| Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
|
A90 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 | |
| MDP-Flow2 [70] | 5.6 | 3.11 1 | 6.35 3 | 1.73 1 | 4.55 6 | 7.35 8 | 1.73 1 | 4.00 7 | 6.35 2 | 1.41 1 | 6.32 2 | 8.12 2 | 4.24 2 | 11.8 1 | 15.8 2 | 4.20 8 | 5.32 16 | 16.6 18 | 3.27 12 | 4.97 5 | 22.9 1 | 2.00 3 | 9.33 12 | 15.6 9 | 1.91 12 |
| NN-field [73] | 9.3 | 3.11 1 | 6.98 33 | 1.73 1 | 4.51 1 | 6.78 4 | 1.73 1 | 4.00 7 | 6.35 2 | 1.41 1 | 6.48 24 | 9.26 55 | 4.24 2 | 11.8 1 | 15.9 4 | 4.20 8 | 5.32 16 | 17.0 27 | 3.27 12 | 4.93 2 | 22.9 1 | 2.00 3 | 9.27 7 | 15.6 9 | 1.83 1 |
| IROF++ [58] | 9.9 | 3.11 1 | 7.16 50 | 1.73 1 | 4.69 11 | 7.62 11 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.27 1 | 8.10 1 | 4.24 2 | 11.9 5 | 16.1 22 | 4.20 8 | 5.23 4 | 16.2 8 | 3.27 12 | 5.03 33 | 23.7 12 | 2.00 3 | 9.26 5 | 15.8 18 | 1.91 12 |
| ComplexFlow [81] | 10.2 | 3.11 1 | 6.78 22 | 1.73 1 | 4.51 1 | 6.76 3 | 1.73 1 | 4.00 7 | 6.35 2 | 1.41 1 | 6.45 20 | 9.04 43 | 4.24 2 | 11.9 5 | 15.9 4 | 4.20 8 | 5.35 28 | 17.6 43 | 3.32 19 | 4.93 2 | 23.5 10 | 2.00 3 | 9.26 5 | 15.7 14 | 1.83 1 |
| SuperFlow [89] | 13.0 | 3.11 1 | 6.24 2 | 1.73 1 | 5.07 38 | 8.81 40 | 1.83 61 | 4.00 7 | 6.68 8 | 1.41 1 | 6.48 24 | 8.50 16 | 4.24 2 | 11.9 5 | 15.9 4 | 4.24 50 | 5.07 1 | 15.9 4 | 3.16 1 | 4.97 5 | 23.7 12 | 2.00 3 | 9.27 7 | 15.5 7 | 1.91 12 |
| Layers++ [37] | 14.1 | 3.11 1 | 6.78 22 | 1.73 1 | 4.51 1 | 6.68 1 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.40 14 | 8.41 12 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.35 28 | 18.7 72 | 3.32 19 | 4.97 5 | 23.5 10 | 2.00 3 | 9.35 15 | 15.9 25 | 1.91 12 |
| nLayers [57] | 14.6 | 3.11 1 | 6.83 30 | 1.73 1 | 4.55 6 | 7.23 7 | 1.73 1 | 3.70 1 | 6.06 1 | 1.41 1 | 6.40 14 | 8.54 19 | 4.24 2 | 12.1 51 | 16.4 63 | 4.20 8 | 5.35 28 | 17.7 44 | 3.32 19 | 4.93 2 | 23.4 8 | 2.00 3 | 9.33 12 | 16.0 28 | 1.83 1 |
| IROF-TV [53] | 15.2 | 3.11 1 | 7.12 44 | 1.73 1 | 4.69 11 | 7.85 18 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.38 6 | 8.50 16 | 4.24 2 | 12.0 23 | 16.1 22 | 4.24 50 | 5.26 8 | 17.1 32 | 3.16 1 | 5.00 22 | 24.1 24 | 2.00 3 | 9.27 7 | 15.4 3 | 1.91 12 |
| Brox et al. [5] | 15.3 | 3.11 1 | 6.66 11 | 1.73 1 | 5.07 38 | 8.58 32 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.56 37 | 8.70 23 | 4.24 2 | 11.9 5 | 15.9 4 | 4.20 8 | 5.32 16 | 17.1 32 | 3.27 12 | 5.00 22 | 24.5 31 | 2.00 3 | 9.29 10 | 15.6 9 | 1.91 12 |
| Deep-Matching [85] | 15.4 | 3.11 1 | 6.35 3 | 1.73 1 | 5.03 35 | 8.72 35 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.61 53 | 8.91 40 | 4.24 2 | 11.9 5 | 15.9 4 | 4.24 50 | 5.20 2 | 15.4 1 | 3.37 70 | 4.97 5 | 23.0 3 | 2.00 3 | 9.15 1 | 15.4 3 | 1.91 12 |
| ADF [67] | 16.2 | 3.11 1 | 6.16 1 | 1.73 1 | 4.76 20 | 8.23 23 | 1.73 1 | 4.00 7 | 6.88 30 | 1.41 1 | 6.35 3 | 8.25 4 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.26 8 | 17.0 27 | 3.16 1 | 5.03 33 | 24.8 34 | 2.00 3 | 9.57 52 | 16.5 60 | 1.91 12 |
| Aniso. Huber-L1 [22] | 16.6 | 3.27 46 | 6.78 22 | 1.73 1 | 5.45 56 | 9.66 55 | 1.73 1 | 4.00 7 | 6.73 25 | 1.41 1 | 6.48 24 | 8.81 29 | 4.24 2 | 11.9 5 | 15.9 4 | 4.20 8 | 5.26 8 | 16.3 11 | 3.16 1 | 5.07 39 | 23.9 18 | 2.00 3 | 9.38 17 | 15.4 3 | 1.91 12 |
