Optical flow evaluation results |
Statistics:
Average
SD
R0.5
R1.0
R2.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
A90 normalized interpolation error |
avg. |
Mequon (Hidden texture) im0 GT im1 |
Schefflera (Hidden texture) im0 GT im1 |
Urban (Synthetic) im0 GT im1 |
Teddy (Stereo) im0 GT im1 |
Backyard (High-speed camera) im0 GT im1 |
Basketball (High-speed camera) im0 GT im1 |
Dumptruck (High-speed camera) im0 GT im1 |
Evergreen (High-speed camera) im0 GT im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
PMMST [114] | 6.5 | 0.89 7 | 0.99 2 | 0.96 14 | 0.84 30 | 1.10 13 | 0.87 5 | 0.86 2 | 0.97 3 | 0.84 1 | 1.41 2 | 1.37 2 | 1.83 3 | 1.45 2 | 1.41 6 | 1.67 17 | 1.40 4 | 1.32 2 | 1.49 10 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
MDP-Flow2 [68] | 6.7 | 0.88 2 | 0.99 2 | 0.95 2 | 0.82 8 | 1.09 11 | 0.87 5 | 0.86 2 | 0.98 5 | 0.84 1 | 1.41 2 | 1.38 7 | 1.83 3 | 1.45 2 | 1.40 2 | 1.67 17 | 1.41 9 | 1.41 20 | 1.50 29 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
PH-Flow [101] | 9.2 | 0.89 7 | 1.04 12 | 0.96 14 | 0.80 1 | 1.03 5 | 0.87 5 | 0.86 2 | 0.99 8 | 0.84 1 | 1.41 2 | 1.37 2 | 1.83 3 | 1.45 2 | 1.41 6 | 1.66 6 | 1.41 9 | 1.59 83 | 1.49 10 | 0.86 1 | 1.16 17 | 1.01 3 | 0.93 8 | 1.23 10 | 0.93 5 |
NNF-Local [87] | 9.8 | 0.88 2 | 1.00 4 | 0.95 2 | 0.80 1 | 1.02 2 | 0.86 1 | 0.86 2 | 0.98 5 | 0.84 1 | 1.43 21 | 1.46 58 | 1.83 3 | 1.45 2 | 1.40 2 | 1.66 6 | 1.41 9 | 1.50 55 | 1.50 29 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.23 10 | 0.93 5 |
CombBMOF [113] | 11.0 | 0.89 7 | 1.00 4 | 0.95 2 | 0.81 5 | 1.08 8 | 0.87 5 | 0.88 43 | 1.02 13 | 0.87 68 | 1.42 17 | 1.40 17 | 1.83 3 | 1.46 8 | 1.41 6 | 1.66 6 | 1.41 9 | 1.36 8 | 1.49 10 | 0.86 1 | 1.16 17 | 1.01 3 | 0.91 1 | 1.20 3 | 0.92 1 |
NN-field [71] | 12.3 | 0.89 7 | 1.04 12 | 0.95 2 | 0.80 1 | 1.02 2 | 0.86 1 | 0.88 43 | 0.97 3 | 0.84 1 | 1.44 38 | 1.49 79 | 1.83 3 | 1.45 2 | 1.40 2 | 1.66 6 | 1.41 9 | 1.44 31 | 1.50 29 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.22 5 | 0.93 5 |
IROF++ [58] | 12.5 | 0.89 7 | 1.06 25 | 0.96 14 | 0.83 17 | 1.12 18 | 0.87 5 | 0.87 8 | 1.04 25 | 0.84 1 | 1.41 2 | 1.37 2 | 1.84 22 | 1.46 8 | 1.42 14 | 1.66 6 | 1.41 9 | 1.39 12 | 1.49 10 | 0.87 25 | 1.18 33 | 1.01 3 | 0.93 8 | 1.25 22 | 0.93 5 |
nLayers [57] | 14.2 | 0.89 7 | 1.02 9 | 0.96 14 | 0.82 8 | 1.08 8 | 0.87 5 | 0.87 8 | 0.96 1 | 0.84 1 | 1.41 2 | 1.39 11 | 1.84 22 | 1.47 36 | 1.43 31 | 1.67 17 | 1.42 55 | 1.51 58 | 1.50 29 | 0.86 1 | 1.13 1 | 1.01 3 | 0.93 8 | 1.22 5 | 0.92 1 |
Layers++ [37] | 14.4 | 0.89 7 | 1.05 19 | 0.96 14 | 0.81 5 | 1.02 2 | 0.87 5 | 0.87 8 | 1.02 13 | 0.84 1 | 1.41 2 | 1.39 11 | 1.83 3 | 1.47 36 | 1.43 31 | 1.67 17 | 1.42 55 | 1.53 64 | 1.50 29 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.22 5 | 0.93 5 |
NNF-EAC [103] | 18.0 | 0.91 55 | 1.05 19 | 0.96 14 | 0.84 30 | 1.15 26 | 0.87 5 | 0.87 8 | 1.01 12 | 0.84 1 | 1.44 38 | 1.40 17 | 1.89 100 | 1.46 8 | 1.41 6 | 1.67 17 | 1.40 4 | 1.34 7 | 1.49 10 | 0.86 1 | 1.16 17 | 1.01 3 | 0.93 8 | 1.25 22 | 0.93 5 |
FMOF [94] | 18.4 | 0.91 55 | 1.09 46 | 0.96 14 | 0.82 8 | 1.08 8 | 0.87 5 | 0.88 43 | 1.02 13 | 0.85 52 | 1.44 38 | 1.43 35 | 1.83 3 | 1.46 8 | 1.42 14 | 1.67 17 | 1.41 9 | 1.44 31 | 1.49 10 | 0.86 1 | 1.14 2 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
TV-L1-MCT [64] | 18.5 | 0.91 55 | 1.12 72 | 0.96 14 | 0.85 37 | 1.22 42 | 0.87 5 | 0.87 8 | 1.04 25 | 0.84 1 | 1.41 2 | 1.39 11 | 1.83 3 | 1.46 8 | 1.43 31 | 1.66 6 | 1.41 9 | 1.39 12 | 1.50 29 | 0.87 25 | 1.18 33 | 1.01 3 | 0.92 3 | 1.22 5 | 0.93 5 |
Sparse-NonSparse [56] | 20.2 | 0.89 7 | 1.06 25 | 0.96 14 | 0.82 8 | 1.11 15 | 0.87 5 | 0.87 8 | 1.03 21 | 0.84 1 | 1.43 21 | 1.40 17 | 1.84 22 | 1.46 8 | 1.42 14 | 1.67 17 | 1.43 64 | 1.55 75 | 1.51 70 | 0.86 1 | 1.17 23 | 1.01 3 | 0.93 8 | 1.26 33 | 0.93 5 |
2DHMM-SAS [92] | 21.5 | 0.90 44 | 1.10 54 | 0.96 14 | 0.88 60 | 1.28 54 | 0.87 5 | 0.87 8 | 1.04 25 | 0.84 1 | 1.42 17 | 1.39 11 | 1.84 22 | 1.46 8 | 1.42 14 | 1.67 17 | 1.41 9 | 1.43 29 | 1.49 10 | 0.86 1 | 1.17 23 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
FlowFields [110] | 21.9 | 0.89 7 | 1.08 35 | 0.96 14 | 0.83 17 | 1.15 26 | 0.87 5 | 0.87 8 | 1.10 52 | 0.84 1 | 1.44 38 | 1.46 58 | 1.85 49 | 1.47 36 | 1.42 14 | 1.67 17 | 1.41 9 | 1.52 59 | 1.50 29 | 0.86 1 | 1.16 17 | 1.01 3 | 0.92 3 | 1.25 22 | 0.93 5 |
S2F-IF [123] | 21.9 | 0.89 7 | 1.08 35 | 0.95 2 | 0.83 17 | 1.13 20 | 0.87 5 | 0.87 8 | 1.09 51 | 0.84 1 | 1.43 21 | 1.44 37 | 1.83 3 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.52 59 | 1.50 29 | 0.87 25 | 1.19 48 | 1.01 3 | 0.92 3 | 1.24 13 | 0.93 5 |
ComponentFusion [96] | 22.0 | 0.89 7 | 1.04 12 | 0.96 14 | 0.82 8 | 1.12 18 | 0.86 1 | 0.87 8 | 1.07 42 | 0.84 1 | 1.41 2 | 1.40 17 | 1.83 3 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.42 27 | 1.50 29 | 0.87 25 | 1.25 91 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
AGIF+OF [85] | 23.9 | 0.89 7 | 1.06 25 | 0.95 2 | 0.83 17 | 1.14 24 | 0.87 5 | 0.87 8 | 1.00 9 | 0.84 1 | 1.41 2 | 1.37 2 | 1.83 3 | 1.48 90 | 1.44 66 | 1.67 17 | 1.43 64 | 1.63 97 | 1.49 10 | 0.87 25 | 1.15 10 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
COFM [59] | 24.3 | 0.89 7 | 1.04 12 | 0.96 14 | 0.83 17 | 1.11 15 | 0.87 5 | 0.87 8 | 1.00 9 | 0.84 1 | 1.41 2 | 1.38 7 | 1.82 1 | 1.46 8 | 1.42 14 | 1.65 1 | 1.41 9 | 1.66 103 | 1.47 2 | 0.87 25 | 1.18 33 | 1.03 100 | 0.95 71 | 1.25 22 | 0.94 97 |
FlowFields+ [130] | 25.5 | 0.89 7 | 1.08 35 | 0.96 14 | 0.83 17 | 1.13 20 | 0.88 42 | 0.87 8 | 1.10 52 | 0.84 1 | 1.43 21 | 1.45 46 | 1.84 22 | 1.47 36 | 1.43 31 | 1.68 57 | 1.42 55 | 1.54 69 | 1.50 29 | 0.86 1 | 1.16 17 | 1.01 3 | 0.92 3 | 1.25 22 | 0.93 5 |
LSM [39] | 26.3 | 0.89 7 | 1.09 46 | 0.96 14 | 0.83 17 | 1.13 20 | 0.87 5 | 0.87 8 | 1.07 42 | 0.84 1 | 1.43 21 | 1.41 27 | 1.84 22 | 1.47 36 | 1.43 31 | 1.67 17 | 1.43 64 | 1.57 79 | 1.50 29 | 0.87 25 | 1.18 33 | 1.00 1 | 0.94 39 | 1.27 42 | 0.93 5 |
