 | 9.22 86 | 6.81 93 |
2DHMM-SAS [92] | 52.5 | 5.14 40 | 21.0 32 | 3.79 63 | 5.26 70 | 25.2 70 | 3.45 55 | 6.97 55 | 20.2 48 | 4.18 61 | 4.06 55 | 23.3 48 | 2.10 63 | 7.18 35 | 10.2 35 | 4.92 62 | 8.29 66 | 23.7 43 | 7.16 70 | 1.26 51 | 5.41 56 | 1.63 63 | 1.71 43 | 3.75 31 | 2.74 46 |
ACK-Prior [27] | 52.7 | 5.49 48 | 24.0 53 | 1.81 5 | 2.55 6 | 15.7 8 | 0.83 1 | 5.07 26 | 17.7 35 | 1.52 15 | 2.14 6 | 18.1 16 | 0.50 1 | 8.64 75 | 11.6 66 | 7.10 88 | 14.6 109 | 30.7 84 | 11.7 99 | 8.46 116 | 11.5 101 | 19.5 118 | 3.68 81 | 7.25 62 | 2.64 45 |
SimpleFlow [49] | 53.4 | 5.65 50 | 22.4 47 | 4.93 86 | 5.47 75 | 24.5 68 | 4.28 79 | 6.88 54 | 21.0 53 | 3.95 57 | 4.74 69 | 25.2 62 | 3.02 75 | 7.19 36 | 10.1 32 | 4.70 49 | 8.34 67 | 23.1 40 | 7.16 70 | 1.02 42 | 4.61 37 | 0.89 47 | 1.29 19 | 3.44 25 | 2.47 42 |
S2F-IF [123] | 55.7 | 9.49 94 | 37.6 100 | 4.93 86 | 4.81 58 | 25.6 73 | 3.34 46 | 8.25 62 | 26.1 69 | 6.40 73 | 4.99 73 | 25.6 69 | 2.93 73 | 7.80 55 | 11.0 54 | 4.90 60 | 5.61 17 | 24.9 54 | 5.83 31 | 0.62 27 | 5.35 55 | 0.22 27 | 1.43 27 | 4.11 37 | 1.67 16 |
Complementary OF [21] | 55.8 | 7.27 70 | 30.0 74 | 4.31 73 | 3.18 16 | 18.9 31 | 1.52 10 | 5.91 44 | 20.2 48 | 2.31 25 | 4.22 62 | 24.8 58 | 2.05 59 | 7.50 47 | 10.4 40 | 4.99 64 | 12.3 101 | 31.7 91 | 8.87 85 | 0.61 25 | 2.69 9 | 1.72 65 | 3.33 72 | 9.22 86 | 4.88 84 |
ROF-ND [107] | 56.6 | 6.70 62 | 27.6 65 | 3.53 54 | 3.08 14 | 16.0 10 | 1.73 15 | 5.81 43 | 18.3 42 | 1.58 16 | 3.81 42 | 18.4 17 | 2.20 64 | 9.45 89 | 14.0 106 | 6.31 82 | 11.3 95 | 29.6 80 | 7.27 73 | 9.92 118 | 10.8 93 | 7.29 103 | 1.53 36 | 3.44 25 | 1.64 15 |
TCOF [69] | 57.3 | 7.04 68 | 26.9 62 | 3.54 55 | 4.93 60 | 23.7 61 | 3.45 55 | 9.94 83 | 27.8 77 | 7.40 84 | 3.74 39 | 23.7 52 | 1.55 32 | 10.0 98 | 14.3 107 | 4.40 42 | 4.91 8 | 17.0 8 | 5.53 23 | 5.08 96 | 9.68 89 | 4.19 90 | 1.43 27 | 4.44 41 | 1.69 18 |
PGM-C [120] | 58.6 | 9.47 92 | 37.1 97 | 4.81 85 | 5.08 63 | 26.1 78 | 3.63 62 | 8.75 71 | 27.6 75 | 7.02 78 | 5.65 84 | 28.1 91 | 3.63 89 | 7.99 60 | 11.3 60 | 4.88 58 | 5.71 21 | 24.5 47 | 5.97 34 | 0.31 7 | 3.01 13 | 0.02 3 | 2.07 50 | 6.50 57 | 2.14 32 |
TF+OM [100] | 59.0 | 6.03 55 | 23.7 52 | 2.78 35 | 4.39 42 | 19.9 35 | 3.57 59 | 8.73 70 | 23.0 57 | 11.2 93 | 3.57 35 | 23.2 46 | 1.36 29 | 7.98 59 | 11.1 57 | 5.89 77 | 8.95 79 | 25.3 56 | 7.06 68 | 1.68 67 | 11.2 98 | 0.20 26 | 3.56 77 | 8.35 70 | 4.18 73 |
Steered-L1 [118] | 59.1 | 4.54 23 | 21.2 38 | 2.09 16 | 2.13 2 | 13.9 4 | 1.31 6 | 4.80 20 | 16.5 22 | 1.64 18 | 3.87 44 | 25.1 60 | 1.60 36 | 8.62 74 | 11.5 65 | 7.01 85 | 11.1 92 | 28.7 74 | 10.4 95 | 12.0 124 | 12.3 106 | 34.9 126 | 5.90 98 | 9.03 84 | 11.6 106 |