| TV-L1-MCT [64] | 17.1 | 3.37 63 | 7.62 75 | 1.73 1 | 4.83 24 | 8.58 32 | 1.73 1 | 3.70 1 | 6.68 8 | 1.41 1 | 6.38 6 | 8.25 4 | 4.24 2 | 12.1 51 | 16.4 63 | 4.20 8 | 5.20 2 | 16.0 5 | 3.32 19 | 4.97 5 | 24.0 21 | 2.00 3 | 9.15 1 | 15.4 3 | 1.91 12 |
| LME [72] | 17.2 | 3.11 1 | 6.81 27 | 1.73 1 | 4.76 20 | 7.94 22 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.38 6 | 8.50 16 | 4.24 2 | 12.1 51 | 16.3 47 | 4.24 50 | 5.42 39 | 17.0 27 | 3.27 12 | 4.97 5 | 23.0 3 | 2.00 3 | 9.29 10 | 15.8 18 | 1.91 12 |
| Sparse-NonSparse [56] | 17.3 | 3.11 1 | 7.07 42 | 1.73 1 | 4.65 9 | 7.53 10 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.38 6 | 8.37 10 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.45 41 | 18.1 54 | 3.32 19 | 4.97 5 | 25.4 46 | 2.00 3 | 9.42 20 | 16.2 39 | 1.91 12 |
| COFM [59] | 17.5 | 3.11 1 | 6.76 21 | 1.73 1 | 4.69 11 | 7.62 11 | 1.73 1 | 4.00 7 | 6.66 7 | 1.41 1 | 6.35 3 | 8.35 8 | 4.24 2 | 12.0 23 | 16.2 34 | 4.16 1 | 5.45 41 | 18.9 74 | 3.16 1 | 4.80 1 | 23.1 5 | 2.08 67 | 9.56 45 | 16.3 42 | 1.91 12 |
| Epistemic [84] | 17.7 | 3.11 1 | 7.16 50 | 1.73 1 | 4.69 11 | 7.72 16 | 1.73 1 | 4.00 7 | 6.88 30 | 1.41 1 | 6.38 6 | 8.54 19 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.26 8 | 16.8 21 | 3.32 19 | 5.03 33 | 26.3 60 | 2.00 3 | 9.42 20 | 16.2 39 | 1.91 12 |
| Second-order prior [8] | 19.3 | 3.11 1 | 6.63 10 | 1.73 1 | 5.32 49 | 9.63 53 | 1.73 1 | 4.00 7 | 7.68 66 | 1.41 1 | 6.56 37 | 9.11 48 | 4.24 2 | 11.9 5 | 16.0 15 | 4.20 8 | 5.23 4 | 16.4 15 | 3.27 12 | 5.10 47 | 24.4 30 | 2.00 3 | 9.40 19 | 15.8 18 | 1.91 12 |
| CLG-TV [48] | 19.5 | 3.16 35 | 6.61 9 | 1.73 1 | 5.35 50 | 9.56 49 | 1.73 1 | 4.00 7 | 7.05 40 | 1.41 1 | 6.56 37 | 8.81 29 | 4.24 2 | 11.9 5 | 15.9 4 | 4.24 50 | 5.26 8 | 16.0 5 | 3.32 19 | 5.07 39 | 24.3 25 | 2.00 3 | 9.43 29 | 15.6 9 | 1.91 12 |
| F-TV-L1 [15] | 20.7 | 3.37 63 | 6.68 12 | 1.73 1 | 5.48 59 | 9.76 59 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.56 37 | 8.76 27 | 4.32 60 | 11.8 1 | 15.8 2 | 4.16 1 | 5.26 8 | 16.1 7 | 3.32 19 | 5.00 22 | 24.0 21 | 2.00 3 | 9.35 15 | 15.6 9 | 1.91 12 |
| ALD-Flow [68] | 20.8 | 3.16 35 | 6.98 33 | 1.73 1 | 4.83 24 | 8.54 31 | 1.73 1 | 4.00 7 | 7.05 40 | 1.41 1 | 6.40 14 | 8.54 19 | 4.24 2 | 12.1 51 | 16.2 34 | 4.24 50 | 5.32 16 | 15.8 2 | 3.32 19 | 4.97 5 | 23.1 5 | 2.00 3 | 9.54 43 | 16.4 50 | 1.91 12 |
| MDP-Flow [26] | 21.2 | 3.11 1 | 6.68 12 | 1.73 1 | 4.65 9 | 7.44 9 | 1.73 1 | 4.00 7 | 6.35 2 | 1.41 1 | 6.58 50 | 8.96 41 | 4.24 2 | 11.9 5 | 16.1 22 | 4.24 50 | 5.60 64 | 19.2 78 | 3.32 19 | 5.16 54 | 24.3 25 | 2.00 3 | 9.33 12 | 16.0 28 | 1.91 12 |
| Levin3 [90] | 21.2 | 3.27 46 | 7.35 57 | 1.73 1 | 4.69 11 | 7.85 18 | 1.73 1 | 3.70 1 | 6.68 8 | 1.41 1 | 6.38 6 | 8.25 4 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.48 56 | 18.2 59 | 3.32 19 | 4.97 5 | 26.3 60 | 2.00 3 | 9.49 36 | 16.2 39 | 1.91 12 |
| DPOF [18] | 21.5 | 3.16 35 | 7.55 71 | 1.73 1 | 4.55 6 | 7.05 6 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.56 37 | 9.20 53 | 4.24 2 | 11.9 5 | 16.0 15 | 4.20 8 | 5.45 41 | 17.8 48 | 3.16 1 | 5.10 47 | 24.0 21 | 2.00 3 | 9.56 45 | 16.3 42 | 1.91 12 |
| LSM [39] | 21.6 | 3.11 1 | 7.53 67 | 1.73 1 | 4.69 11 | 7.79 17 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.45 20 | 8.70 23 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.45 41 | 18.3 60 | 3.32 19 | 4.97 5 | 25.5 47 | 2.00 3 | 9.47 31 | 16.4 50 | 1.83 1 |