ProbFlowFields [128] | 26.4 | 0.89 7 | 1.10 54 | 0.96 14 | 0.82 8 | 1.11 15 | 0.87 5 | 0.86 2 | 1.02 13 | 0.84 1 | 1.44 38 | 1.44 37 | 1.85 49 | 1.47 36 | 1.43 31 | 1.69 90 | 1.43 64 | 1.59 83 | 1.51 70 | 0.86 1 | 1.14 2 | 1.01 3 | 0.91 1 | 1.21 4 | 0.93 5 |
WLIF-Flow [93] | 27.5 | 0.89 7 | 1.05 19 | 0.96 14 | 0.83 17 | 1.15 26 | 0.87 5 | 0.87 8 | 1.02 13 | 0.84 1 | 1.43 21 | 1.38 7 | 1.87 82 | 1.46 8 | 1.42 14 | 1.68 57 | 1.45 95 | 1.62 95 | 1.52 91 | 0.86 1 | 1.15 10 | 1.01 3 | 0.94 39 | 1.25 22 | 0.93 5 |
LME [70] | 28.1 | 0.88 2 | 1.00 4 | 0.95 2 | 0.85 37 | 1.15 26 | 0.91 85 | 0.87 8 | 1.12 60 | 0.84 1 | 1.41 2 | 1.40 17 | 1.84 22 | 1.48 90 | 1.45 92 | 1.71 115 | 1.41 9 | 1.47 44 | 1.50 29 | 0.86 1 | 1.14 2 | 1.00 1 | 0.93 8 | 1.24 13 | 0.93 5 |
RNLOD-Flow [121] | 28.6 | 0.89 7 | 1.07 30 | 0.96 14 | 0.86 47 | 1.27 53 | 0.87 5 | 0.87 8 | 1.08 46 | 0.84 1 | 1.41 2 | 1.39 11 | 1.83 3 | 1.47 36 | 1.44 66 | 1.67 17 | 1.43 64 | 1.57 79 | 1.50 29 | 0.86 1 | 1.15 10 | 1.01 3 | 0.95 71 | 1.30 79 | 0.93 5 |
HAST [109] | 28.8 | 0.89 7 | 1.01 7 | 0.96 14 | 0.82 8 | 1.09 11 | 0.87 5 | 0.88 43 | 1.08 46 | 0.86 62 | 1.40 1 | 1.36 1 | 1.83 3 | 1.46 8 | 1.44 66 | 1.66 6 | 1.43 64 | 1.66 103 | 1.48 5 | 0.87 25 | 1.19 48 | 1.01 3 | 0.95 71 | 1.30 79 | 0.93 5 |
DeepFlow2 [108] | 29.9 | 0.90 44 | 1.07 30 | 0.96 14 | 0.87 55 | 1.29 58 | 0.89 68 | 0.87 8 | 1.15 68 | 0.84 1 | 1.44 38 | 1.45 46 | 1.85 49 | 1.46 8 | 1.41 6 | 1.69 90 | 1.41 9 | 1.33 3 | 1.51 70 | 0.86 1 | 1.17 23 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
PGM-C [120] | 30.3 | 0.89 7 | 1.10 54 | 0.96 14 | 0.84 30 | 1.17 34 | 0.88 42 | 0.88 43 | 1.15 68 | 0.84 1 | 1.44 38 | 1.48 71 | 1.84 22 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.45 35 | 1.50 29 | 0.87 25 | 1.18 33 | 1.01 3 | 0.93 8 | 1.26 33 | 0.93 5 |
Ramp [62] | 30.5 | 0.90 44 | 1.10 54 | 0.96 14 | 0.83 17 | 1.13 20 | 0.87 5 | 0.87 8 | 1.03 21 | 0.84 1 | 1.41 2 | 1.39 11 | 1.84 22 | 1.47 36 | 1.43 31 | 1.67 17 | 1.45 95 | 1.65 101 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
OFLAF [77] | 32.5 | 0.88 2 | 1.01 7 | 0.95 2 | 0.81 5 | 1.04 6 | 0.87 5 | 0.87 8 | 1.04 25 | 0.84 1 | 1.41 2 | 1.38 7 | 1.83 3 | 1.47 36 | 1.44 66 | 1.68 57 | 1.43 64 | 1.68 109 | 1.50 29 | 0.88 77 | 1.26 95 | 1.01 3 | 0.96 86 | 1.30 79 | 0.93 5 |
Classic+NL [31] | 32.7 | 0.91 55 | 1.11 62 | 0.96 14 | 0.83 17 | 1.14 24 | 0.87 5 | 0.87 8 | 1.03 21 | 0.84 1 | 1.43 21 | 1.41 27 | 1.85 49 | 1.47 36 | 1.43 31 | 1.67 17 | 1.44 81 | 1.58 82 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
Second-order prior [8] | 32.9 | 0.90 44 | 1.07 30 | 0.96 14 | 0.92 79 | 1.39 80 | 0.88 42 | 0.90 88 | 1.26 103 | 0.87 68 | 1.44 38 | 1.44 37 | 1.83 3 | 1.46 8 | 1.41 6 | 1.67 17 | 1.40 4 | 1.39 12 | 1.49 10 | 0.87 25 | 1.17 23 | 1.01 3 | 0.93 8 | 1.27 42 | 0.93 5 |
MDP-Flow [26] | 33.2 | 0.89 7 | 1.04 12 | 0.96 14 | 0.83 17 | 1.15 26 | 0.88 42 | 0.87 8 | 1.04 25 | 0.84 1 | 1.46 68 | 1.48 71 | 1.85 49 | 1.46 8 | 1.42 14 | 1.68 57 | 1.44 81 | 1.75 119 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.93 8 | 1.26 33 | 0.93 5 |
SRR-TVOF-NL [91] | 33.4 | 0.91 55 | 1.08 35 | 0.96 14 | 0.88 60 | 1.31 68 | 0.89 68 | 0.88 43 | 1.10 52 | 0.84 1 | 1.43 21 | 1.40 17 | 1.82 1 | 1.46 8 | 1.44 66 | 1.67 17 | 1.40 4 | 1.46 40 | 1.47 2 | 0.87 25 | 1.17 23 | 1.01 3 | 0.96 86 | 1.31 87 | 0.93 5 |
Aniso. Huber-L1 [22] | 33.6 | 0.91 55 | 1.12 72 | 0.98 77 | 0.94 87 | 1.42 90 | 0.89 68 | 0.88 43 | 1.07 42 | 0.84 1 | 1.44 38 | 1.43 35 | 1.84 22 | 1.46 8 | 1.41 6 | 1.67 17 | 1.40 4 | 1.41 20 | 1.48 5 | 0.87 25 | 1.17 23 | 1.01 3 | 0.94 39 | 1.25 22 | 0.93 5 |
IROF-TV [53] | 33.9 | 0.91 55 | 1.12 72 | 0.96 14 | 0.83 17 | 1.15 26 | 0.87 5 | 0.88 43 | 1.21 90 | 0.84 1 | 1.43 21 | 1.42 32 | 1.86 71 | 1.47 36 | 1.44 66 | 1.69 90 | 1.41 9 | 1.48 49 | 1.48 5 | 0.87 25 | 1.19 48 | 1.01 3 | 0.93 8 | 1.25 22 | 0.93 5 |
DF-Auto [115] | 34.1 | 0.91 55 | 1.05 19 | 0.98 77 | 0.92 79 | 1.30 64 | 0.96 96 | 0.87 8 | 1.02 13 | 0.84 1 | 1.44 38 | 1.45 46 | 1.84 22 | 1.46 8 | 1.42 14 | 1.68 57 | 1.41 9 | 1.37 9 | 1.50 29 | 0.87 25 | 1.20 61 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
FESL [72] | 35.3 | 0.91 55 | 1.08 35 | 0.96 14 | 0.84 30 | 1.15 26 | 0.87 5 | 0.87 8 | 1.05 33 | 0.84 1 | 1.43 21 | 1.41 27 | 1.84 22 | 1.47 36 | 1.44 66 | 1.68 57 | 1.44 81 | 1.64 98 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
FC-2Layers-FF [74] | 35.8 | 0.90 44 | 1.09 46 | 0.96 14 | 0.80 1 | 1.01 1 | 0.88 42 | 0.87 8 | 1.04 25 | 0.84 1 | 1.42 17 | 1.40 17 | 1.85 49 | 1.47 36 | 1.44 66 | 1.68 57 | 1.45 95 | 1.68 109 | 1.51 70 | 0.87 25 | 1.19 48 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
CPM-Flow [116] | 35.8 | 0.90 44 | 1.11 62 | 0.96 14 | 0.84 30 | 1.17 34 | 0.88 42 | 0.88 43 | 1.11 57 | 0.84 1 | 1.46 68 | 1.51 97 | 1.85 49 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.41 20 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.93 8 | 1.25 22 | 0.93 5 |
Efficient-NL [60] | 36.4 | 0.90 44 | 1.08 35 | 0.96 14 | 0.85 37 | 1.22 42 | 0.87 5 | 0.89 70 | 1.05 33 | 0.87 68 | 1.43 21 | 1.41 27 | 1.83 3 | 1.46 8 | 1.42 14 | 1.67 17 | 1.42 55 | 1.61 93 | 1.49 10 | 0.87 25 | 1.21 72 | 1.01 3 | 0.96 86 | 1.31 87 | 0.93 5 |
S2D-Matching [84] | 37.5 | 0.91 55 | 1.11 62 | 0.96 14 | 0.87 55 | 1.29 58 | 0.87 5 | 0.87 8 | 1.02 13 | 0.84 1 | 1.43 21 | 1.40 17 | 1.87 82 | 1.47 36 | 1.44 66 | 1.67 17 | 1.44 81 | 1.67 107 | 1.51 70 | 0.87 25 | 1.16 17 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
DeepFlow [86] | 38.2 | 0.89 7 | 1.06 25 | 0.96 14 | 0.88 60 | 1.29 58 | 0.90 84 | 0.88 43 | 1.19 87 | 0.85 52 | 1.46 68 | 1.46 58 | 1.85 49 | 1.46 8 | 1.42 14 | 1.69 90 | 1.42 55 | 1.33 3 | 1.53 103 | 0.86 1 | 1.15 10 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
Brox et al. [5] | 38.5 | 0.90 44 | 1.07 30 | 0.96 14 | 0.89 65 | 1.30 64 | 0.89 68 | 0.89 70 | 1.22 96 | 0.87 68 | 1.44 38 | 1.42 32 | 1.84 22 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.45 35 | 1.50 29 | 0.87 25 | 1.20 61 | 1.01 3 | 0.93 8 | 1.24 13 | 0.93 5 |