FlowFields [110] | 60.5 | 9.65 96 | 37.6 100 | 5.13 89 | 5.09 64 | 25.9 76 | 3.72 68 | 8.92 73 | 28.3 81 | 7.07 80 | 5.45 80 | 26.0 74 | 3.82 90 | 7.95 58 | 11.2 59 | 5.01 66 | 5.75 22 | 26.1 61 | 6.01 35 | 0.40 15 | 3.29 18 | 0.12 21 | 1.92 48 | 5.99 54 | 1.89 25 |
DeepFlow2 [108] | 61.0 | 6.80 64 | 28.5 68 | 2.99 40 | 5.20 69 | 22.9 49 | 3.60 61 | 8.88 72 | 26.2 70 | 5.75 70 | 5.76 86 | 26.8 81 | 3.41 86 | 7.34 41 | 10.7 46 | 3.58 20 | 5.86 27 | 24.8 51 | 6.22 42 | 1.02 42 | 3.78 27 | 3.08 84 | 4.35 90 | 9.84 90 | 5.80 88 |
EPPM w/o HM [88] | 61.2 | 8.62 85 | 33.5 88 | 3.62 59 | 3.58 25 | 19.7 33 | 1.93 21 | 6.19 48 | 20.5 50 | 1.64 18 | 4.64 67 | 25.2 62 | 2.54 67 | 7.60 51 | 10.4 40 | 5.81 76 | 11.2 93 | 31.6 89 | 9.82 93 | 6.91 108 | 8.93 86 | 15.9 114 | 1.48 33 | 4.06 36 | 2.01 28 |
FlowFields+ [130] | 61.2 | 9.76 98 | 38.1 104 | 5.31 91 | 5.14 66 | 26.2 80 | 3.72 68 | 8.99 74 | 28.6 83 | 7.15 83 | 5.09 75 | 25.9 73 | 3.29 82 | 7.82 56 | 11.0 54 | 4.94 63 | 5.22 11 | 24.7 50 | 5.18 21 | 0.70 31 | 5.85 65 | 0.30 32 | 1.79 45 | 5.77 52 | 1.45 13 |
CPM-Flow [116] | 61.9 | 9.47 92 | 37.1 97 | 4.79 83 | 5.15 67 | 26.3 81 | 3.67 64 | 8.59 68 | 27.1 73 | 7.00 77 | 5.59 82 | 27.8 88 | 3.57 87 | 7.99 60 | 11.3 60 | 4.74 51 | 5.70 20 | 24.1 46 | 6.05 37 | 0.48 19 | 4.29 34 | 0.02 3 | 2.76 60 | 7.63 66 | 4.11 71 |
EpicFlow [102] | 63.0 | 9.44 91 | 37.1 97 | 4.80 84 | 5.15 67 | 26.4 82 | 3.70 66 | 9.58 79 | 30.0 85 | 7.07 80 | 5.38 79 | 27.8 88 | 3.29 82 | 8.01 65 | 11.3 60 | 4.88 58 | 5.67 19 | 24.6 48 | 6.12 39 | 0.32 10 | 3.13 16 | 0.02 3 | 3.10 69 | 7.52 64 | 4.79 81 |
ComplOF-FED-GPU [35] | 63.2 | 6.96 66 | 30.7 77 | 3.33 48 | 4.74 55 | 24.9 69 | 2.66 30 | 6.71 52 | 22.4 54 | 2.45 31 | 4.44 64 | 26.2 77 | 2.05 59 | 7.50 47 | 10.7 46 | 4.20 34 | 9.78 83 | 34.0 97 | 9.47 91 | 2.42 74 | 4.74 39 | 6.63 101 | 3.09 67 | 9.17 85 | 3.91 70 |
SRR-TVOF-NL [91] | 64.4 | 7.45 73 | 28.6 69 | 3.09 44 | 6.20 80 | 26.1 78 | 3.90 74 | 9.82 81 | 28.4 82 | 5.78 71 | 3.96 52 | 23.5 50 | 1.55 32 | 7.55 49 | 10.8 49 | 5.27 70 | 9.21 81 | 26.7 66 | 7.25 72 | 5.74 100 | 11.5 101 | 4.01 88 | 1.30 20 | 3.49 28 | 2.19 35 |
TV-L1-improved [17] | 64.8 | 5.52 49 | 23.4 51 | 3.42 51 | 4.13 38 | 20.8 40 | 2.96 37 | 8.29 63 | 24.2 60 | 3.64 52 | 4.06 55 | 24.4 57 | 1.77 44 | 8.34 71 | 12.1 76 | 4.15 33 | 13.7 105 | 38.4 106 | 14.9 107 | 4.40 92 | 10.1 91 | 2.14 70 | 3.33 72 | 8.42 72 | 3.40 64 |
F-TV-L1 [15] | 65.0 | 8.70 86 | 31.4 82 | 8.47 103 | 7.61 90 | 27.3 87 | 5.86 88 | 11.0 86 | 28.0 78 | 5.73 69 | 5.75 85 | 28.7 93 | 3.32 85 | 7.28 40 | 10.8 49 | 3.72 22 | 6.59 33 | 26.4 62 | 4.38 11 | 1.26 51 | 5.30 53 | 0.44 36 | 3.04 66 | 7.76 67 | 2.29 39 |
SIOF [67] | 66.2 | 5.37 44 | 22.6 48 | 2.34 24 | 6.11 78 | 28.4 92 | 4.30 80 | 12.6 92 | 29.2 84 | 14.4 94 | 5.52 81 | 27.4 85 | 3.00 74 | 8.96 83 | 12.6 84 | 6.02 78 | 8.72 73 | 27.9 70 | 7.93 77 | 0.38 12 | 3.48 19 | 0.02 3 | 3.09 67 | 7.58 65 | 4.85 83 |