| Classic+NL [31] | 21.6 | 3.27 46 | 7.35 57 | 1.73 1 | 4.69 11 | 7.68 15 | 1.73 1 | 3.70 1 | 6.68 8 | 1.41 1 | 6.38 6 | 8.35 8 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.48 56 | 18.1 54 | 3.32 19 | 4.97 5 | 25.8 52 | 2.00 3 | 9.52 41 | 16.3 42 | 1.91 12 |
| Ramp [62] | 22.5 | 3.16 35 | 7.19 53 | 1.73 1 | 4.69 11 | 7.62 11 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.35 3 | 8.27 7 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.51 59 | 18.9 74 | 3.32 19 | 4.97 5 | 25.9 54 | 2.00 3 | 9.56 45 | 16.4 50 | 1.91 12 |
| LDOF [28] | 22.7 | 3.37 63 | 6.68 12 | 1.73 1 | 5.35 50 | 8.35 24 | 1.83 61 | 4.00 7 | 7.35 50 | 1.41 1 | 6.61 53 | 9.09 46 | 4.24 2 | 11.9 5 | 15.9 4 | 4.24 50 | 5.23 4 | 16.2 8 | 3.32 19 | 5.00 22 | 23.7 12 | 2.00 3 | 9.38 17 | 15.8 18 | 1.91 12 |
| CBF [12] | 23.0 | 3.11 1 | 6.38 7 | 1.73 1 | 5.07 38 | 8.72 35 | 1.73 1 | 4.00 7 | 6.73 25 | 1.41 1 | 6.56 37 | 8.60 22 | 4.43 75 | 11.9 5 | 15.9 4 | 4.24 50 | 5.32 16 | 16.5 16 | 3.27 12 | 5.07 39 | 24.5 31 | 2.08 67 | 9.49 36 | 15.7 14 | 1.91 12 |
| SCR [74] | 23.5 | 3.16 35 | 7.39 61 | 1.73 1 | 4.69 11 | 7.62 11 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.40 14 | 8.39 11 | 4.24 2 | 12.1 51 | 16.4 63 | 4.20 8 | 5.48 56 | 18.1 54 | 3.32 19 | 4.97 5 | 25.9 54 | 2.00 3 | 9.49 36 | 16.4 50 | 1.83 1 |
| p-harmonic [29] | 23.7 | 3.11 1 | 6.68 12 | 1.73 1 | 5.45 56 | 9.68 56 | 1.73 1 | 4.00 7 | 7.39 65 | 1.41 1 | 6.68 58 | 9.15 51 | 4.24 2 | 12.0 23 | 16.1 22 | 4.20 8 | 5.32 16 | 16.5 16 | 3.32 19 | 5.20 58 | 24.8 34 | 2.00 3 | 9.43 29 | 15.8 18 | 1.91 12 |
| SIOF [69] | 24.3 | 3.37 63 | 6.98 33 | 1.73 1 | 5.48 59 | 10.0 65 | 1.83 61 | 4.00 7 | 7.00 32 | 1.41 1 | 6.48 24 | 8.76 27 | 4.24 2 | 11.8 1 | 15.7 1 | 4.20 8 | 5.32 16 | 16.2 8 | 3.32 19 | 5.07 39 | 23.7 12 | 2.00 3 | 9.59 55 | 16.1 34 | 1.91 12 |
| ComplOF-FED-GPU [35] | 24.5 | 3.11 1 | 7.05 39 | 1.73 1 | 4.83 24 | 8.43 26 | 1.73 1 | 4.08 65 | 7.19 48 | 1.41 1 | 6.48 24 | 9.11 48 | 4.24 2 | 12.0 23 | 16.1 22 | 4.20 8 | 5.35 28 | 17.1 32 | 3.32 19 | 5.07 39 | 24.8 34 | 2.00 3 | 9.56 45 | 16.3 42 | 1.91 12 |
| TC-Flow [46] | 25.0 | 3.11 1 | 6.81 27 | 1.73 1 | 4.90 28 | 8.76 38 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.45 20 | 8.81 29 | 4.24 2 | 12.1 51 | 16.4 63 | 4.24 50 | 5.45 41 | 17.0 27 | 3.32 19 | 5.00 22 | 24.3 25 | 2.00 3 | 9.47 31 | 16.4 50 | 1.91 12 |
| FC-2Layers-FF [77] | 25.5 | 3.16 35 | 7.23 55 | 1.73 1 | 4.51 1 | 6.68 1 | 1.73 1 | 4.00 7 | 6.78 28 | 1.41 1 | 6.40 14 | 8.49 15 | 4.24 2 | 12.1 51 | 16.4 63 | 4.20 8 | 5.57 61 | 19.0 77 | 3.32 19 | 4.97 5 | 25.6 49 | 2.00 3 | 9.57 52 | 16.4 50 | 1.91 12 |
| FastOF [78] | 26.6 | 3.37 63 | 7.53 67 | 1.73 1 | 5.29 48 | 9.42 47 | 1.83 61 | 4.00 7 | 8.00 73 | 1.41 1 | 6.76 61 | 9.68 66 | 4.20 1 | 11.9 5 | 16.0 15 | 4.20 8 | 5.23 4 | 15.8 2 | 3.32 19 | 5.00 22 | 23.9 18 | 2.00 3 | 9.42 20 | 15.7 14 | 1.91 12 |
| Local-TV-L1 [65] | 27.4 | 3.32 51 | 6.35 3 | 1.83 70 | 5.51 62 | 9.63 53 | 1.83 61 | 4.00 7 | 6.68 8 | 1.41 1 | 6.48 24 | 8.70 23 | 4.55 78 | 11.9 5 | 16.0 15 | 4.24 50 | 5.32 16 | 16.3 11 | 3.51 86 | 4.97 5 | 23.4 8 | 2.00 3 | 9.20 4 | 15.3 2 | 1.91 12 |
| OFLADF [82] | 28.0 | 3.11 1 | 6.98 33 | 1.73 1 | 4.51 1 | 7.00 5 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.40 14 | 8.43 14 | 4.24 2 | 12.1 51 | 16.4 63 | 4.24 50 | 5.60 64 | 18.7 72 | 3.32 19 | 5.07 39 | 28.0 74 | 2.00 3 | 9.83 66 | 17.0 72 | 1.91 12 |