Kuang [131] | 38.9 | 0.89 7 | 1.11 62 | 0.96 14 | 0.85 37 | 1.21 41 | 0.88 42 | 0.88 43 | 1.15 68 | 0.85 52 | 1.44 38 | 1.48 71 | 1.86 71 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.45 35 | 1.49 10 | 0.87 25 | 1.22 77 | 1.02 73 | 0.93 8 | 1.25 22 | 0.93 5 |
AggregFlow [97] | 39.0 | 0.92 90 | 1.13 82 | 0.97 72 | 0.87 55 | 1.25 46 | 0.89 68 | 0.86 2 | 1.00 9 | 0.84 1 | 1.44 38 | 1.44 37 | 1.84 22 | 1.47 36 | 1.42 14 | 1.68 57 | 1.44 81 | 1.41 20 | 1.54 109 | 0.87 25 | 1.18 33 | 1.01 3 | 0.93 8 | 1.25 22 | 0.93 5 |
p-harmonic [29] | 39.2 | 0.89 7 | 1.07 30 | 0.96 14 | 0.93 83 | 1.41 84 | 0.89 68 | 0.88 43 | 1.22 96 | 0.87 68 | 1.46 68 | 1.48 71 | 1.85 49 | 1.47 36 | 1.43 31 | 1.67 17 | 1.41 9 | 1.40 16 | 1.50 29 | 0.87 25 | 1.19 48 | 1.01 3 | 0.93 8 | 1.26 33 | 0.93 5 |
EPPM w/o HM [88] | 40.2 | 0.88 2 | 1.02 9 | 0.95 2 | 0.85 37 | 1.22 42 | 0.87 5 | 0.90 88 | 1.26 103 | 0.87 68 | 1.43 21 | 1.45 46 | 1.84 22 | 1.46 8 | 1.43 31 | 1.67 17 | 1.43 64 | 1.54 69 | 1.51 70 | 0.87 25 | 1.22 77 | 1.02 73 | 0.94 39 | 1.27 42 | 0.93 5 |
DPOF [18] | 40.3 | 0.91 55 | 1.18 106 | 0.97 72 | 0.82 8 | 1.06 7 | 0.88 42 | 0.89 70 | 1.05 33 | 0.87 68 | 1.44 38 | 1.45 46 | 1.85 49 | 1.46 8 | 1.42 14 | 1.67 17 | 1.41 9 | 1.49 51 | 1.49 10 | 0.87 25 | 1.18 33 | 1.02 73 | 0.95 71 | 1.28 58 | 0.93 5 |
Classic+CPF [83] | 40.6 | 0.90 44 | 1.08 35 | 0.96 14 | 0.84 30 | 1.16 33 | 0.87 5 | 0.87 8 | 1.04 25 | 0.84 1 | 1.41 2 | 1.37 2 | 1.83 3 | 1.49 106 | 1.46 108 | 1.67 17 | 1.44 81 | 1.72 116 | 1.50 29 | 0.88 77 | 1.21 72 | 1.01 3 | 0.95 71 | 1.31 87 | 0.93 5 |
EpicFlow [102] | 41.0 | 0.89 7 | 1.10 54 | 0.96 14 | 0.86 47 | 1.29 58 | 0.88 42 | 0.88 43 | 1.15 68 | 0.85 52 | 1.45 59 | 1.50 89 | 1.85 49 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.52 59 | 1.50 29 | 0.87 25 | 1.20 61 | 1.01 3 | 0.93 8 | 1.30 79 | 0.93 5 |
ComplOF-FED-GPU [35] | 41.2 | 0.89 7 | 1.10 54 | 0.96 14 | 0.85 37 | 1.25 46 | 0.88 42 | 0.91 94 | 1.18 85 | 0.87 68 | 1.44 38 | 1.47 64 | 1.85 49 | 1.46 8 | 1.43 31 | 1.68 57 | 1.41 9 | 1.49 51 | 1.50 29 | 0.87 25 | 1.20 61 | 1.01 3 | 0.94 39 | 1.29 72 | 0.93 5 |
Sparse Occlusion [54] | 41.2 | 0.91 55 | 1.12 72 | 0.96 14 | 0.89 65 | 1.37 75 | 0.87 5 | 0.87 8 | 1.06 37 | 0.84 1 | 1.44 38 | 1.45 46 | 1.84 22 | 1.47 36 | 1.43 31 | 1.67 17 | 1.43 64 | 1.60 89 | 1.51 70 | 0.87 25 | 1.20 61 | 1.01 3 | 0.95 71 | 1.30 79 | 0.93 5 |
SepConv-v1 [127] | 41.2 | 0.76 1 | 0.94 1 | 0.81 1 | 0.83 17 | 1.19 39 | 0.91 85 | 0.84 1 | 0.98 5 | 0.97 125 | 1.50 99 | 1.44 37 | 1.88 94 | 1.46 8 | 1.40 2 | 1.67 17 | 1.39 1 | 1.22 1 | 1.49 10 | 0.93 124 | 1.20 61 | 1.08 129 | 0.92 3 | 1.12 1 | 1.00 127 |
TC/T-Flow [76] | 41.5 | 0.91 55 | 1.09 46 | 0.96 14 | 0.86 47 | 1.26 50 | 0.87 5 | 0.87 8 | 1.08 46 | 0.84 1 | 1.44 38 | 1.45 46 | 1.85 49 | 1.47 36 | 1.44 66 | 1.68 57 | 1.41 9 | 1.46 40 | 1.50 29 | 0.88 77 | 1.24 87 | 1.02 73 | 0.94 39 | 1.29 72 | 0.93 5 |
ALD-Flow [66] | 43.3 | 0.91 55 | 1.11 62 | 0.98 77 | 0.86 47 | 1.28 54 | 0.89 68 | 0.88 43 | 1.17 81 | 0.84 1 | 1.43 21 | 1.45 46 | 1.86 71 | 1.47 36 | 1.43 31 | 1.69 90 | 1.41 9 | 1.40 16 | 1.51 70 | 0.86 1 | 1.15 10 | 1.01 3 | 0.95 71 | 1.29 72 | 0.93 5 |
PMF [73] | 43.8 | 0.89 7 | 1.02 9 | 0.95 2 | 0.85 37 | 1.18 37 | 0.86 1 | 0.89 70 | 1.21 90 | 0.86 62 | 1.42 17 | 1.40 17 | 1.84 22 | 1.47 36 | 1.44 66 | 1.67 17 | 1.44 81 | 1.45 35 | 1.54 109 | 0.87 25 | 1.19 48 | 1.02 73 | 0.96 86 | 1.32 99 | 0.93 5 |
SIOF [67] | 43.9 | 0.91 55 | 1.13 82 | 0.97 72 | 0.97 99 | 1.47 99 | 0.94 93 | 0.88 43 | 1.12 60 | 0.85 52 | 1.44 38 | 1.46 58 | 1.85 49 | 1.45 2 | 1.41 6 | 1.66 6 | 1.41 9 | 1.41 20 | 1.50 29 | 0.86 1 | 1.17 23 | 1.01 3 | 0.95 71 | 1.30 79 | 0.93 5 |
RFlow [90] | 45.4 | 0.90 44 | 1.11 62 | 0.97 72 | 0.91 74 | 1.41 84 | 0.87 5 | 0.88 43 | 1.15 68 | 0.85 52 | 1.45 59 | 1.49 79 | 1.84 22 | 1.47 36 | 1.43 31 | 1.67 17 | 1.41 9 | 1.47 44 | 1.48 5 | 0.87 25 | 1.22 77 | 1.01 3 | 0.96 86 | 1.31 87 | 0.93 5 |
CLG-TV [48] | 46.3 | 0.91 55 | 1.12 72 | 0.98 77 | 0.93 83 | 1.40 82 | 0.89 68 | 0.89 70 | 1.19 87 | 0.87 68 | 1.45 59 | 1.45 46 | 1.86 71 | 1.46 8 | 1.42 14 | 1.68 57 | 1.41 9 | 1.37 9 | 1.50 29 | 0.87 25 | 1.18 33 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
SuperFlow [81] | 48.4 | 0.91 55 | 1.08 35 | 0.98 77 | 0.92 79 | 1.32 70 | 0.97 99 | 0.89 70 | 1.14 65 | 0.87 68 | 1.46 68 | 1.44 37 | 1.86 71 | 1.47 36 | 1.43 31 | 1.69 90 | 1.39 1 | 1.33 3 | 1.49 10 | 0.87 25 | 1.21 72 | 1.02 73 | 0.93 8 | 1.24 13 | 0.93 5 |
TC-Flow [46] | 48.7 | 0.89 7 | 1.09 46 | 0.96 14 | 0.86 47 | 1.31 68 | 0.88 42 | 0.89 70 | 1.17 81 | 0.84 1 | 1.45 59 | 1.47 64 | 1.87 82 | 1.48 90 | 1.44 66 | 1.68 57 | 1.43 64 | 1.53 64 | 1.51 70 | 0.87 25 | 1.18 33 | 1.01 3 | 0.94 39 | 1.29 72 | 0.93 5 |
TCOF [69] | 51.5 | 0.91 55 | 1.11 62 | 0.96 14 | 0.96 94 | 1.48 101 | 0.89 68 | 0.87 8 | 1.05 33 | 0.84 1 | 1.44 38 | 1.45 46 | 1.86 71 | 1.47 36 | 1.43 31 | 1.67 17 | 1.42 55 | 1.59 83 | 1.49 10 | 0.87 25 | 1.22 77 | 1.01 3 | 0.97 105 | 1.34 107 | 0.94 97 |
OAR-Flow [125] | 52.9 | 0.91 55 | 1.09 46 | 0.97 72 | 0.87 55 | 1.30 64 | 0.89 68 | 0.88 43 | 1.16 78 | 0.84 1 | 1.43 21 | 1.45 46 | 1.84 22 | 1.47 36 | 1.44 66 | 1.69 90 | 1.43 64 | 1.52 59 | 1.51 70 | 0.88 77 | 1.22 77 | 1.02 73 | 0.94 39 | 1.27 42 | 0.93 5 |
SVFilterOh [111] | 53.8 | 0.89 7 | 1.04 12 | 0.96 14 | 0.82 8 | 1.10 13 | 0.88 42 | 0.88 43 | 1.02 13 | 0.87 68 | 1.43 21 | 1.40 17 | 1.89 100 | 1.49 106 | 1.45 92 | 1.71 115 | 1.43 64 | 1.54 69 | 1.50 29 | 0.88 77 | 1.15 10 | 1.04 114 | 0.96 86 | 1.28 58 | 0.95 112 |
IAOF [50] | 54.8 | 0.95 109 | 1.15 93 | 1.01 108 | 1.16 125 | 1.70 130 | 1.00 109 | 0.88 43 | 1.14 65 | 0.87 68 | 1.48 90 | 1.45 46 | 1.85 49 | 1.46 8 | 1.42 14 | 1.67 17 | 1.41 9 | 1.47 44 | 1.49 10 | 0.87 25 | 1.19 48 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
OFH [38] | 55.3 | 0.91 55 | 1.11 62 | 0.96 14 | 0.89 65 | 1.34 72 | 0.88 42 | 0.89 70 | 1.26 103 | 0.85 52 | 1.44 38 | 1.48 71 | 1.84 22 | 1.47 36 | 1.44 66 | 1.67 17 | 1.42 55 | 1.54 69 | 1.50 29 | 0.88 77 | 1.27 96 | 1.02 73 | 0.94 39 | 1.32 99 | 0.93 5 |