DPOF [18] | 66.3 | 9.01 88 | 34.7 90 | 3.68 62 | 6.16 79 | 25.4 72 | 4.32 81 | 5.55 40 | 17.9 38 | 3.36 45 | 3.92 48 | 25.3 66 | 2.00 57 | 8.14 67 | 11.0 54 | 6.05 79 | 10.5 88 | 27.9 70 | 8.16 79 | 9.33 117 | 6.19 68 | 21.0 120 | 1.46 31 | 4.57 44 | 0.80 9 |
Aniso. Huber-L1 [22] | 66.5 | 5.98 54 | 24.2 54 | 3.23 47 | 8.53 94 | 27.3 87 | 7.91 93 | 9.64 80 | 25.6 68 | 5.52 67 | 5.00 74 | 25.7 70 | 2.75 71 | 8.66 76 | 12.8 89 | 4.74 51 | 7.60 50 | 24.8 51 | 3.51 5 | 3.65 85 | 7.24 79 | 3.00 83 | 2.57 57 | 6.69 59 | 2.86 52 |
Kuang [131] | 66.8 | 9.07 89 | 37.0 96 | 4.51 80 | 5.33 73 | 27.5 89 | 3.72 68 | 9.47 77 | 30.4 87 | 6.52 75 | 4.70 68 | 25.3 66 | 2.62 70 | 8.00 63 | 11.4 63 | 5.58 72 | 8.05 63 | 28.7 74 | 8.99 87 | 0.31 7 | 3.11 15 | 0.02 3 | 3.00 65 | 7.43 63 | 5.99 90 |
BriefMatch [124] | 67.9 | 4.78 31 | 21.0 32 | 2.40 29 | 4.00 35 | 19.8 34 | 2.68 31 | 5.13 27 | 17.5 34 | 2.41 29 | 3.23 22 | 22.1 33 | 1.28 25 | 9.81 96 | 12.0 73 | 13.1 116 | 17.2 111 | 33.8 96 | 17.8 113 | 7.84 111 | 12.7 108 | 22.3 121 | 8.01 110 | 10.5 96 | 16.1 117 |
Classic++ [32] | 68.2 | 5.46 47 | 22.2 45 | 4.35 75 | 4.66 50 | 22.1 46 | 3.57 59 | 8.00 60 | 24.3 63 | 5.06 64 | 4.21 61 | 25.2 62 | 2.01 58 | 8.77 79 | 12.7 87 | 5.47 71 | 9.03 80 | 30.2 82 | 7.29 74 | 2.92 81 | 7.73 81 | 3.10 85 | 3.83 84 | 8.53 73 | 3.87 69 |
LocallyOriented [52] | 68.6 | 8.05 79 | 30.6 76 | 3.63 61 | 8.09 92 | 30.8 98 | 6.17 90 | 12.3 91 | 32.3 92 | 7.04 79 | 4.88 72 | 25.2 62 | 2.88 72 | 8.80 81 | 12.7 87 | 4.27 38 | 5.41 15 | 20.4 18 | 6.07 38 | 1.35 56 | 6.03 67 | 0.99 52 | 3.73 83 | 8.62 75 | 4.18 73 |
CRTflow [80] | 70.8 | 7.63 76 | 31.8 85 | 3.42 51 | 4.40 43 | 21.2 42 | 2.97 38 | 8.99 74 | 26.6 71 | 4.11 60 | 4.86 71 | 26.5 78 | 2.57 68 | 7.99 60 | 11.7 68 | 3.26 13 | 18.0 115 | 40.2 109 | 22.2 118 | 1.47 61 | 4.45 36 | 2.51 76 | 4.73 92 | 11.4 101 | 7.30 94 |
DeepFlow [86] | 71.2 | 7.55 74 | 29.3 72 | 4.67 81 | 6.29 82 | 23.7 61 | 4.86 83 | 10.0 84 | 28.0 78 | 8.76 92 | 6.15 93 | 27.3 83 | 3.83 91 | 7.49 45 | 10.8 49 | 3.72 22 | 6.40 31 | 26.8 67 | 6.85 62 | 1.12 48 | 2.92 12 | 3.94 87 | 7.07 103 | 11.2 100 | 12.7 108 |
TriFlow [95] | 71.2 | 7.87 78 | 30.1 75 | 3.19 46 | 7.12 87 | 24.4 67 | 7.15 92 | 13.9 95 | 31.4 89 | 20.0 99 | 3.50 33 | 22.4 35 | 1.77 44 | 8.70 77 | 11.7 68 | 7.03 87 | 7.51 48 | 21.9 30 | 6.63 52 | 28.6 127 | 14.7 117 | 78.3 129 | 2.16 52 | 5.57 50 | 2.14 32 |
Rannacher [23] | 73.0 | 6.99 67 | 27.1 63 | 5.36 93 | 5.27 71 | 24.3 66 | 4.22 77 | 9.51 78 | 27.1 73 | 5.54 68 | 4.76 70 | 25.7 70 | 2.58 69 | 8.80 81 | 12.9 91 | 4.82 56 | 11.0 90 | 35.7 100 | 9.36 90 | 2.33 73 | 4.76 41 | 2.39 75 | 2.82 62 | 8.01 68 | 3.13 59 |