| Classic++ [32] | 28.3 | 3.11 1 | 6.78 22 | 1.73 1 | 5.07 38 | 9.15 42 | 1.73 1 | 4.00 7 | 7.12 45 | 1.41 1 | 6.56 37 | 8.83 32 | 4.32 60 | 12.0 23 | 16.2 34 | 4.24 50 | 5.45 41 | 17.7 44 | 3.37 70 | 5.00 22 | 24.8 34 | 2.00 3 | 9.47 31 | 16.0 28 | 1.91 12 |
| Modified CLG [34] | 29.0 | 3.11 1 | 6.40 8 | 1.73 1 | 5.80 71 | 9.75 58 | 2.00 76 | 4.00 7 | 7.77 70 | 1.41 1 | 6.68 58 | 9.43 59 | 4.24 2 | 12.0 23 | 16.1 22 | 4.24 50 | 5.35 28 | 16.9 23 | 3.32 19 | 5.10 47 | 23.9 18 | 2.00 3 | 9.42 20 | 15.8 18 | 1.91 12 |
| TC/T-Flow [80] | 30.1 | 3.32 51 | 7.53 67 | 1.73 1 | 4.93 30 | 8.74 37 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.48 24 | 8.87 36 | 4.24 2 | 12.1 51 | 16.4 63 | 4.24 50 | 5.45 41 | 16.8 21 | 3.32 19 | 5.10 47 | 26.6 63 | 2.00 3 | 9.63 57 | 16.3 42 | 1.83 1 |
| CRTflow [88] | 30.5 | 3.32 51 | 7.05 39 | 1.73 1 | 5.26 46 | 9.54 48 | 1.73 1 | 4.36 72 | 7.85 72 | 1.41 1 | 6.48 24 | 8.74 26 | 4.40 72 | 12.0 23 | 16.2 34 | 4.24 50 | 5.32 16 | 16.3 11 | 3.32 19 | 5.00 22 | 25.1 41 | 2.00 3 | 9.42 20 | 16.0 28 | 1.91 12 |
| OFH [38] | 30.8 | 3.16 35 | 7.14 46 | 1.73 1 | 5.10 44 | 9.15 42 | 1.73 1 | 4.00 7 | 7.79 71 | 1.41 1 | 6.45 20 | 9.04 43 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.45 41 | 17.3 39 | 3.32 19 | 5.10 47 | 27.1 70 | 2.00 3 | 9.57 52 | 16.8 65 | 1.91 12 |
| EP-PM [83] | 32.0 | 3.11 1 | 7.77 79 | 1.73 1 | 4.97 32 | 8.76 38 | 1.73 1 | 4.08 65 | 8.39 80 | 1.41 1 | 6.48 24 | 9.42 57 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.45 41 | 18.3 60 | 3.32 19 | 5.16 54 | 25.0 39 | 2.00 3 | 9.56 45 | 16.5 60 | 1.83 1 |
| PMF [76] | 32.1 | 3.11 1 | 7.14 46 | 1.73 1 | 4.97 32 | 8.49 29 | 1.73 1 | 4.00 7 | 8.00 73 | 1.41 1 | 6.48 24 | 8.89 37 | 4.24 2 | 12.2 74 | 16.5 74 | 4.20 8 | 5.45 41 | 17.4 40 | 3.37 70 | 4.97 5 | 25.5 47 | 2.00 3 | 9.90 74 | 17.3 79 | 1.83 1 |
| Efficient-NL [60] | 32.2 | 3.32 51 | 7.19 53 | 1.73 1 | 4.90 28 | 8.50 30 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.56 37 | 8.83 32 | 4.24 2 | 12.0 23 | 16.3 47 | 4.20 8 | 5.80 76 | 18.9 74 | 3.16 1 | 5.07 39 | 26.6 63 | 2.00 3 | 9.97 80 | 17.0 72 | 1.91 12 |
| BlockOverlap [61] | 32.3 | 3.32 51 | 6.35 3 | 1.83 70 | 5.48 59 | 9.33 46 | 1.91 72 | 4.00 7 | 6.35 2 | 1.41 1 | 6.48 24 | 8.19 3 | 4.65 82 | 12.0 23 | 16.1 22 | 4.36 85 | 5.35 28 | 16.6 18 | 3.42 81 | 4.97 5 | 23.7 12 | 2.08 67 | 9.15 1 | 15.1 1 | 1.91 12 |
| Adaptive [20] | 32.7 | 3.32 51 | 6.83 30 | 1.73 1 | 5.69 67 | 10.4 74 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.53 36 | 8.89 37 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.45 41 | 17.9 50 | 3.32 19 | 5.20 58 | 27.4 73 | 2.00 3 | 9.63 57 | 16.4 50 | 1.91 12 |
| Sparse Occlusion [54] | 33.1 | 3.27 46 | 7.05 39 | 1.73 1 | 5.07 38 | 9.56 49 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.58 50 | 9.04 43 | 4.24 2 | 12.1 51 | 16.3 47 | 4.24 50 | 5.69 67 | 18.6 68 | 3.32 19 | 5.07 39 | 26.2 57 | 1.91 1 | 9.61 56 | 16.3 42 | 1.91 12 |
| FESL [75] | 33.2 | 3.32 51 | 7.39 61 | 1.73 1 | 4.76 20 | 7.87 20 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.56 37 | 8.89 37 | 4.24 2 | 12.1 51 | 16.5 74 | 4.24 50 | 5.72 69 | 18.6 68 | 3.32 19 | 5.00 22 | 25.6 49 | 1.91 1 | 9.68 59 | 16.8 65 | 1.83 1 |