LDOF [28] | 55.8 | 0.93 95 | 1.12 72 | 1.00 93 | 0.94 87 | 1.30 64 | 0.97 99 | 0.90 88 | 1.24 102 | 0.87 68 | 1.46 68 | 1.50 89 | 1.87 82 | 1.47 36 | 1.42 14 | 1.68 57 | 1.41 9 | 1.38 11 | 1.50 29 | 0.87 25 | 1.20 61 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
Fusion [6] | 56.4 | 0.89 7 | 1.14 89 | 0.96 14 | 0.85 37 | 1.20 40 | 0.88 42 | 0.88 43 | 1.06 37 | 0.87 68 | 1.47 85 | 1.50 89 | 1.84 22 | 1.47 36 | 1.46 108 | 1.65 1 | 1.41 9 | 1.71 114 | 1.47 2 | 0.89 100 | 1.29 103 | 1.02 73 | 0.99 118 | 1.35 111 | 0.93 5 |
CostFilter [40] | 56.5 | 0.89 7 | 1.05 19 | 0.95 2 | 0.84 30 | 1.17 34 | 0.87 5 | 0.89 70 | 1.27 107 | 0.87 68 | 1.44 38 | 1.44 37 | 1.84 22 | 1.48 90 | 1.45 92 | 1.68 57 | 1.48 111 | 1.46 40 | 1.58 122 | 0.88 77 | 1.22 77 | 1.02 73 | 0.95 71 | 1.33 102 | 0.93 5 |
MLDP_OF [89] | 56.8 | 0.89 7 | 1.06 25 | 0.96 14 | 0.86 47 | 1.25 46 | 0.87 5 | 0.87 8 | 1.06 37 | 0.84 1 | 1.45 59 | 1.42 32 | 1.88 94 | 1.47 36 | 1.44 66 | 1.70 108 | 1.52 125 | 1.66 103 | 1.60 124 | 0.87 25 | 1.20 61 | 1.03 100 | 0.95 71 | 1.29 72 | 0.94 97 |
Modified CLG [34] | 56.9 | 0.91 55 | 1.08 35 | 1.00 93 | 1.04 109 | 1.49 105 | 1.03 114 | 0.90 88 | 1.33 113 | 0.87 68 | 1.46 68 | 1.49 79 | 1.85 49 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.48 49 | 1.50 29 | 0.87 25 | 1.19 48 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
FlowNet2 [122] | 58.0 | 0.98 114 | 1.25 116 | 1.02 111 | 0.92 79 | 1.28 54 | 0.97 99 | 0.89 70 | 1.16 78 | 0.87 68 | 1.45 59 | 1.51 97 | 1.85 49 | 1.48 90 | 1.45 92 | 1.67 17 | 1.41 9 | 1.47 44 | 1.50 29 | 0.87 25 | 1.19 48 | 1.01 3 | 0.93 8 | 1.26 33 | 0.92 1 |
Complementary OF [21] | 58.8 | 0.89 7 | 1.12 72 | 0.96 14 | 0.85 37 | 1.25 46 | 0.88 42 | 0.93 102 | 1.14 65 | 0.87 68 | 1.46 68 | 1.50 89 | 1.86 71 | 1.47 36 | 1.44 66 | 1.67 17 | 1.42 55 | 1.54 69 | 1.50 29 | 0.88 77 | 1.28 98 | 1.02 73 | 0.96 86 | 1.40 120 | 0.93 5 |
Classic++ [32] | 59.1 | 0.91 55 | 1.13 82 | 0.98 77 | 0.89 65 | 1.35 73 | 0.88 42 | 0.89 70 | 1.18 85 | 0.86 62 | 1.47 85 | 1.49 79 | 1.87 82 | 1.47 36 | 1.43 31 | 1.67 17 | 1.46 103 | 1.55 75 | 1.54 109 | 0.87 25 | 1.20 61 | 1.01 3 | 0.94 39 | 1.28 58 | 0.93 5 |
TriFlow [95] | 59.4 | 0.92 90 | 1.19 107 | 0.98 77 | 0.94 87 | 1.39 80 | 0.98 104 | 0.88 43 | 1.17 81 | 0.84 1 | 1.45 59 | 1.47 64 | 1.83 3 | 1.48 90 | 1.45 92 | 1.68 57 | 1.43 64 | 1.53 64 | 1.50 29 | 0.87 25 | 1.21 72 | 1.01 3 | 0.95 71 | 1.28 58 | 0.93 5 |
Local-TV-L1 [65] | 59.9 | 0.94 102 | 1.14 89 | 1.01 108 | 0.98 100 | 1.43 93 | 0.96 96 | 0.87 8 | 1.08 46 | 0.84 1 | 1.50 99 | 1.46 58 | 1.97 116 | 1.47 36 | 1.43 31 | 1.69 90 | 1.50 123 | 1.40 16 | 1.61 126 | 0.87 25 | 1.19 48 | 1.01 3 | 0.93 8 | 1.23 10 | 0.93 5 |
ROF-ND [107] | 60.9 | 0.91 55 | 1.05 19 | 0.96 14 | 0.89 65 | 1.35 73 | 0.88 42 | 0.88 43 | 1.06 37 | 0.84 1 | 1.50 99 | 1.61 117 | 1.85 49 | 1.47 36 | 1.43 31 | 1.68 57 | 1.43 64 | 1.66 103 | 1.49 10 | 0.90 112 | 1.28 98 | 1.04 114 | 0.97 105 | 1.36 112 | 0.93 5 |
TF+OM [100] | 61.9 | 0.91 55 | 1.11 62 | 0.98 77 | 0.86 47 | 1.18 37 | 0.93 89 | 0.87 8 | 1.16 78 | 0.84 1 | 1.46 68 | 1.47 64 | 1.85 49 | 1.47 36 | 1.44 66 | 1.69 90 | 1.43 64 | 1.46 40 | 1.52 91 | 0.88 77 | 1.24 87 | 1.02 73 | 0.95 71 | 1.28 58 | 0.94 97 |
F-TV-L1 [15] | 62.9 | 0.93 95 | 1.16 100 | 1.00 93 | 0.96 94 | 1.45 97 | 0.91 85 | 0.89 70 | 1.22 96 | 0.87 68 | 1.46 68 | 1.49 79 | 1.87 82 | 1.46 8 | 1.43 31 | 1.66 6 | 1.41 9 | 1.41 20 | 1.51 70 | 0.87 25 | 1.21 72 | 1.02 73 | 0.94 39 | 1.26 33 | 0.94 97 |
SimpleFlow [49] | 63.2 | 0.91 55 | 1.12 72 | 0.96 14 | 0.88 60 | 1.29 58 | 0.88 42 | 0.92 99 | 1.10 52 | 0.87 68 | 1.43 21 | 1.41 27 | 1.85 49 | 1.47 36 | 1.43 31 | 1.67 17 | 1.45 95 | 1.79 120 | 1.51 70 | 0.89 100 | 1.58 127 | 1.03 100 | 0.96 86 | 1.36 112 | 0.93 5 |
CBF [12] | 66.3 | 0.91 55 | 1.10 54 | 0.98 77 | 0.89 65 | 1.33 71 | 0.89 68 | 0.88 43 | 1.07 42 | 0.85 52 | 1.48 90 | 1.46 58 | 1.95 113 | 1.47 36 | 1.43 31 | 1.72 119 | 1.41 9 | 1.44 31 | 1.50 29 | 0.88 77 | 1.24 87 | 1.03 100 | 0.97 105 | 1.28 58 | 0.97 121 |
CRTflow [80] | 66.8 | 0.91 55 | 1.15 93 | 0.98 77 | 0.91 74 | 1.40 82 | 0.88 42 | 0.93 102 | 1.29 110 | 0.89 105 | 1.46 68 | 1.47 64 | 1.90 105 | 1.47 36 | 1.44 66 | 1.68 57 | 1.41 9 | 1.41 20 | 1.51 70 | 0.87 25 | 1.22 77 | 1.02 73 | 0.94 39 | 1.28 58 | 0.94 97 |
Black & Anandan [4] | 67.1 | 0.94 102 | 1.15 93 | 1.00 93 | 1.06 112 | 1.53 117 | 0.98 104 | 0.94 109 | 1.26 103 | 0.88 101 | 1.48 90 | 1.49 79 | 1.84 22 | 1.47 36 | 1.44 66 | 1.69 90 | 1.41 9 | 1.39 12 | 1.50 29 | 0.88 77 | 1.22 77 | 1.01 3 | 0.94 39 | 1.27 42 | 0.93 5 |
2D-CLG [1] | 67.2 | 0.94 102 | 1.11 62 | 1.02 111 | 1.11 117 | 1.52 114 | 1.08 121 | 0.94 109 | 1.27 107 | 0.89 105 | 1.50 99 | 1.51 97 | 1.84 22 | 1.47 36 | 1.43 31 | 1.68 57 | 1.41 9 | 1.50 55 | 1.50 29 | 0.88 77 | 1.30 104 | 1.01 3 | 0.93 8 | 1.26 33 | 0.93 5 |
FlowNetS+ft+v [112] | 67.3 | 0.92 90 | 1.09 46 | 1.00 93 | 0.99 102 | 1.47 99 | 0.97 99 | 0.89 70 | 1.23 100 | 0.87 68 | 1.45 59 | 1.47 64 | 1.86 71 | 1.48 90 | 1.44 66 | 1.69 90 | 1.41 9 | 1.42 27 | 1.50 29 | 0.88 77 | 1.25 91 | 1.02 73 | 0.94 39 | 1.28 58 | 0.93 5 |
Occlusion-TV-L1 [63] | 67.6 | 0.91 55 | 1.12 72 | 0.98 77 | 0.94 87 | 1.48 101 | 0.89 68 | 0.89 70 | 1.21 90 | 0.87 68 | 1.48 90 | 1.53 102 | 1.87 82 | 1.47 36 | 1.42 14 | 1.68 57 | 1.44 81 | 1.50 55 | 1.53 103 | 0.88 77 | 1.19 48 | 1.02 73 | 0.94 39 | 1.29 72 | 0.93 5 |
Aniso-Texture [82] | 67.6 | 0.89 7 | 1.09 46 | 0.96 14 | 0.93 83 | 1.48 101 | 0.88 42 | 0.91 94 | 1.12 60 | 0.86 62 | 1.47 85 | 1.53 102 | 1.89 100 | 1.48 90 | 1.45 92 | 1.69 90 | 1.47 106 | 2.03 128 | 1.52 91 | 0.87 25 | 1.17 23 | 1.01 3 | 0.96 86 | 1.31 87 | 0.93 5 |
CNN-flow-warp+ref [117] | 69.2 | 0.91 55 | 1.04 12 | 0.98 77 | 0.94 87 | 1.42 90 | 0.93 89 | 0.93 102 | 1.30 111 | 0.87 68 | 1.55 113 | 1.57 108 | 1.93 109 | 1.47 36 | 1.43 31 | 1.70 108 | 1.41 9 | 1.47 44 | 1.51 70 | 0.89 100 | 1.37 113 | 1.02 73 | 0.93 8 | 1.27 42 | 0.93 5 |
Nguyen [33] | 70.5 | 1.00 117 | 1.14 89 | 1.07 121 | 1.15 123 | 1.59 122 | 1.04 115 | 0.90 88 | 1.37 114 | 0.87 68 | 1.51 105 | 1.52 101 | 1.85 49 | 1.47 36 | 1.43 31 | 1.67 17 | 1.41 9 | 1.49 51 | 1.48 5 | 0.88 77 | 1.36 111 | 1.02 73 | 0.93 8 | 1.28 58 | 0.93 5 |