Brox et al. [5] | 73.4 | 8.32 82 | 32.6 86 | 6.95 98 | 6.23 81 | 26.9 86 | 5.23 85 | 9.13 76 | 27.6 75 | 6.55 76 | 5.85 88 | 28.2 92 | 3.26 79 | 10.2 100 | 12.9 91 | 11.0 111 | 5.43 16 | 29.3 79 | 4.79 16 | 0.86 35 | 4.00 29 | 0.12 21 | 4.32 88 | 10.2 93 | 4.54 79 |
Bartels [41] | 73.6 | 6.83 65 | 26.2 60 | 5.19 90 | 3.93 33 | 17.4 18 | 3.30 44 | 6.63 51 | 22.6 55 | 3.25 43 | 4.45 65 | 23.9 53 | 2.48 66 | 9.12 85 | 12.1 76 | 8.25 96 | 10.6 89 | 31.1 85 | 12.3 102 | 5.74 100 | 10.4 92 | 18.9 117 | 5.34 94 | 9.52 88 | 8.47 100 |
Local-TV-L1 [65] | 73.9 | 9.60 95 | 30.8 78 | 7.89 102 | 12.7 100 | 30.2 97 | 13.3 100 | 15.9 101 | 32.3 92 | 17.3 96 | 6.19 94 | 28.0 90 | 3.84 92 | 7.55 49 | 10.9 53 | 4.22 35 | 7.48 45 | 26.4 62 | 6.02 36 | 0.28 3 | 1.87 1 | 0.15 24 | 9.10 112 | 10.8 98 | 20.5 118 |
Dynamic MRF [7] | 74.4 | 7.74 77 | 31.6 84 | 4.44 78 | 4.12 37 | 23.6 59 | 2.47 29 | 8.49 66 | 28.0 78 | 2.83 39 | 4.25 63 | 27.4 85 | 2.41 65 | 8.61 73 | 12.0 73 | 6.08 80 | 14.5 108 | 43.2 113 | 14.9 107 | 0.64 28 | 2.35 3 | 4.51 93 | 9.85 115 | 15.6 117 | 15.3 115 |
SuperFlow [81] | 74.8 | 7.15 69 | 27.4 64 | 3.52 53 | 10.4 97 | 27.8 90 | 11.2 97 | 14.5 99 | 31.5 91 | 22.4 101 | 5.93 89 | 31.6 99 | 3.23 78 | 8.77 79 | 11.9 70 | 8.59 100 | 5.61 17 | 25.9 58 | 3.72 7 | 3.76 88 | 11.1 97 | 0.37 35 | 3.59 79 | 8.96 82 | 3.01 55 |
CBF [12] | 78.7 | 6.32 57 | 26.2 60 | 3.35 49 | 11.1 98 | 25.6 73 | 13.7 101 | 8.51 67 | 24.1 59 | 7.12 82 | 5.12 76 | 26.0 74 | 3.04 77 | 10.3 101 | 13.6 101 | 9.59 107 | 7.85 59 | 26.4 62 | 4.25 9 | 11.8 121 | 13.8 112 | 14.2 113 | 3.54 76 | 8.06 69 | 5.32 86 |
CLG-TV [48] | 79.8 | 6.33 58 | 24.7 55 | 4.13 69 | 9.08 96 | 26.6 83 | 9.31 96 | 9.85 82 | 26.8 72 | 5.82 72 | 5.30 78 | 26.5 78 | 3.03 76 | 10.4 103 | 14.6 111 | 7.57 91 | 7.95 61 | 31.1 85 | 6.51 49 | 5.92 102 | 11.4 99 | 4.36 91 | 3.41 74 | 8.81 78 | 3.06 56 |
TriangleFlow [30] | 80.0 | 7.35 71 | 28.2 67 | 4.31 73 | 5.35 74 | 25.2 70 | 3.36 48 | 8.00 60 | 24.8 66 | 2.70 35 | 3.90 47 | 24.1 55 | 1.97 56 | 12.9 117 | 17.8 123 | 10.7 109 | 13.1 103 | 32.3 94 | 13.9 105 | 4.71 94 | 16.1 119 | 4.04 89 | 3.65 80 | 8.73 77 | 5.69 87 |
DF-Auto [115] | 81.5 | 9.74 97 | 34.1 89 | 4.36 76 | 14.1 103 | 31.9 101 | 15.4 103 | 15.6 100 | 33.1 98 | 23.6 103 | 5.94 90 | 27.3 83 | 3.59 88 | 10.4 103 | 14.8 114 | 6.97 84 | 3.80 3 | 21.1 24 | 2.46 3 | 5.25 99 | 11.4 99 | 0.49 38 | 4.33 89 | 10.4 94 | 4.33 75 |
p-harmonic [29] | 82.0 | 8.47 83 | 36.3 94 | 7.17 99 | 5.27 71 | 24.1 64 | 4.39 82 | 11.2 88 | 31.4 89 | 8.13 91 | 7.18 99 | 32.4 100 | 5.24 100 | 8.04 66 | 11.1 57 | 6.89 83 | 9.82 84 | 36.4 102 | 10.6 96 | 2.61 76 | 5.51 59 | 0.54 40 | 4.07 86 | 9.01 83 | 4.34 76 |
CNN-flow-warp+ref [117] | 82.8 | 9.81 100 | 35.7 92 | 7.67 101 | 8.14 93 | 26.0 77 | 8.55 94 | 14.3 97 | 35.8 101 | 15.7 95 | 6.69 96 | 30.3 96 | 4.31 96 | 9.17 87 | 12.2 79 | 8.71 102 | 7.03 39 | 29.6 80 | 5.55 26 | 0.69 29 | 3.77 26 | 2.00 68 | 7.79 108 | 12.1 105 | 8.13 99 |