| TV-L1-improved [17] | 33.5 | 3.16 35 | 6.73 18 | 1.73 1 | 5.60 63 | 10.2 68 | 1.73 1 | 4.08 65 | 7.05 40 | 1.41 1 | 6.58 50 | 9.02 42 | 4.24 2 | 12.0 23 | 16.2 34 | 4.20 8 | 5.45 41 | 18.4 65 | 3.32 19 | 5.20 58 | 28.7 77 | 2.00 3 | 9.54 43 | 16.1 34 | 1.91 12 |
| TCOF [71] | 33.5 | 3.32 51 | 7.14 46 | 1.73 1 | 5.72 68 | 10.3 71 | 1.73 1 | 4.00 7 | 6.78 28 | 1.41 1 | 6.56 37 | 8.83 32 | 4.24 2 | 12.0 23 | 16.0 15 | 4.20 8 | 5.72 69 | 18.0 52 | 3.16 1 | 5.35 75 | 27.1 70 | 2.00 3 | 9.87 70 | 16.5 60 | 1.91 12 |
| Complementary OF [21] | 34.2 | 3.11 1 | 7.35 57 | 1.73 1 | 4.83 24 | 8.43 26 | 1.73 1 | 4.36 72 | 7.05 40 | 1.41 1 | 6.48 24 | 9.15 51 | 4.24 2 | 12.1 51 | 16.4 63 | 4.20 8 | 5.42 39 | 17.8 48 | 3.32 19 | 5.16 54 | 27.0 69 | 2.00 3 | 9.87 70 | 18.1 85 | 1.91 12 |
| Fusion [6] | 35.0 | 3.11 1 | 7.12 44 | 1.73 1 | 4.80 23 | 7.90 21 | 1.73 1 | 4.00 7 | 6.73 25 | 1.41 1 | 6.83 65 | 9.26 55 | 4.24 2 | 12.2 74 | 16.5 74 | 4.16 1 | 5.80 76 | 19.6 80 | 3.16 1 | 5.20 58 | 25.9 54 | 2.00 3 | 10.2 82 | 17.3 79 | 1.91 12 |
| Occlusion-TV-L1 [63] | 35.2 | 3.27 46 | 6.81 27 | 1.73 1 | 5.45 56 | 10.2 68 | 1.73 1 | 4.00 7 | 7.35 50 | 1.41 1 | 6.66 56 | 9.43 59 | 4.32 60 | 11.9 5 | 15.9 4 | 4.24 50 | 5.35 28 | 17.2 37 | 3.37 70 | 5.32 70 | 24.3 25 | 2.08 67 | 9.42 20 | 15.9 25 | 1.91 12 |
| CostFilter [40] | 36.4 | 3.11 1 | 7.90 80 | 1.73 1 | 4.93 30 | 8.43 26 | 1.73 1 | 4.00 7 | 8.68 82 | 1.41 1 | 6.56 37 | 9.68 66 | 4.24 2 | 12.2 74 | 16.7 79 | 4.20 8 | 5.45 41 | 17.0 27 | 3.46 85 | 5.00 22 | 26.2 57 | 2.00 3 | 9.80 63 | 17.3 79 | 1.83 1 |
| 2D-CLG [1] | 36.8 | 3.16 35 | 6.73 18 | 1.83 70 | 6.16 76 | 9.88 63 | 2.16 82 | 4.08 65 | 7.35 50 | 1.41 1 | 7.05 73 | 9.95 71 | 4.24 2 | 11.9 5 | 16.0 15 | 4.20 8 | 5.35 28 | 16.9 23 | 3.32 19 | 5.23 66 | 26.6 63 | 2.00 3 | 9.42 20 | 15.7 14 | 1.91 12 |
| IAOF [50] | 38.0 | 3.42 74 | 7.16 50 | 1.83 70 | 6.88 84 | 11.7 89 | 1.91 72 | 3.70 1 | 7.35 50 | 1.41 1 | 6.98 69 | 9.49 62 | 4.24 2 | 11.9 5 | 16.0 15 | 4.20 8 | 5.32 16 | 17.2 37 | 3.32 19 | 5.20 58 | 25.1 41 | 2.00 3 | 9.56 45 | 16.0 28 | 1.91 12 |
| SimpleFlow [49] | 38.4 | 3.16 35 | 7.42 63 | 1.73 1 | 5.07 38 | 9.00 41 | 1.73 1 | 4.00 7 | 7.14 46 | 1.41 1 | 6.38 6 | 8.41 12 | 4.24 2 | 12.1 51 | 16.5 74 | 4.20 8 | 5.72 69 | 19.6 80 | 3.32 19 | 5.16 54 | 32.0 88 | 2.08 67 | 9.81 64 | 17.6 82 | 1.91 12 |
| Rannacher [23] | 39.1 | 3.32 51 | 7.00 38 | 1.73 1 | 5.60 63 | 10.4 74 | 1.73 1 | 4.08 65 | 7.35 50 | 1.41 1 | 6.56 37 | 9.11 48 | 4.32 60 | 12.0 23 | 16.1 22 | 4.24 50 | 5.45 41 | 18.3 60 | 3.32 19 | 5.20 58 | 28.1 76 | 2.00 3 | 9.49 36 | 16.4 50 | 1.91 12 |
| Nguyen [33] | 39.4 | 3.37 63 | 6.78 22 | 1.91 78 | 6.56 82 | 10.5 78 | 2.00 76 | 4.00 7 | 8.00 73 | 1.41 1 | 7.14 77 | 10.3 77 | 4.24 2 | 11.9 5 | 16.1 22 | 4.20 8 | 5.32 16 | 17.1 32 | 3.16 1 | 5.72 88 | 28.7 77 | 2.00 3 | 9.42 20 | 15.9 25 | 1.91 12 |
| HBpMotionGpu [43] | 39.5 | 3.42 74 | 6.98 33 | 1.91 78 | 6.19 78 | 10.7 81 | 2.08 78 | 4.00 7 | 6.68 8 | 1.41 1 | 6.78 62 | 9.95 71 | 4.36 70 | 12.0 23 | 16.1 22 | 4.20 8 | 5.57 61 | 17.7 44 | 3.32 19 | 5.00 22 | 23.8 17 | 2.00 3 | 9.52 41 | 16.1 34 | 1.91 12 |
| GraphCuts [14] | 41.1 | 3.37 63 | 7.53 67 | 1.73 1 | 5.03 35 | 8.39 25 | 1.83 61 | 4.36 72 | 6.68 8 | 1.41 1 | 6.83 65 | 9.56 63 | 4.32 60 | 12.1 51 | 16.3 47 | 4.16 1 | 5.26 8 | 17.5 42 | 3.16 1 | 5.03 33 | 25.6 49 | 2.08 67 | 9.95 78 | 17.1 77 | 1.91 12 |