Shiralkar [42] | 71.5 | 0.91 55 | 1.14 89 | 0.96 14 | 0.94 87 | 1.41 84 | 0.88 42 | 0.91 94 | 1.48 119 | 0.88 101 | 1.52 106 | 1.59 113 | 1.84 22 | 1.46 8 | 1.44 66 | 1.65 1 | 1.45 95 | 1.60 89 | 1.52 91 | 0.89 100 | 1.38 117 | 1.02 73 | 0.94 39 | 1.34 107 | 0.93 5 |
Adaptive [20] | 72.0 | 0.92 90 | 1.16 100 | 0.98 77 | 0.96 94 | 1.49 105 | 0.89 68 | 0.89 70 | 1.17 81 | 0.87 68 | 1.45 59 | 1.47 64 | 1.86 71 | 1.48 90 | 1.44 66 | 1.68 57 | 1.44 81 | 1.54 69 | 1.52 91 | 0.88 77 | 1.23 85 | 1.01 3 | 0.95 71 | 1.31 87 | 0.93 5 |
Correlation Flow [75] | 72.4 | 0.89 7 | 1.08 35 | 0.95 2 | 0.90 73 | 1.41 84 | 0.88 42 | 0.88 43 | 1.06 37 | 0.84 1 | 1.46 68 | 1.44 37 | 1.89 100 | 1.50 112 | 1.45 92 | 1.77 127 | 1.48 111 | 1.85 122 | 1.53 103 | 0.90 112 | 1.37 113 | 1.03 100 | 0.97 105 | 1.34 107 | 0.93 5 |
IAOF2 [51] | 73.0 | 0.94 102 | 1.19 107 | 1.00 93 | 0.99 102 | 1.55 119 | 0.95 94 | 0.88 43 | 1.15 68 | 0.87 68 | 1.49 94 | 1.50 89 | 1.87 82 | 1.49 106 | 1.47 114 | 1.67 17 | 1.43 64 | 1.61 93 | 1.50 29 | 0.87 25 | 1.19 48 | 1.01 3 | 0.96 86 | 1.33 102 | 0.93 5 |
BriefMatch [124] | 73.5 | 0.91 55 | 1.10 54 | 0.96 14 | 0.88 60 | 1.29 58 | 0.92 88 | 0.93 102 | 1.12 60 | 0.89 105 | 1.56 115 | 1.56 106 | 2.03 124 | 1.47 36 | 1.44 66 | 1.70 108 | 1.56 128 | 1.59 83 | 1.66 128 | 0.87 25 | 1.20 61 | 1.02 73 | 0.94 39 | 1.29 72 | 0.93 5 |
Steered-L1 [118] | 74.1 | 0.89 7 | 1.13 82 | 0.96 14 | 0.86 47 | 1.28 54 | 0.88 42 | 0.92 99 | 1.11 57 | 0.87 68 | 1.49 94 | 1.50 89 | 1.90 105 | 1.48 90 | 1.45 92 | 1.68 57 | 1.43 64 | 1.52 59 | 1.52 91 | 0.89 100 | 1.28 98 | 1.03 100 | 0.96 86 | 1.31 87 | 0.94 97 |
GraphCuts [14] | 74.5 | 0.95 109 | 1.23 114 | 1.00 93 | 0.91 74 | 1.26 50 | 0.98 104 | 1.00 120 | 1.04 25 | 0.89 105 | 1.49 94 | 1.50 89 | 1.88 94 | 1.46 8 | 1.43 31 | 1.65 1 | 1.39 1 | 1.53 64 | 1.46 1 | 0.89 100 | 1.31 107 | 1.03 100 | 0.97 105 | 1.33 102 | 0.94 97 |
HBpMotionGpu [43] | 74.9 | 0.98 114 | 1.25 116 | 1.04 117 | 1.10 115 | 1.61 124 | 1.05 118 | 0.87 8 | 1.08 46 | 0.86 62 | 1.50 99 | 1.56 106 | 1.90 105 | 1.47 36 | 1.44 66 | 1.67 17 | 1.44 81 | 1.56 78 | 1.52 91 | 0.86 1 | 1.15 10 | 1.01 3 | 0.96 86 | 1.31 87 | 0.95 112 |
TriangleFlow [30] | 76.1 | 0.92 90 | 1.15 93 | 0.98 77 | 0.91 74 | 1.37 75 | 0.88 42 | 0.90 88 | 1.13 64 | 0.87 68 | 1.47 85 | 1.49 79 | 1.88 94 | 1.46 8 | 1.43 31 | 1.66 6 | 1.44 81 | 1.64 98 | 1.50 29 | 0.89 100 | 1.36 111 | 1.03 100 | 0.98 113 | 1.41 123 | 0.94 97 |
HBM-GC [105] | 76.5 | 0.93 95 | 1.13 82 | 1.00 93 | 0.87 55 | 1.26 50 | 0.89 68 | 0.87 8 | 0.96 1 | 0.85 52 | 1.46 68 | 1.44 37 | 1.87 82 | 1.50 112 | 1.47 114 | 1.73 122 | 1.48 111 | 1.88 123 | 1.53 103 | 0.88 77 | 1.17 23 | 1.05 119 | 0.96 86 | 1.27 42 | 0.95 112 |
LocallyOriented [52] | 80.1 | 0.93 95 | 1.15 93 | 1.00 93 | 0.98 100 | 1.50 109 | 0.93 89 | 0.91 94 | 1.20 89 | 0.87 68 | 1.49 94 | 1.54 104 | 1.88 94 | 1.47 36 | 1.44 66 | 1.67 17 | 1.49 118 | 1.60 89 | 1.57 120 | 0.88 77 | 1.23 85 | 1.01 3 | 0.96 86 | 1.32 99 | 0.93 5 |
StereoOF-V1MT [119] | 81.0 | 0.91 55 | 1.19 107 | 0.96 14 | 0.93 83 | 1.41 84 | 0.87 5 | 0.96 114 | 1.42 116 | 0.89 105 | 1.59 119 | 1.63 119 | 1.92 108 | 1.48 90 | 1.46 108 | 1.67 17 | 1.47 106 | 1.65 101 | 1.54 109 | 0.91 117 | 1.40 120 | 1.03 100 | 0.93 8 | 1.26 33 | 0.93 5 |
ACK-Prior [27] | 82.9 | 0.89 7 | 1.08 35 | 0.96 14 | 0.85 37 | 1.24 45 | 0.87 5 | 0.93 102 | 1.11 57 | 0.87 68 | 1.46 68 | 1.48 71 | 1.86 71 | 1.51 117 | 1.47 114 | 1.73 122 | 1.49 118 | 1.70 113 | 1.55 116 | 0.91 117 | 1.30 104 | 1.06 123 | 1.03 128 | 1.40 120 | 0.96 117 |
Ad-TV-NDC [36] | 83.4 | 1.03 122 | 1.20 111 | 1.11 122 | 1.10 115 | 1.52 114 | 1.04 115 | 0.88 43 | 1.15 68 | 0.86 62 | 1.53 110 | 1.49 79 | 1.93 109 | 1.49 106 | 1.45 92 | 1.70 108 | 1.46 103 | 1.40 16 | 1.55 116 | 0.87 25 | 1.20 61 | 1.01 3 | 0.95 71 | 1.26 33 | 0.94 97 |
Dynamic MRF [7] | 85.1 | 0.90 44 | 1.16 100 | 0.96 14 | 0.89 65 | 1.44 94 | 0.88 42 | 0.95 112 | 1.53 124 | 0.89 105 | 1.59 119 | 1.68 123 | 1.96 114 | 1.47 36 | 1.45 92 | 1.67 17 | 1.47 106 | 1.97 127 | 1.53 103 | 0.90 112 | 1.47 122 | 1.02 73 | 0.96 86 | 1.34 107 | 0.93 5 |
TV-L1-improved [17] | 85.9 | 0.91 55 | 1.15 93 | 0.98 77 | 0.96 94 | 1.50 109 | 0.89 68 | 0.93 102 | 1.15 68 | 0.88 101 | 1.46 68 | 1.50 89 | 1.87 82 | 1.48 90 | 1.45 92 | 1.68 57 | 1.44 81 | 1.59 83 | 1.52 91 | 0.89 100 | 1.39 119 | 1.02 73 | 0.96 86 | 1.31 87 | 0.94 97 |
BlockOverlap [61] | 85.9 | 0.96 112 | 1.13 82 | 1.03 116 | 1.00 105 | 1.42 90 | 1.02 113 | 0.89 70 | 1.03 21 | 0.87 68 | 1.52 106 | 1.48 71 | 2.02 123 | 1.50 112 | 1.45 92 | 1.74 125 | 1.49 118 | 1.45 35 | 1.59 123 | 0.88 77 | 1.17 23 | 1.05 119 | 0.94 39 | 1.22 5 | 0.96 117 |
SegOF [10] | 86.1 | 0.93 95 | 1.12 72 | 1.00 93 | 0.95 93 | 1.37 75 | 0.96 96 | 0.97 117 | 1.30 111 | 0.89 105 | 1.49 94 | 1.63 119 | 1.85 49 | 1.48 90 | 1.44 66 | 1.68 57 | 1.44 81 | 1.74 118 | 1.51 70 | 0.91 117 | 1.57 125 | 1.03 100 | 0.94 39 | 1.30 79 | 0.93 5 |
AdaConv-v1 [126] | 86.1 | 1.00 117 | 1.21 113 | 1.05 119 | 1.11 117 | 1.44 94 | 1.22 127 | 1.08 127 | 1.43 117 | 1.15 129 | 1.63 124 | 1.69 126 | 1.98 118 | 1.43 1 | 1.37 1 | 1.65 1 | 1.41 9 | 1.33 3 | 1.50 29 | 1.00 131 | 1.25 91 | 1.09 130 | 0.98 113 | 1.18 2 | 1.00 127 |
StereoFlow [44] | 87.3 | 1.14 127 | 1.49 130 | 1.12 123 | 1.22 126 | 1.67 126 | 1.07 120 | 0.88 43 | 1.23 100 | 0.85 52 | 1.46 68 | 1.49 79 | 1.86 71 | 1.59 130 | 1.67 129 | 1.70 108 | 1.49 118 | 2.18 131 | 1.50 29 | 0.86 1 | 1.18 33 | 1.01 3 | 1.00 119 | 1.45 124 | 0.93 5 |
UnFlow [129] | 88.7 | 0.97 113 | 1.26 119 | 1.02 111 | 1.05 110 | 1.50 109 | 0.97 99 | 0.96 114 | 1.52 122 | 0.89 105 | 1.47 85 | 1.54 104 | 1.84 22 | 1.50 112 | 1.49 120 | 1.69 90 | 1.45 95 | 1.89 125 | 1.49 10 | 0.87 25 | 1.24 87 | 1.01 3 | 1.00 119 | 1.45 124 | 0.93 5 |
Rannacher [23] | 90.0 | 0.91 55 | 1.17 104 | 0.98 77 | 0.96 94 | 1.51 112 | 0.89 68 | 0.93 102 | 1.22 96 | 0.88 101 | 1.46 68 | 1.51 97 | 1.88 94 | 1.48 90 | 1.45 92 | 1.68 57 | 1.45 95 | 1.62 95 | 1.52 91 | 0.89 100 | 1.37 113 | 1.02 73 | 0.96 86 | 1.33 102 | 0.94 97 |
