Optical flow evaluation results |
Statistics:
Average
SD
R0.5
R1.0
R2.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
A95 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 | |
MDP-Flow2 [68] | 7.5 | 1.09 2 | 1.35 2 | 1.13 2 | 1.11 9 | 1.60 9 | 1.06 6 | 1.19 2 | 1.49 6 | 1.04 1 | 1.80 2 | 1.83 8 | 2.22 4 | 1.73 2 | 1.70 2 | 1.94 14 | 1.70 25 | 2.17 32 | 1.74 22 | 1.08 1 | 1.48 4 | 1.20 1 | 1.19 10 | 1.69 12 | 1.07 2 |
PMMST [114] | 8.5 | 1.10 6 | 1.35 2 | 1.14 9 | 1.14 25 | 1.62 14 | 1.07 18 | 1.19 2 | 1.45 2 | 1.04 1 | 1.80 2 | 1.82 6 | 2.23 9 | 1.74 3 | 1.71 6 | 1.94 14 | 1.67 3 | 1.85 2 | 1.74 22 | 1.08 1 | 1.49 7 | 1.20 1 | 1.19 10 | 1.69 12 | 1.08 27 |
CombBMOF [113] | 11.2 | 1.10 6 | 1.37 4 | 1.14 9 | 1.10 7 | 1.59 8 | 1.06 6 | 1.23 36 | 1.55 10 | 1.10 60 | 1.82 18 | 1.85 17 | 2.24 19 | 1.75 11 | 1.72 9 | 1.93 3 | 1.67 3 | 1.91 7 | 1.73 11 | 1.09 7 | 1.50 10 | 1.20 1 | 1.15 2 | 1.62 3 | 1.06 1 |
NNF-Local [87] | 12.0 | 1.09 2 | 1.38 5 | 1.13 2 | 1.07 1 | 1.46 2 | 1.05 1 | 1.19 2 | 1.47 4 | 1.04 1 | 1.83 24 | 1.93 51 | 2.23 9 | 1.74 3 | 1.70 2 | 1.93 3 | 1.72 49 | 2.42 55 | 1.75 38 | 1.09 7 | 1.50 10 | 1.20 1 | 1.18 4 | 1.68 9 | 1.07 2 |
PH-Flow [101] | 13.4 | 1.11 19 | 1.41 11 | 1.14 9 | 1.08 2 | 1.51 5 | 1.05 1 | 1.20 5 | 1.52 8 | 1.04 1 | 1.80 2 | 1.81 2 | 2.23 9 | 1.74 3 | 1.71 6 | 1.93 3 | 1.72 49 | 2.62 85 | 1.74 22 | 1.09 7 | 1.52 18 | 1.20 1 | 1.19 10 | 1.70 16 | 1.08 27 |
NN-field [71] | 15.3 | 1.10 6 | 1.43 13 | 1.14 9 | 1.08 2 | 1.47 4 | 1.05 1 | 1.24 44 | 1.47 4 | 1.07 21 | 1.85 53 | 2.00 80 | 2.23 9 | 1.74 3 | 1.70 2 | 1.94 14 | 1.70 25 | 2.21 38 | 1.74 22 | 1.08 1 | 1.48 4 | 1.20 1 | 1.18 4 | 1.67 6 | 1.07 2 |
IROF++ [58] | 16.7 | 1.11 19 | 1.44 14 | 1.14 9 | 1.13 20 | 1.68 20 | 1.05 1 | 1.22 13 | 1.61 25 | 1.07 21 | 1.80 2 | 1.81 2 | 2.24 19 | 1.74 3 | 1.72 9 | 1.93 3 | 1.68 10 | 2.06 14 | 1.73 11 | 1.10 23 | 1.56 40 | 1.21 39 | 1.20 24 | 1.75 32 | 1.08 27 |
nLayers [57] | 18.8 | 1.11 19 | 1.40 9 | 1.15 25 | 1.11 9 | 1.60 9 | 1.07 18 | 1.20 5 | 1.44 1 | 1.06 9 | 1.81 8 | 1.83 8 | 2.23 9 | 1.77 51 | 1.76 53 | 1.95 35 | 1.72 49 | 2.42 55 | 1.76 58 | 1.09 7 | 1.47 1 | 1.20 1 | 1.18 4 | 1.67 6 | 1.07 2 |