FlowNet2 [122] | 84.2 | 21.7 114 | 43.8 108 | 13.5 107 | 24.6 115 | 42.3 114 | 27.3 116 | 19.8 104 | 40.5 104 | 29.9 109 | 8.21 103 | 23.6 51 | 5.39 102 | 9.85 97 | 12.6 84 | 8.54 98 | 8.76 74 | 28.9 76 | 5.89 33 | 2.77 78 | 15.5 118 | 0.81 46 | 1.28 18 | 4.68 45 | 0.26 7 |
FlowNetS+ft+v [112] | 85.4 | 7.57 75 | 29.4 73 | 3.96 66 | 7.50 89 | 26.6 83 | 6.48 91 | 14.3 97 | 32.7 96 | 17.5 97 | 7.55 100 | 31.3 97 | 5.28 101 | 10.5 105 | 14.7 112 | 7.49 90 | 6.75 36 | 27.8 69 | 6.97 66 | 4.01 90 | 8.84 84 | 6.77 102 | 3.52 75 | 9.71 89 | 3.61 67 |
SegOF [10] | 86.2 | 12.6 103 | 34.9 91 | 7.20 100 | 21.3 111 | 36.9 109 | 25.3 114 | 21.6 107 | 40.5 104 | 31.8 113 | 14.1 111 | 37.7 108 | 10.8 106 | 10.3 101 | 12.5 82 | 12.6 115 | 10.2 86 | 40.2 109 | 11.2 98 | 0.29 4 | 2.91 11 | 0.07 16 | 2.90 64 | 8.68 76 | 2.07 31 |
Fusion [6] | 86.9 | 8.51 84 | 37.6 100 | 6.69 97 | 3.62 27 | 20.0 37 | 3.08 40 | 6.82 53 | 22.6 55 | 6.47 74 | 5.78 87 | 31.3 97 | 4.29 95 | 11.2 113 | 14.7 112 | 10.6 108 | 14.0 106 | 35.2 98 | 15.0 109 | 7.88 112 | 14.3 115 | 2.22 71 | 5.35 95 | 11.0 99 | 8.56 101 |
LDOF [28] | 86.9 | 8.22 80 | 31.4 82 | 4.08 67 | 7.64 91 | 29.4 94 | 5.87 89 | 10.7 85 | 30.3 86 | 7.99 90 | 7.80 101 | 36.8 106 | 4.86 99 | 9.14 86 | 12.4 81 | 8.24 95 | 8.58 70 | 32.0 92 | 8.38 82 | 1.75 68 | 5.26 52 | 5.02 94 | 5.52 96 | 12.9 109 | 6.04 91 |
Learning Flow [11] | 89.4 | 6.74 63 | 28.1 66 | 3.03 42 | 6.37 83 | 28.7 93 | 5.02 84 | 11.8 89 | 32.6 95 | 7.93 89 | 6.87 98 | 33.2 103 | 4.32 97 | 12.5 116 | 17.4 121 | 7.78 92 | 9.98 85 | 35.2 98 | 8.41 83 | 2.66 77 | 10.9 95 | 2.24 72 | 6.76 102 | 13.7 111 | 6.41 92 |
StereoFlow [44] | 90.2 | 58.0 129 | 76.4 129 | 63.7 126 | 51.8 128 | 66.9 129 | 48.3 124 | 51.0 129 | 73.0 129 | 41.6 123 | 63.5 129 | 83.4 129 | 56.7 127 | 13.3 119 | 13.7 102 | 19.1 122 | 3.63 2 | 20.4 18 | 2.73 4 | 0.26 1 | 2.49 5 | 0.05 13 | 4.06 85 | 8.57 74 | 5.81 89 |
Ad-TV-NDC [36] | 91.2 | 21.2 113 | 36.8 95 | 34.1 121 | 25.9 117 | 38.5 111 | 29.9 117 | 23.5 111 | 41.0 106 | 27.1 104 | 13.3 108 | 32.4 100 | 13.3 111 | 8.75 78 | 13.2 95 | 3.82 27 | 7.43 44 | 25.1 55 | 6.92 65 | 1.50 63 | 4.84 43 | 0.34 33 | 17.1 124 | 15.9 121 | 37.2 127 |
Second-order prior [8] | 91.7 | 7.35 71 | 31.2 81 | 4.16 70 | 6.80 85 | 29.5 95 | 5.27 86 | 11.8 89 | 33.3 99 | 7.78 88 | 6.05 91 | 27.2 82 | 3.90 93 | 9.67 94 | 13.8 104 | 5.74 74 | 14.0 106 | 41.8 112 | 11.7 99 | 6.86 105 | 9.72 90 | 7.61 106 | 4.72 91 | 10.1 92 | 7.78 97 |
HBpMotionGpu [43] | 92.8 | 11.7 101 | 32.8 87 | 6.34 96 | 18.9 108 | 35.4 107 | 22.0 111 | 22.3 108 | 42.7 109 | 31.1 112 | 5.62 83 | 26.7 80 | 3.31 84 | 9.47 90 | 13.0 93 | 8.55 99 | 8.68 71 | 31.2 87 | 5.58 27 | 6.88 107 | 11.9 103 | 0.64 42 | 7.67 107 | 11.4 101 | 15.2 113 |