SPSA-learn [13] | 91.0 | 0.94 102 | 1.16 100 | 1.00 93 | 1.00 105 | 1.44 94 | 0.98 104 | 0.95 112 | 1.21 90 | 0.89 105 | 1.50 99 | 1.48 71 | 1.84 22 | 1.48 90 | 1.46 108 | 1.69 90 | 1.42 55 | 1.59 83 | 1.50 29 | 0.94 128 | 2.17 131 | 1.05 119 | 1.00 119 | 1.66 129 | 0.93 5 |
TI-DOFE [24] | 91.0 | 1.07 124 | 1.24 115 | 1.14 125 | 1.25 127 | 1.67 126 | 1.13 125 | 0.96 114 | 1.50 121 | 0.89 105 | 1.59 119 | 1.59 113 | 1.89 100 | 1.47 36 | 1.45 92 | 1.68 57 | 1.41 9 | 1.43 29 | 1.49 10 | 0.88 77 | 1.28 98 | 1.02 73 | 0.97 105 | 1.31 87 | 0.94 97 |
Horn & Schunck [3] | 91.4 | 0.94 102 | 1.17 104 | 1.00 93 | 1.08 114 | 1.57 121 | 1.00 109 | 0.98 118 | 1.46 118 | 0.91 118 | 1.55 113 | 1.58 111 | 1.87 82 | 1.48 90 | 1.45 92 | 1.69 90 | 1.41 9 | 1.44 31 | 1.50 29 | 0.89 100 | 1.31 107 | 1.02 73 | 0.96 86 | 1.31 87 | 0.94 97 |
Filter Flow [19] | 93.2 | 0.94 102 | 1.15 93 | 1.00 93 | 1.05 110 | 1.49 105 | 1.06 119 | 0.89 70 | 1.15 68 | 0.87 68 | 1.52 106 | 1.49 79 | 1.93 109 | 1.49 106 | 1.45 92 | 1.71 115 | 1.44 81 | 1.49 51 | 1.52 91 | 0.88 77 | 1.27 96 | 1.02 73 | 0.98 113 | 1.33 102 | 0.96 117 |
NL-TV-NCC [25] | 96.4 | 0.91 55 | 1.13 82 | 0.96 14 | 0.89 65 | 1.37 75 | 0.88 42 | 0.92 99 | 1.21 90 | 0.87 68 | 1.53 110 | 1.59 113 | 1.96 114 | 1.53 125 | 1.47 114 | 1.83 130 | 1.46 103 | 1.72 116 | 1.52 91 | 0.91 117 | 1.30 104 | 1.07 126 | 1.01 125 | 1.37 114 | 0.97 121 |
Bartels [41] | 101.5 | 0.93 95 | 1.20 111 | 1.00 93 | 0.91 74 | 1.38 79 | 0.95 94 | 0.89 70 | 1.15 68 | 0.89 105 | 1.54 112 | 1.57 108 | 2.06 127 | 1.53 125 | 1.46 108 | 1.83 130 | 1.67 130 | 1.67 107 | 1.79 131 | 0.88 77 | 1.19 48 | 1.07 126 | 0.98 113 | 1.30 79 | 1.00 127 |
SILK [79] | 103.8 | 1.00 117 | 1.27 121 | 1.05 119 | 1.14 119 | 1.60 123 | 1.04 115 | 1.02 121 | 1.52 122 | 0.93 119 | 1.60 122 | 1.61 117 | 1.98 118 | 1.49 106 | 1.46 108 | 1.69 90 | 1.52 125 | 1.53 64 | 1.62 127 | 0.88 77 | 1.28 98 | 1.03 100 | 0.95 71 | 1.31 87 | 0.93 5 |
GroupFlow [9] | 106.5 | 1.00 117 | 1.37 125 | 1.04 117 | 1.02 108 | 1.48 101 | 1.00 109 | 1.05 124 | 1.60 125 | 0.96 123 | 1.52 106 | 1.63 119 | 1.87 82 | 1.52 122 | 1.53 128 | 1.69 90 | 1.48 111 | 2.05 129 | 1.52 91 | 0.89 100 | 1.38 117 | 1.02 73 | 0.98 113 | 1.47 126 | 0.92 1 |
Learning Flow [11] | 110.5 | 0.93 95 | 1.25 116 | 1.00 93 | 0.99 102 | 1.52 114 | 0.93 89 | 0.98 118 | 1.48 119 | 0.89 105 | 1.58 117 | 1.65 122 | 1.97 116 | 1.52 122 | 1.50 121 | 1.73 122 | 1.47 106 | 1.64 98 | 1.54 109 | 0.89 100 | 1.34 110 | 1.03 100 | 1.01 125 | 1.40 120 | 0.95 112 |
Heeger++ [104] | 110.5 | 1.00 117 | 1.37 125 | 1.01 108 | 1.07 113 | 1.45 97 | 0.99 108 | 1.24 129 | 2.05 129 | 1.01 127 | 1.69 125 | 1.68 123 | 2.00 120 | 1.51 117 | 1.51 125 | 1.70 108 | 1.48 111 | 1.71 114 | 1.53 103 | 0.92 123 | 1.49 123 | 1.03 100 | 0.96 86 | 1.38 117 | 0.93 5 |
SLK [47] | 111.2 | 1.05 123 | 1.26 119 | 1.13 124 | 1.15 123 | 1.51 112 | 1.10 122 | 1.07 125 | 1.62 126 | 0.94 122 | 1.73 127 | 1.79 127 | 2.01 122 | 1.50 112 | 1.50 121 | 1.66 6 | 1.45 95 | 1.69 111 | 1.51 70 | 0.93 124 | 1.57 125 | 1.04 114 | 0.97 105 | 1.39 118 | 0.94 97 |
2bit-BM-tele [98] | 111.7 | 0.95 109 | 1.19 107 | 1.02 111 | 1.00 105 | 1.54 118 | 1.00 109 | 0.91 94 | 1.10 52 | 0.89 105 | 1.56 115 | 1.59 113 | 2.05 126 | 1.53 125 | 1.48 118 | 1.79 128 | 1.62 129 | 1.88 123 | 1.70 129 | 0.97 130 | 1.95 130 | 1.12 131 | 0.97 105 | 1.27 42 | 1.00 127 |
FFV1MT [106] | 117.5 | 0.98 114 | 1.35 124 | 1.02 111 | 1.14 119 | 1.49 105 | 1.10 122 | 1.22 128 | 2.34 130 | 1.03 128 | 1.69 125 | 1.68 123 | 2.00 120 | 1.51 117 | 1.50 121 | 1.71 115 | 1.48 111 | 1.57 79 | 1.54 109 | 0.93 124 | 1.51 124 | 1.03 100 | 1.02 127 | 1.51 127 | 0.96 117 |
Adaptive flow [45] | 118.0 | 1.12 126 | 1.32 122 | 1.19 127 | 1.26 128 | 1.66 125 | 1.25 129 | 0.94 109 | 1.21 90 | 0.93 119 | 1.61 123 | 1.57 108 | 2.04 125 | 1.53 125 | 1.51 125 | 1.72 119 | 1.49 118 | 1.91 126 | 1.54 109 | 0.90 112 | 1.25 91 | 1.06 123 | 1.00 119 | 1.37 114 | 0.97 121 |
HCIC-L [99] | 119.0 | 1.30 131 | 1.47 129 | 1.41 131 | 1.14 119 | 1.41 84 | 1.24 128 | 1.03 122 | 1.28 109 | 0.93 119 | 1.58 117 | 1.58 111 | 1.93 109 | 1.52 122 | 1.48 118 | 1.74 125 | 1.50 123 | 1.69 111 | 1.56 119 | 0.91 117 | 1.31 107 | 1.07 126 | 1.10 130 | 1.60 128 | 0.97 121 |
FOLKI [16] | 120.7 | 1.20 128 | 1.37 125 | 1.32 129 | 1.27 129 | 1.69 129 | 1.18 126 | 1.04 123 | 1.76 128 | 1.00 126 | 1.81 129 | 1.79 127 | 2.23 130 | 1.51 117 | 1.51 125 | 1.70 108 | 1.48 111 | 1.55 75 | 1.57 120 | 0.91 117 | 1.42 121 | 1.05 119 | 1.00 119 | 1.37 114 | 0.97 121 |
PGAM+LK [55] | 122.0 | 1.11 125 | 1.44 128 | 1.17 126 | 1.14 119 | 1.55 119 | 1.12 124 | 1.07 125 | 1.65 127 | 0.96 123 | 1.79 128 | 1.84 129 | 2.20 129 | 1.51 117 | 1.50 121 | 1.72 119 | 1.53 127 | 1.80 121 | 1.60 124 | 0.90 112 | 1.37 113 | 1.04 114 | 1.00 119 | 1.39 118 | 0.97 121 |
Pyramid LK [2] | 122.3 | 1.25 130 | 1.32 122 | 1.38 130 | 1.39 130 | 1.68 128 | 1.35 130 | 1.49 130 | 1.38 115 | 1.22 130 | 2.22 131 | 3.01 131 | 2.39 131 | 1.58 129 | 1.67 129 | 1.69 90 | 1.47 106 | 1.60 89 | 1.55 116 | 0.93 124 | 1.60 128 | 1.04 114 | 1.09 129 | 1.90 131 | 0.95 112 |
Periodicity [78] | 129.8 | 1.21 129 | 1.59 131 | 1.29 128 | 1.65 131 | 1.80 131 | 1.47 131 | 1.61 131 | 2.64 131 | 1.37 131 | 1.90 130 | 3.00 130 | 2.16 128 | 1.68 131 | 1.80 131 | 1.80 129 | 1.71 131 | 2.09 130 | 1.78 130 | 0.94 128 | 1.72 129 | 1.06 123 | 1.15 131 | 1.71 130 | 1.04 131 |
Method | time* | frames | color | Reference and notes | |
[1] 2D-CLG | 844 | 2 | gray | The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences. | |
[2] Pyramid LK | 12 | 2 | color | A modification of Bouguet's pyramidal implementation of Lucas-Kanade. | |
[3] Horn & Schunck | 49 | 2 | gray | A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data. | |
[4] Black & Anandan | 328 | 2 | gray | A modern Matlab implementation of the Black & Anandan method by Deqing Sun. | |
[5] Brox et al. | 18 | 2 | color | T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.) | |
[6] Fusion | 2,666 | 2 | color | V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008. | |