| Ad-TV-NDC [36] | 42.3 | 3.65 81 | 6.68 12 | 2.00 82 | 6.16 76 | 10.2 68 | 2.08 78 | 4.00 7 | 7.35 50 | 1.41 1 | 6.98 69 | 9.47 61 | 4.43 75 | 12.1 51 | 16.1 22 | 4.24 50 | 5.32 16 | 16.3 11 | 3.42 81 | 5.20 58 | 24.3 25 | 2.00 3 | 9.42 20 | 15.5 7 | 1.91 12 |
| Black & Anandan [4] | 42.4 | 3.37 63 | 6.68 12 | 1.83 70 | 6.06 75 | 10.4 74 | 1.83 61 | 4.36 72 | 7.72 69 | 1.41 1 | 7.07 75 | 9.90 70 | 4.24 2 | 12.1 51 | 16.1 22 | 4.24 50 | 5.26 8 | 16.9 23 | 3.32 19 | 5.32 70 | 26.4 62 | 2.00 3 | 9.49 36 | 15.8 18 | 1.91 12 |
| Shiralkar [42] | 44.2 | 3.32 51 | 7.96 81 | 1.73 1 | 5.60 63 | 9.85 62 | 1.73 1 | 4.00 7 | 8.43 81 | 1.41 1 | 7.12 76 | 11.1 82 | 4.24 2 | 12.0 23 | 16.3 47 | 4.16 1 | 5.57 61 | 18.3 60 | 3.37 70 | 5.35 75 | 29.8 85 | 2.00 3 | 9.56 45 | 17.0 72 | 1.91 12 |
| Filter Flow [19] | 45.6 | 3.37 63 | 6.93 32 | 1.83 70 | 5.80 71 | 9.98 64 | 2.08 78 | 4.00 7 | 7.05 40 | 1.41 1 | 6.95 68 | 9.09 46 | 4.43 75 | 12.2 74 | 16.3 47 | 4.24 50 | 5.35 28 | 17.4 40 | 3.32 19 | 5.10 47 | 25.3 43 | 2.00 3 | 9.83 66 | 16.4 50 | 1.91 12 |
| Bartels [41] | 45.7 | 3.32 51 | 7.35 57 | 1.73 1 | 5.03 35 | 9.26 45 | 1.83 61 | 4.00 7 | 7.00 32 | 1.41 1 | 6.73 60 | 9.42 57 | 4.69 84 | 12.0 23 | 15.9 4 | 4.55 88 | 5.94 81 | 18.4 65 | 3.87 89 | 5.03 33 | 23.2 7 | 2.08 67 | 9.47 31 | 16.0 28 | 2.00 89 |
| IAOF2 [51] | 47.6 | 3.46 78 | 7.59 73 | 1.73 1 | 5.74 70 | 10.9 85 | 1.83 61 | 3.70 1 | 7.14 46 | 1.41 1 | 6.98 69 | 10.0 73 | 4.32 60 | 12.3 80 | 16.8 82 | 4.20 8 | 5.51 59 | 18.6 68 | 3.32 19 | 5.10 47 | 25.3 43 | 2.00 3 | 9.75 61 | 16.3 42 | 1.91 12 |
| Direct ZNCC [66] | 47.8 | 3.11 1 | 7.33 56 | 1.73 1 | 5.35 50 | 10.0 65 | 1.73 1 | 4.00 7 | 7.00 32 | 1.41 1 | 6.66 56 | 9.70 68 | 4.40 72 | 12.1 51 | 16.3 47 | 4.32 83 | 5.97 82 | 20.5 85 | 3.32 19 | 5.35 75 | 30.6 86 | 2.08 67 | 9.83 66 | 16.8 65 | 1.91 12 |
| LocallyOriented [52] | 48.5 | 3.37 63 | 7.42 63 | 1.73 1 | 5.80 71 | 10.6 79 | 1.73 1 | 4.00 7 | 7.68 66 | 1.41 1 | 6.81 64 | 10.1 74 | 4.32 60 | 12.1 51 | 16.4 63 | 4.20 8 | 5.80 76 | 18.3 60 | 3.42 81 | 5.32 70 | 26.6 63 | 2.00 3 | 9.81 64 | 16.7 64 | 1.91 12 |
| TriangleFlow [30] | 48.8 | 3.37 63 | 7.70 76 | 1.73 1 | 5.35 50 | 9.70 57 | 1.73 1 | 4.08 65 | 7.19 48 | 1.41 1 | 6.78 62 | 10.1 74 | 4.32 60 | 12.0 23 | 16.2 34 | 4.16 1 | 5.77 75 | 18.6 68 | 3.32 19 | 5.32 70 | 29.0 79 | 2.08 67 | 10.1 81 | 17.8 84 | 1.91 12 |
| Correlation Flow [79] | 48.9 | 3.16 35 | 7.70 76 | 1.73 1 | 5.35 50 | 10.1 67 | 1.73 1 | 4.00 7 | 6.68 8 | 1.41 1 | 6.61 53 | 9.20 53 | 4.40 72 | 12.1 51 | 16.3 47 | 4.40 87 | 6.06 86 | 20.6 86 | 3.32 19 | 5.35 75 | 29.5 83 | 2.08 67 | 9.88 72 | 16.8 65 | 1.91 12 |
| SegOF [10] | 49.3 | 3.11 1 | 7.07 42 | 1.83 70 | 5.35 50 | 9.20 44 | 1.83 61 | 4.36 72 | 8.00 73 | 1.41 1 | 6.98 69 | 11.3 83 | 4.24 2 | 12.1 51 | 16.3 47 | 4.24 50 | 5.72 69 | 18.1 54 | 3.32 19 | 5.26 68 | 29.4 82 | 2.08 67 | 9.47 31 | 16.8 65 | 1.91 12 |
| Dynamic MRF [7] | 50.2 | 3.11 1 | 7.44 65 | 1.73 1 | 5.20 45 | 9.80 60 | 1.73 1 | 4.36 72 | 8.68 82 | 1.41 1 | 7.33 80 | 10.7 79 | 4.55 78 | 12.1 51 | 16.4 63 | 4.20 8 | 5.80 76 | 20.4 84 | 3.37 70 | 5.29 69 | 29.0 79 | 2.00 3 | 9.83 66 | 16.5 60 | 1.91 12 |
| SPSA-learn [13] | 51.4 | 3.32 51 | 6.73 18 | 1.73 1 | 5.66 66 | 9.59 51 | 1.83 61 | 4.36 72 | 7.35 50 | 1.41 1 | 7.05 73 | 9.57 65 | 4.24 2 | 12.1 51 | 16.6 78 | 4.24 50 | 5.45 41 | 18.0 52 | 3.32 19 | 5.66 87 | 35.7 90 | 2.08 67 | 10.4 86 | 20.9 89 | 1.91 12 |