StereoOF-V1MT [119] | 94.5 | 9.29 90 | 44.8 110 | 4.17 71 | 7.22 88 | 34.5 104 | 3.68 65 | 13.7 94 | 42.6 108 | 3.80 55 | 6.06 92 | 38.5 110 | 3.27 80 | 11.0 110 | 15.1 116 | 9.55 106 | 15.1 110 | 49.9 119 | 14.0 106 | 1.08 46 | 5.51 59 | 5.44 96 | 9.33 114 | 15.5 116 | 9.73 104 |
Shiralkar [42] | 94.8 | 9.76 98 | 46.6 112 | 4.40 77 | 6.53 84 | 31.3 100 | 4.04 75 | 12.7 93 | 37.5 102 | 5.34 66 | 6.47 95 | 32.9 102 | 4.34 98 | 8.33 70 | 11.9 70 | 5.58 72 | 17.4 114 | 43.3 115 | 15.5 111 | 6.82 104 | 8.77 83 | 14.0 112 | 7.36 105 | 15.7 120 | 7.83 98 |
SPSA-learn [13] | 95.0 | 15.7 108 | 48.8 114 | 16.5 109 | 16.6 105 | 35.0 106 | 17.5 106 | 21.4 106 | 42.3 107 | 29.7 108 | 12.6 106 | 37.4 107 | 12.3 109 | 9.64 92 | 12.8 89 | 9.16 103 | 11.0 90 | 37.9 105 | 12.2 101 | 0.98 40 | 3.88 28 | 0.05 13 | 8.38 111 | 11.6 103 | 15.2 113 |
Filter Flow [19] | 97.0 | 14.6 105 | 38.2 105 | 8.96 105 | 12.4 99 | 34.6 105 | 11.3 98 | 20.2 105 | 38.3 103 | 30.1 110 | 19.2 113 | 43.4 114 | 18.6 114 | 10.0 98 | 13.4 97 | 9.43 105 | 10.3 87 | 31.4 88 | 9.08 88 | 8.21 114 | 19.6 123 | 0.79 45 | 3.72 82 | 6.85 61 | 3.41 65 |
Modified CLG [34] | 97.2 | 15.7 108 | 43.7 107 | 12.2 106 | 19.1 109 | 33.3 103 | 23.7 112 | 25.1 112 | 47.4 112 | 35.6 118 | 13.2 107 | 35.5 105 | 11.1 107 | 10.7 107 | 14.4 109 | 9.36 104 | 7.26 41 | 35.8 101 | 6.19 41 | 1.66 66 | 5.21 51 | 6.43 99 | 5.94 99 | 13.8 113 | 7.73 96 |
2D-CLG [1] | 98.5 | 24.4 116 | 51.8 117 | 19.4 113 | 27.4 118 | 38.7 112 | 33.8 120 | 34.6 119 | 57.7 118 | 42.2 125 | 33.4 123 | 57.1 124 | 32.9 122 | 9.64 92 | 12.2 79 | 11.0 111 | 11.2 93 | 40.2 109 | 12.8 103 | 0.31 7 | 2.62 7 | 0.25 29 | 6.33 100 | 13.7 111 | 7.33 95 |
GraphCuts [14] | 98.5 | 12.6 103 | 36.1 93 | 5.46 94 | 14.7 104 | 39.4 113 | 12.5 99 | 17.8 103 | 35.6 100 | 29.1 107 | 6.86 97 | 33.7 104 | 4.15 94 | 9.33 88 | 12.6 84 | 8.69 101 | 23.0 120 | 31.6 89 | 15.5 111 | 3.52 84 | 7.38 80 | 11.7 110 | 5.33 93 | 9.87 91 | 8.75 102 |
IAOF2 [51] | 98.5 | 8.72 87 | 30.9 79 | 5.32 92 | 13.9 102 | 31.1 99 | 15.4 103 | 14.1 96 | 33.0 97 | 18.2 98 | 30.8 121 | 42.2 113 | 36.4 123 | 9.74 95 | 13.8 104 | 6.09 81 | 12.0 98 | 33.4 95 | 7.96 78 | 7.92 113 | 13.9 113 | 7.49 105 | 5.69 97 | 10.6 97 | 4.51 78 |
BlockOverlap [61] | 101.5 | 12.3 102 | 29.2 71 | 8.49 104 | 13.7 101 | 29.6 96 | 15.3 102 | 16.2 102 | 32.5 94 | 20.0 99 | 8.87 104 | 27.4 85 | 7.62 104 | 10.9 109 | 13.4 97 | 12.5 114 | 13.3 104 | 29.1 78 | 10.3 94 | 11.8 121 | 14.4 116 | 23.8 122 | 10.6 116 | 8.92 80 | 24.8 120 |
IAOF [50] | 103.0 | 14.7 106 | 37.8 103 | 14.8 108 | 17.3 107 | 33.2 102 | 18.7 107 | 22.7 109 | 44.3 110 | 23.3 102 | 20.9 115 | 38.7 111 | 24.5 118 | 9.60 91 | 13.3 96 | 8.28 97 | 13.0 102 | 38.8 107 | 7.37 75 | 4.20 91 | 7.90 82 | 2.59 77 | 14.5 121 | 13.4 110 | 32.0 125 |