[7] Dynamic MRF | 366 | 2 | gray | B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.) | |
[8] Second-order prior | 14 | 2 | gray | W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[9] GroupFlow | 600 | 2 | gray | X. Ren. Local Grouping for Optical Flow. CVPR 2008. | |
[10] SegOF | 60 | 2 | color | L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available. | |
[11] Learning Flow | 825 | 2 | gray | D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008. | |
[12] CBF | 69 | 2 | color | W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[13] SPSA-learn | 200 | 2 | color | Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008. | |
[14] GraphCuts | 1,200 | 2 | color | T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008. | |
[15] F-TV-L1 | 8 | 2 | gray | A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008. | |
[16] FOLKI | 1.4 | 2 | gray | G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005. | |
[17] TV-L1-improved | 2.9 | 2 | gray | A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision. | |
[18] DPOF | 287 | 2 | color | C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.) | |
[19] Filter Flow | 34,000 | 2 | color | S. Seitz and S. Baker. Filter flow. ICCV 2009. | |
[20] Adaptive | 9.2 | 2 | gray | A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009. | |
[21] Complementary OF | 44 | 2 | color | H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009. | |
[22] Aniso. Huber-L1 | 2 | 2 | gray | M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision. | |
[23] Rannacher | 0.12 | 2 | gray | J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009. | |
[24] TI-DOFE | 260 | 2 | gray | C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009. | |
[25] NL-TV-NCC | 20 | 2 | color | M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010. | |
[26] MDP-Flow | 188 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010. | |
[27] ACK-Prior | 5872 | 2 | color | K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010. | |
[28] LDOF | 122 | 2 | color | T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011. | |
[29] p-harmonic | 565 | 2 | gray | J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010. | |
[30] TriangleFlow | 4200 | 2 | gray | B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010. | |
[31] Classic+NL | 972 | 2 | color | D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code. | |
[32] Classic++ | 486 | 2 | gray | A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010. | |
[33] Nguyen | 33 | 2 | gray | D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011. | |
[34] Modified CLG | 133 | 2 | gray | R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010. | |
[35] ComplOF-FED-GPU | 0.97 | 2 | color | P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010. | |
[36] Ad-TV-NDC | 35 | 2 | gray | M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010. | |
[37] Layers++ | 18206 | 2 | color | D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010. | |
[38] OFH | 620 | 3 | color | H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011. | |
[39] LSM | 1615 | 2 | color | K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011. | |
[40] CostFilter | 55 | 2 | color | C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011. | |
[41] Bartels | 0.15 | 2 | gray | C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU. | |
[42] Shiralkar | 600 | 2 | gray | M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242. | |
[43] HBpMotionGpu | 1000 | 5 | gray | S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.) | |
[44] StereoFlow | 7200 | 2 | color | G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772. | |
[45] Adaptive flow | 121 | 2 | gray | T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011. | |
[46] TC-Flow | 2500 | 5 | color | S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011. | |
[47] SLK | 300 | 2 | gray | T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011. | |
[48] CLG-TV | 29 | 2 | gray | M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code. | |
[49] SimpleFlow | 1.7 | 2 | color | M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012. | |
[50] IAOF | 57 | 2 | gray | D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011. | |
[51] IAOF2 | 56 | 2 | gray | D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011. | |
[52] LocallyOriented | 9541 | 2 | gray | Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012. | |
[53] IROF-TV | 261 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop. | |
[54] Sparse Occlusion | 2312 | 2 | color | A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011. | |
[55] PGAM+LK | 0.37 | 2 | gray | A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010. | |
[56] Sparse-NonSparse | 713 | 2 | color | L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013. | |
[57] nLayers | 36150 | 4 | color | D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012. | |
[58] IROF++ | 187 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013. | |
[59] COFM | 600 | 3 | color | M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013. | |
[60] Efficient-NL | 400 | 2 | color | P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012. | |
[61] BlockOverlap | 2 | 2 | gray | M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012. | |
[62] Ramp | 1200 | 2 | color | A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012. | |
[63] Occlusion-TV-L1 | 538 | 3 | gray | C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012. | |
[64] TV-L1-MCT | 90 | 2 | color | M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012. | |
[65] Local-TV-L1 | 500 | 2 | gray | L. Raket. Local smoothness for global optical flow. ICIP 2012. | |
[66] ALD-Flow | 61 | 2 | color | M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012. | |
[67] SIOF | 234 | 2 | color | L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012. | |
[68] MDP-Flow2 | 342 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available. | |