Layers++ [37] | 19.4 | 1.12 39 | 1.45 16 | 1.15 25 | 1.09 6 | 1.46 2 | 1.07 18 | 1.22 13 | 1.59 17 | 1.07 21 | 1.81 8 | 1.85 17 | 2.23 9 | 1.76 20 | 1.75 35 | 1.94 14 | 1.72 49 | 2.56 74 | 1.75 38 | 1.09 7 | 1.47 1 | 1.20 1 | 1.18 4 | 1.66 4 | 1.08 27 |
FMOF [94] | 21.3 | 1.12 39 | 1.52 42 | 1.15 25 | 1.12 12 | 1.61 12 | 1.07 18 | 1.24 44 | 1.60 20 | 1.10 60 | 1.83 24 | 1.90 37 | 2.23 9 | 1.75 11 | 1.73 12 | 1.94 14 | 1.70 25 | 2.09 20 | 1.74 22 | 1.08 1 | 1.47 1 | 1.20 1 | 1.20 24 | 1.69 12 | 1.08 27 |
2DHMM-SAS [92] | 24.0 | 1.12 39 | 1.50 32 | 1.15 25 | 1.26 64 | 2.00 65 | 1.07 18 | 1.21 10 | 1.62 27 | 1.07 21 | 1.82 18 | 1.85 17 | 2.24 19 | 1.75 11 | 1.73 12 | 1.94 14 | 1.69 16 | 2.09 20 | 1.73 11 | 1.10 23 | 1.53 23 | 1.20 1 | 1.21 37 | 1.78 51 | 1.07 2 |
NNF-EAC [103] | 24.1 | 1.12 39 | 1.48 30 | 1.15 25 | 1.15 28 | 1.71 26 | 1.07 18 | 1.22 13 | 1.55 10 | 1.07 21 | 1.85 53 | 1.88 28 | 2.30 97 | 1.75 11 | 1.72 9 | 1.94 14 | 1.67 3 | 1.87 3 | 1.73 11 | 1.09 7 | 1.53 23 | 1.21 39 | 1.20 24 | 1.71 19 | 1.08 27 |
Sparse-NonSparse [56] | 25.5 | 1.11 19 | 1.47 23 | 1.15 25 | 1.12 12 | 1.68 20 | 1.06 6 | 1.22 13 | 1.61 25 | 1.06 9 | 1.83 24 | 1.86 22 | 2.24 19 | 1.76 20 | 1.74 24 | 1.94 14 | 1.73 65 | 2.54 68 | 1.76 58 | 1.10 23 | 1.57 45 | 1.20 1 | 1.20 24 | 1.78 51 | 1.07 2 |
COFM [59] | 27.2 | 1.11 19 | 1.44 14 | 1.15 25 | 1.12 12 | 1.66 18 | 1.07 18 | 1.21 10 | 1.55 10 | 1.06 9 | 1.80 2 | 1.83 8 | 2.21 1 | 1.74 3 | 1.73 12 | 1.93 3 | 1.71 41 | 2.82 104 | 1.72 4 | 1.11 59 | 1.53 23 | 1.24 106 | 1.21 37 | 1.71 19 | 1.10 95 |
TV-L1-MCT [64] | 28.0 | 1.13 74 | 1.55 57 | 1.15 25 | 1.19 44 | 1.89 47 | 1.07 18 | 1.22 13 | 1.66 41 | 1.07 21 | 1.81 8 | 1.84 13 | 2.24 19 | 1.76 20 | 1.75 35 | 1.94 14 | 1.70 25 | 2.10 22 | 1.75 38 | 1.10 23 | 1.55 35 | 1.21 39 | 1.18 4 | 1.68 9 | 1.08 27 |
HAST [109] | 28.9 | 1.10 6 | 1.39 7 | 1.15 25 | 1.12 12 | 1.60 9 | 1.06 6 | 1.25 56 | 1.67 47 | 1.08 43 | 1.79 1 | 1.79 1 | 2.21 1 | 1.76 20 | 1.75 35 | 1.93 3 | 1.73 65 | 2.77 98 | 1.73 11 | 1.10 23 | 1.56 40 | 1.21 39 | 1.23 70 | 1.81 73 | 1.07 2 |