Black & Anandan [4] | 104.1 | 15.1 107 | 45.4 111 | 18.1 112 | 16.6 105 | 36.3 108 | 16.9 105 | 23.3 110 | 44.9 111 | 27.8 105 | 13.5 109 | 38.1 109 | 13.1 110 | 11.1 112 | 15.7 117 | 7.97 93 | 11.6 97 | 39.6 108 | 11.0 97 | 5.17 98 | 9.06 87 | 2.27 73 | 7.28 104 | 12.3 106 | 10.2 105 |
2bit-BM-tele [98] | 104.9 | 20.3 112 | 39.1 106 | 26.1 117 | 8.84 95 | 26.8 85 | 9.29 95 | 11.1 87 | 30.7 88 | 7.60 86 | 8.06 102 | 29.9 95 | 5.91 103 | 11.0 110 | 13.7 102 | 11.8 113 | 18.0 115 | 37.1 103 | 19.8 117 | 17.1 125 | 20.4 125 | 30.8 125 | 6.54 101 | 11.7 104 | 11.8 107 |
UnFlow [129] | 105.0 | 45.7 126 | 58.8 118 | 25.7 116 | 28.2 119 | 44.0 115 | 31.2 119 | 38.6 125 | 68.3 127 | 37.0 120 | 19.4 114 | 46.0 115 | 16.6 113 | 13.8 121 | 14.9 115 | 18.2 121 | 20.9 118 | 49.2 118 | 23.5 119 | 2.86 79 | 6.76 74 | 0.22 27 | 3.12 70 | 10.4 94 | 2.27 36 |
GroupFlow [9] | 105.8 | 22.9 115 | 47.1 113 | 26.7 119 | 28.4 120 | 50.0 121 | 30.8 118 | 25.4 113 | 52.4 114 | 30.6 111 | 9.32 105 | 29.6 94 | 8.14 105 | 10.7 107 | 13.4 97 | 7.16 89 | 23.0 120 | 46.3 116 | 27.8 123 | 1.56 64 | 5.72 64 | 2.76 79 | 8.00 109 | 12.5 107 | 15.3 115 |
Nguyen [33] | 106.0 | 20.0 111 | 44.7 109 | 17.4 111 | 39.5 124 | 37.5 110 | 52.5 125 | 34.0 118 | 56.0 117 | 38.8 121 | 35.6 124 | 47.9 117 | 41.1 124 | 12.1 114 | 14.3 107 | 16.5 119 | 12.0 98 | 37.8 104 | 13.8 104 | 1.37 58 | 4.27 33 | 0.71 43 | 11.6 119 | 14.5 115 | 20.8 119 |
SILK [79] | 110.8 | 26.9 117 | 51.7 116 | 36.6 123 | 22.3 113 | 45.5 117 | 24.5 113 | 28.8 114 | 54.7 116 | 34.2 114 | 18.4 112 | 41.6 112 | 15.8 112 | 13.1 118 | 16.5 118 | 16.1 118 | 19.1 117 | 47.8 117 | 19.3 116 | 2.87 80 | 4.22 31 | 6.53 100 | 15.9 122 | 19.1 122 | 25.8 121 |
Heeger++ [104] | 111.8 | 42.8 124 | 66.4 128 | 26.2 118 | 25.0 116 | 60.7 128 | 19.8 110 | 38.4 124 | 66.9 124 | 28.0 106 | 23.5 117 | 49.3 118 | 19.7 115 | 10.6 106 | 13.4 97 | 8.12 94 | 40.8 127 | 67.2 129 | 45.1 127 | 2.04 72 | 10.9 95 | 1.70 64 | 11.2 117 | 15.6 117 | 12.8 109 |
Horn & Schunck [3] | 113.2 | 19.9 110 | 61.0 122 | 23.3 114 | 19.4 110 | 44.3 116 | 19.1 108 | 29.5 115 | 58.8 120 | 34.9 116 | 21.0 116 | 49.9 119 | 21.2 116 | 12.3 115 | 16.5 118 | 10.8 110 | 17.3 113 | 50.6 121 | 18.0 114 | 7.23 110 | 11.9 103 | 2.34 74 | 13.4 120 | 22.2 124 | 14.9 112 |
Periodicity [78] | 116.8 | 30.6 120 | 48.8 114 | 16.7 110 | 24.1 114 | 49.8 119 | 26.2 115 | 39.1 126 | 54.5 115 | 39.5 122 | 13.6 110 | 47.1 116 | 12.0 108 | 37.5 129 | 48.2 129 | 33.6 128 | 38.5 126 | 66.9 128 | 36.0 126 | 2.02 71 | 10.8 93 | 8.18 107 | 20.8 125 | 35.9 128 | 30.1 123 |