[69] TCOF | 1421 | all | gray | J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013. | |
[70] LME | 476 | 2 | color | W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013. | |
[71] NN-field | 362 | 2 | color | L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[72] FESL | 3310 | 2 | color | W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013. | |
[73] PMF | 35 | 2 | color | J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013. | |
[74] FC-2Layers-FF | 2662 | 4 | color | D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013. | |
[75] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code. | |
[76] TC/T-Flow | 341 | 5 | color | M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013. | |
[77] OFLAF | 1530 | 2 | color | T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013. | |
[78] Periodicity | 8000 | 4 | color | G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013. | |
[79] SILK | 572 | 2 | gray | P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP. | |
[80] CRTflow | 13 | 3 | color | O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013. | |
[81] SuperFlow | 178 | 2 | color | Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507. | |
[82] Aniso-Texture | 300 | 2 | color | Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267. | |
[83] Classic+CPF | 640 | 2 | gray | Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013. | |
[84] S2D-Matching | 1200 | 2 | color | Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479. | |
[85] AGIF+OF | 438 | 2 | gray | Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015. | |
[86] DeepFlow | 13 | 2 | color | P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[87] NNF-Local | 673 | 2 | color | Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014. | |
[88] EPPM w/o HM | 2.5 | 2 | color | L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014. | |
[89] MLDP_OF | 165 | 2 | gray | M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014. | |
[90] RFlow | 20 | 2 | gray | S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014. | |
[91] SRR-TVOF-NL | 32 | all | color | P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014. | |
[92] 2DHMM-SAS | 157 | 2 | color | M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission. | |
[93] WLIF-Flow | 700 | 2 | color | Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014. | |
[94] FMOF | 215 | 2 | color | N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014. | |
[95] TriFlow | 150 | 2 | color | TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914. | |
[96] ComponentFusion | 6.5 | 2 | color | Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941. | |
[97] AggregFlow | 1642 | 2 | color | D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759. | |
[98] 2bit-BM-tele | 124 | 2 | gray | R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013. | |
[99] HCIC-L | 330 | 2 | color | Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114. | |
[100] TF+OM | 600 | 2 | color | R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015. | |
[101] PH-Flow | 800 | 2 | color | J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015. | |
[102] EpicFlow | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015. | |
[103] NNF-EAC | 380 | 2 | color | Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336. | |
[104] Heeger++ | 6600 | 5 | gray | Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238. | |
[105] HBM-GC | 330 | 2 | color | A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015. | |
[106] FFV1MT | 358 | 5 | gray | F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015. | |
[107] ROF-ND | 4 | 2 | color | S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015. | |
[108] DeepFlow2 | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015. | |
[109] HAST | 2667 | 2 | color | Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221. | |
[110] FlowFields | 15 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015. | |
[111] SVFilterOh | 1.56 | 2 | color | Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788. | |
[112] FlowNetS+ft+v | 0.5 | 2 | color | Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235. | |
[113] CombBMOF | 51 | 2 | color | M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.) | |
[114] PMMST | 182 | 2 | color | F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015. | |
[115] DF-Auto | 70 | 2 | color | N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015. | |
[116] CPM-Flow | 3 | 2 | color | Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241. | |
[117] CNN-flow-warp+ref | 1.4 | 3 | color | D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016. | |
[118] Steered-L1 | 804 | 2 | color | Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016. | |
[119] StereoOF-V1MT | 343 | 2 | gray | Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132. | |
[120] PGM-C | 5 | 2 | color | Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016. | |
[121] RNLOD-Flow | 1040 | 2 | gray | C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016. | |
[122] FlowNet2 | 0.091 | 2 | color | Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900. | |
[123] S2F-IF | 20 | 2 | color | Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765. | |
[124] BriefMatch | 0.068 | 2 | gray | G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62. | |
[125] OAR-Flow | 60 | 2 | color | Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20. | |
[126] AdaConv-v1 | 2.8 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017. | |
[127] SepConv-v1 | 0.2 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017. | |
[128] ProbFlowFields | 37 | 2 | color | A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017. | |
[129] UnFlow | 0.12 | 2 | color | Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018. | |
[130] FlowFields+ | 10.5 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017. | |
[131] Kuang | 9.9 | 2 | gray | F. Kuang. PatchMatch algorithms for motion estimation and stereo reconstruction. Master thesis, University of Stuttgart, 2017. |