| Horn & Schunck [3] | 53.0 | 3.42 74 | 7.14 46 | 1.83 70 | 6.27 79 | 10.6 79 | 1.91 72 | 4.36 72 | 8.35 78 | 1.41 1 | 7.70 84 | 11.0 81 | 4.24 2 | 12.1 51 | 16.2 34 | 4.24 50 | 5.35 28 | 16.7 20 | 3.32 19 | 5.60 86 | 27.3 72 | 2.08 67 | 9.75 61 | 16.1 34 | 1.91 12 |
| TI-DOFE [24] | 55.0 | 3.70 82 | 7.51 66 | 2.16 85 | 6.95 85 | 11.1 87 | 2.16 82 | 4.36 72 | 8.35 78 | 1.41 1 | 7.72 85 | 10.9 80 | 4.36 70 | 12.0 23 | 16.2 34 | 4.20 8 | 5.35 28 | 16.9 23 | 3.32 19 | 5.45 80 | 25.3 43 | 2.08 67 | 9.93 76 | 16.1 34 | 1.91 12 |
| StereoFlow [44] | 55.0 | 5.20 90 | 12.2 90 | 2.00 82 | 6.98 86 | 11.2 88 | 2.16 82 | 4.00 7 | 7.35 50 | 1.41 1 | 6.56 37 | 8.83 32 | 4.24 2 | 14.1 89 | 20.1 89 | 4.24 50 | 7.05 90 | 24.6 90 | 3.32 19 | 5.03 33 | 24.8 34 | 2.00 3 | 10.2 82 | 17.7 83 | 1.91 12 |
| ACK-Prior [27] | 55.5 | 3.11 1 | 7.55 71 | 1.73 1 | 4.97 32 | 8.70 34 | 1.73 1 | 4.36 72 | 7.35 50 | 1.41 1 | 6.86 67 | 10.1 74 | 4.32 60 | 12.4 81 | 16.8 82 | 4.32 83 | 6.03 84 | 20.3 83 | 3.37 70 | 5.23 66 | 26.8 68 | 2.08 67 | 10.7 88 | 18.1 85 | 1.91 12 |
| NL-TV-NCC [25] | 61.2 | 3.46 78 | 8.50 84 | 1.73 1 | 5.26 46 | 9.83 61 | 1.73 1 | 4.36 72 | 7.68 66 | 1.41 1 | 7.39 83 | 11.6 85 | 4.55 78 | 12.2 74 | 16.3 47 | 4.55 88 | 6.19 88 | 19.6 80 | 3.32 19 | 6.76 90 | 28.0 74 | 2.16 89 | 10.2 82 | 16.9 70 | 1.91 12 |
| Learning Flow [11] | 62.0 | 3.42 74 | 7.59 73 | 1.73 1 | 5.72 68 | 10.3 71 | 1.73 1 | 4.51 83 | 8.68 82 | 1.41 1 | 7.26 78 | 9.85 69 | 4.55 78 | 12.4 81 | 16.7 79 | 4.36 85 | 5.66 66 | 18.1 54 | 3.37 70 | 5.45 80 | 26.6 63 | 2.08 67 | 10.2 82 | 16.9 70 | 1.91 12 |
| SILK [87] | 68.6 | 3.56 80 | 8.12 82 | 1.91 78 | 6.61 83 | 10.8 83 | 2.08 78 | 4.69 84 | 8.68 82 | 1.73 84 | 7.35 81 | 10.4 78 | 4.65 82 | 12.2 74 | 16.4 63 | 4.24 50 | 5.72 69 | 17.7 44 | 3.56 88 | 5.32 70 | 24.6 33 | 2.08 67 | 9.68 59 | 16.3 42 | 1.91 12 |
| Adaptive flow [45] | 70.9 | 4.04 85 | 7.72 78 | 2.16 85 | 6.98 86 | 10.8 83 | 2.52 88 | 4.24 71 | 7.35 50 | 1.63 83 | 7.26 78 | 9.56 63 | 4.69 84 | 12.4 81 | 16.8 82 | 4.24 50 | 5.80 76 | 20.7 87 | 3.37 70 | 5.20 58 | 25.0 39 | 2.08 67 | 9.90 74 | 17.0 72 | 1.91 12 |
| SLK [47] | 71.5 | 3.70 82 | 8.76 86 | 2.08 84 | 6.35 80 | 9.59 51 | 2.16 82 | 4.93 87 | 8.68 82 | 1.73 84 | 8.70 87 | 13.3 87 | 4.69 84 | 12.5 85 | 17.1 86 | 4.16 1 | 5.97 82 | 18.4 65 | 3.32 19 | 5.74 89 | 29.2 81 | 2.08 67 | 9.93 76 | 17.2 78 | 1.91 12 |
| FOLKI [16] | 73.0 | 4.08 86 | 8.29 83 | 2.45 89 | 7.05 88 | 10.7 81 | 2.38 87 | 4.69 84 | 9.35 87 | 1.73 84 | 8.60 86 | 11.5 84 | 5.10 88 | 12.4 81 | 16.7 79 | 4.24 50 | 5.69 67 | 17.1 32 | 3.42 81 | 5.48 83 | 25.8 52 | 2.08 67 | 9.88 72 | 16.4 50 | 1.91 12 |
| GroupFlow [9] | 73.5 | 3.74 84 | 11.0 89 | 1.91 78 | 5.92 74 | 10.3 71 | 1.91 72 | 4.76 86 | 9.98 89 | 1.73 84 | 7.35 81 | 13.0 86 | 4.32 60 | 12.9 87 | 18.2 87 | 4.24 50 | 6.06 86 | 21.7 88 | 3.37 70 | 5.42 79 | 31.0 87 | 2.00 3 | 10.4 86 | 19.6 87 | 1.83 1 |
| PGAM+LK [55] | 77.1 | 4.08 86 | 9.76 87 | 2.16 85 | 6.40 81 | 10.4 74 | 2.16 82 | 5.00 88 | 9.81 88 | 1.73 84 | 8.70 87 | 13.4 88 | 5.10 88 | 12.5 85 | 16.8 82 | 4.24 50 | 6.03 84 | 19.4 79 | 3.51 86 | 5.45 80 | 26.2 57 | 2.08 67 | 9.95 78 | 17.0 72 | 1.91 12 |