TI-DOFE [24] | 117.5 | 44.7 125 | 66.3 127 | 66.5 128 | 44.2 126 | 50.5 122 | 54.8 127 | 43.5 128 | 72.0 128 | 44.7 127 | 48.6 126 | 63.3 125 | 54.0 126 | 13.6 120 | 17.7 122 | 15.1 117 | 17.2 111 | 50.3 120 | 19.0 115 | 3.07 82 | 5.50 58 | 2.93 82 | 21.5 126 | 24.7 126 | 33.9 126 |
FFV1MT [106] | 117.5 | 39.5 122 | 59.3 119 | 25.4 115 | 21.8 112 | 56.3 127 | 19.1 108 | 38.0 123 | 67.0 125 | 34.9 116 | 24.3 118 | 55.7 123 | 22.2 117 | 17.7 125 | 18.9 125 | 25.5 126 | 41.8 128 | 66.3 127 | 45.5 128 | 3.73 86 | 12.9 110 | 6.35 98 | 11.2 117 | 15.6 117 | 12.8 109 |
SLK [47] | 119.0 | 28.9 119 | 63.3 125 | 36.4 122 | 42.3 125 | 54.0 126 | 52.8 126 | 36.6 121 | 67.7 126 | 42.5 126 | 51.4 127 | 54.3 122 | 60.0 128 | 14.5 123 | 16.7 120 | 20.8 124 | 21.5 119 | 53.4 125 | 24.1 120 | 3.92 89 | 6.27 70 | 5.91 97 | 21.7 127 | 23.7 125 | 31.5 124 |
Adaptive flow [45] | 121.8 | 49.6 127 | 62.1 123 | 66.8 129 | 37.4 122 | 46.5 118 | 43.1 122 | 34.9 120 | 58.6 119 | 41.7 124 | 27.3 120 | 53.5 121 | 28.7 119 | 16.1 124 | 18.2 124 | 17.6 120 | 25.3 124 | 52.9 123 | 25.1 122 | 45.4 128 | 38.1 128 | 74.4 127 | 9.25 113 | 14.4 114 | 13.9 111 |
PGAM+LK [55] | 122.1 | 35.2 121 | 65.7 126 | 44.1 125 | 31.5 121 | 51.1 123 | 36.1 121 | 30.9 116 | 60.0 122 | 36.8 119 | 33.0 122 | 72.3 128 | 32.7 121 | 13.8 121 | 14.4 109 | 22.6 125 | 24.6 122 | 53.2 124 | 24.6 121 | 27.1 126 | 32.6 127 | 26.2 123 | 17.0 123 | 20.4 123 | 28.4 122 |
FOLKI [16] | 122.3 | 27.4 118 | 59.9 120 | 40.6 124 | 37.4 122 | 51.5 124 | 46.6 123 | 32.4 117 | 61.6 123 | 34.2 114 | 26.3 119 | 50.6 120 | 30.2 120 | 18.2 127 | 19.7 126 | 26.3 127 | 24.6 122 | 56.6 126 | 28.8 124 | 10.3 119 | 13.9 113 | 26.7 124 | 27.1 128 | 26.9 127 | 45.3 128 |
HCIC-L [99] | 122.8 | 51.6 128 | 60.9 121 | 30.9 120 | 58.4 129 | 53.4 125 | 73.0 129 | 39.8 127 | 50.8 113 | 52.8 129 | 63.4 128 | 71.0 127 | 69.9 129 | 18.1 126 | 20.6 127 | 20.5 123 | 29.9 125 | 43.2 113 | 34.1 125 | 73.0 129 | 62.0 129 | 76.4 128 | 7.45 106 | 12.5 107 | 8.87 103 |
Pyramid LK [2] | 125.5 | 41.0 123 | 62.5 124 | 66.4 127 | 47.2 127 | 49.9 120 | 59.7 128 | 37.5 122 | 59.5 121 | 45.5 128 | 43.8 125 | 65.1 126 | 49.5 125 | 36.5 128 | 43.8 128 | 42.6 129 | 43.3 129 | 52.8 122 | 45.9 129 | 11.8 121 | 20.2 124 | 20.7 119 | 40.0 129 | 46.5 129 | 59.5 129 |
AdaConv-v1 [126] | 130.0 | 99.3 130 | 97.8 130 | 99.8 130 | 99.9 130 | 100.0 130 | 99.8 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.5 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.1 130 | 98.9 130 | 99.7 130 | 98.5 130 | 93.0 130 | 100.0 130 | 99.9 130 | 99.9 130 | 99.9 130 |
SepConv-v1 [127] | 130.0 | 99.3 130 | 97.8 130 | 99.8 130 | 99.9 130 | 100.0 130 | 99.8 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.5 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.9 130 | 99.1 130 | 98.9 130 | 99.7 130 | 98.5 130 | 93.0 130 | 100.0 130 | 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. |