AGIF+OF [85] | 29.9 | 1.11 19 | 1.47 23 | 1.14 9 | 1.14 25 | 1.73 32 | 1.07 18 | 1.22 13 | 1.57 15 | 1.07 21 | 1.81 8 | 1.82 6 | 2.22 4 | 1.78 83 | 1.78 89 | 1.95 35 | 1.73 65 | 2.72 95 | 1.74 22 | 1.10 23 | 1.51 14 | 1.20 1 | 1.21 37 | 1.79 58 | 1.07 2 |
ComponentFusion [96] | 30.0 | 1.10 6 | 1.46 20 | 1.14 9 | 1.12 12 | 1.65 15 | 1.05 1 | 1.22 13 | 1.64 36 | 1.07 21 | 1.81 8 | 1.85 17 | 2.22 4 | 1.77 51 | 1.75 35 | 1.95 35 | 1.70 25 | 2.21 38 | 1.75 38 | 1.11 59 | 1.69 92 | 1.21 39 | 1.22 53 | 1.80 66 | 1.08 27 |
LME [70] | 30.1 | 1.09 2 | 1.38 5 | 1.13 2 | 1.15 28 | 1.70 23 | 1.12 81 | 1.23 36 | 1.76 60 | 1.07 21 | 1.81 8 | 1.87 25 | 2.24 19 | 1.78 83 | 1.78 89 | 2.00 114 | 1.70 25 | 2.26 43 | 1.74 22 | 1.08 1 | 1.48 4 | 1.20 1 | 1.19 10 | 1.71 19 | 1.07 2 |
FlowFields [110] | 30.1 | 1.10 6 | 1.53 48 | 1.14 9 | 1.13 20 | 1.70 23 | 1.07 18 | 1.22 13 | 1.68 48 | 1.06 9 | 1.84 42 | 1.95 63 | 2.26 59 | 1.76 20 | 1.74 24 | 1.95 35 | 1.72 49 | 2.49 62 | 1.76 58 | 1.09 7 | 1.52 18 | 1.21 39 | 1.19 10 | 1.77 41 | 1.07 2 |
S2F-IF [123] | 30.1 | 1.10 6 | 1.51 37 | 1.14 9 | 1.12 12 | 1.65 15 | 1.07 18 | 1.22 13 | 1.70 52 | 1.06 9 | 1.82 18 | 1.91 41 | 2.24 19 | 1.77 51 | 1.76 53 | 1.95 35 | 1.72 49 | 2.54 68 | 1.76 58 | 1.10 23 | 1.57 45 | 1.21 39 | 1.19 10 | 1.77 41 | 1.07 2 |
WLIF-Flow [93] | 30.4 | 1.10 6 | 1.45 16 | 1.14 9 | 1.14 25 | 1.74 34 | 1.07 18 | 1.22 13 | 1.55 10 | 1.06 9 | 1.83 24 | 1.83 8 | 2.28 88 | 1.75 11 | 1.73 12 | 1.96 72 | 1.76 92 | 2.68 91 | 1.79 102 | 1.09 7 | 1.49 7 | 1.20 1 | 1.20 24 | 1.72 24 | 1.08 27 |
LSM [39] | 31.7 | 1.12 39 | 1.50 32 | 1.15 25 | 1.13 20 | 1.70 23 | 1.06 6 | 1.22 13 | 1.68 48 | 1.06 9 | 1.83 24 | 1.87 25 | 2.24 19 | 1.76 20 | 1.75 35 | 1.95 35 | 1.73 65 | 2.63 86 | 1.76 58 | 1.10 23 | 1.58 57 | 1.20 1 | 1.21 37 | 1.79 58 | 1.07 2 |
FlowFields+ [130] | 32.0 | 1.10 6 | 1.51 37 | 1.14 9 | 1.12 12 | 1.66 18 | 1.08 39 | 1.22 13 | 1.72 54 | 1.06 9 | 1.83 24 | 1.93 51 | 2.25 43 | 1.77 51 | 1.76 53 | 1.95 35 | 1.72 49 | 2.60 84 | 1.76 58 | 1.09 7 | 1.51 14 | 1.21 39 | 1.19 10 | 1.78 51 | 1.07 2 |