| Pyramid LK [2] | 78.6 | 4.08 86 | 8.68 85 | 2.58 90 | 7.75 89 | 11.0 86 | 2.71 89 | 7.00 89 | 8.00 73 | 2.00 89 | 13.9 90 | 26.4 90 | 5.60 90 | 13.5 88 | 20.0 88 | 4.24 50 | 5.72 69 | 17.9 50 | 3.37 70 | 5.48 83 | 29.7 84 | 2.08 67 | 11.6 89 | 23.4 90 | 1.91 12 |
| Periodicity [86] | 89.0 | 4.32 89 | 10.2 88 | 2.38 88 | 9.88 90 | 11.9 90 | 3.00 90 | 7.35 90 | 14.4 90 | 2.38 90 | 9.56 89 | 24.6 89 | 4.97 87 | 14.3 90 | 20.9 90 | 4.55 88 | 6.38 89 | 21.9 89 | 3.87 89 | 5.51 85 | 33.0 89 | 2.16 89 | 11.6 89 | 19.9 88 | 2.16 90 |
| 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. CVPR 2012. | |
| [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] Direct ZNCC | 260 | 2 | color | M. Drulea, C. Pantilie, and S. Nedevschi. A direct approach for correlation-based matching in variational optical flow. Submitted to TIP 2012. | |
| [67] ADF | 1535 | 2 | color | Anonymous. Optical flow estimation by adaptive data fusion. NIPS 2012 submission 601. | |
| [68] ALD-Flow | 61 | 2 | color | M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012. | |
| [69] SIOF | 234 | 2 | color | L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012. | |
| [70] 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. | |
| [71] TCOF | 1421 | all | gray | Anonymous. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013 submission 20. | |
| [72] LME | 476 | 2 | color | Anonymous. Optical flow estimation using Laplacian mesh energy. CVPR 2013 submission 11. | |
| [73] 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. | |
| [74] SCR | 257 | 2 | color | Anonymous. Segmentation constrained regularization for optical flow estimation. CVPR 2013 submission 297. | |
| [75] 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. | |
| [76] PMF | 35 | 2 | color | Anonymous. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013 submission 573. | |
| [77] 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. | |
| [78] FastOF | 0.18 | 2 | color | Anonymous. Quasi-realtime variational optical flow computation. CVPR 2013 submission 792. | |
| [79] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. Submitted to TIP 2013. | |
| [80] TC/T-Flow | 341 | 5 | color | Anonymous. Joint trilateral filtering for multiframe optical flow. ICIP 2013 submission 2685. | |
| [81] ComplexFlow | 673 | 2 | color | Anonymous. Constructing dense correspondence for complex motion. ICCV 2013 submission 353. | |
| [82] OFLADF | 1530 | 2 | color | Anonymous. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013 submission 423. | |
| [83] EP-PM | 2.7 | 2 | color | Anonymous. Fast edge-preserving PatchMatch for large displacement optical flow. ICCV 2013 submission 575. | |
| [84] Epistemic | 6.5 | 2 | color | Anonymous. Epistemic optical flow. ICCV 2013 submission 804. | |
| [85] Deep-Matching | 13 | 2 | color | Anonymous. Large displacement optical flow with deep matching. ICCV 2013 submission 1095. | |
| [86] Periodicity | 8000 | 4 | color | Anonymous. A periodicity-based computation of optical flow. BMVC 2013 submission 133. | |
| [87] 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. | |
| [88] CRTflow | 13 | 3 | color | Anonymous. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013 submission 488. | |
| [89] SuperFlow | 178 | 2 | color | Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507. | |
| [90] Levin3 | 247 | 2 | color | L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013. |