ProbFlowFields [128] | 35.1 | 1.11 19 | 1.56 63 | 1.15 25 | 1.11 9 | 1.65 15 | 1.06 6 | 1.20 5 | 1.57 15 | 1.05 7 | 1.84 42 | 1.94 60 | 2.26 59 | 1.77 51 | 1.76 53 | 1.97 101 | 1.74 79 | 2.80 99 | 1.77 82 | 1.08 1 | 1.51 14 | 1.20 1 | 1.17 3 | 1.67 6 | 1.08 27 |
SRR-TVOF-NL [91] | 35.1 | 1.12 39 | 1.54 51 | 1.15 25 | 1.24 58 | 1.97 59 | 1.11 76 | 1.24 44 | 1.64 36 | 1.07 21 | 1.81 8 | 1.84 13 | 2.22 4 | 1.76 20 | 1.76 53 | 1.94 14 | 1.67 3 | 2.21 38 | 1.71 2 | 1.10 23 | 1.53 23 | 1.21 39 | 1.24 84 | 1.83 83 | 1.08 27 |
Ramp [62] | 35.4 | 1.12 39 | 1.52 42 | 1.15 25 | 1.13 20 | 1.71 26 | 1.07 18 | 1.22 13 | 1.62 27 | 1.06 9 | 1.81 8 | 1.84 13 | 2.24 19 | 1.76 20 | 1.75 35 | 1.95 35 | 1.76 92 | 2.87 110 | 1.77 82 | 1.10 23 | 1.56 40 | 1.20 1 | 1.22 53 | 1.81 73 | 1.08 27 |
Classic+NL [31] | 36.1 | 1.12 39 | 1.54 51 | 1.15 25 | 1.15 28 | 1.73 32 | 1.07 18 | 1.22 13 | 1.63 30 | 1.06 9 | 1.83 24 | 1.89 31 | 2.25 43 | 1.76 20 | 1.74 24 | 1.95 35 | 1.75 86 | 2.57 76 | 1.77 82 | 1.10 23 | 1.57 45 | 1.20 1 | 1.22 53 | 1.78 51 | 1.08 27 |
FC-2Layers-FF [74] | 36.4 | 1.12 39 | 1.50 32 | 1.15 25 | 1.08 2 | 1.45 1 | 1.08 39 | 1.21 10 | 1.60 20 | 1.06 9 | 1.82 18 | 1.86 22 | 2.24 19 | 1.77 51 | 1.76 53 | 1.95 35 | 1.76 92 | 2.95 115 | 1.77 82 | 1.10 23 | 1.60 65 | 1.20 1 | 1.22 53 | 1.77 41 | 1.08 27 |
Aniso. Huber-L1 [22] | 36.6 | 1.13 74 | 1.57 68 | 1.17 75 | 1.41 92 | 2.18 88 | 1.11 76 | 1.25 56 | 1.65 39 | 1.08 43 | 1.83 24 | 1.89 31 | 2.25 43 | 1.75 11 | 1.73 12 | 1.94 14 | 1.67 3 | 2.06 14 | 1.72 4 | 1.10 23 | 1.52 18 | 1.20 1 | 1.20 24 | 1.71 19 | 1.08 27 |
DeepFlow2 [108] | 37.2 | 1.12 39 | 1.52 42 | 1.15 25 | 1.24 58 | 1.99 64 | 1.10 63 | 1.24 44 | 1.83 72 | 1.08 43 | 1.85 53 | 1.91 41 | 2.25 43 | 1.76 20 | 1.73 12 | 1.96 72 | 1.68 10 | 1.87 3 | 1.75 38 | 1.10 23 | 1.54 28 | 1.21 39 | 1.19 10 | 1.72 24 | 1.08 27 |
RNLOD-Flow [121] | 37.6 | 1.11 19 | 1.47 23 | 1.15 25 | 1.21 49 | 1.98 62 | 1.07 18 | 1.23 36 | 1.72 54 | 1.07 21 | 1.81 8 | 1.83 8 | 2.23 9 | 1.77 51 | 1.77 76 | 1.95 35 | 1.73 65 | 2.55 72 | 1.76 58 | 1.09 7 | 1.52 18 | 1.21 39 | 1.23 70 | 1.82 78 | 1.07 2 |
MDP-Flow [26] | 38.2 | 1.10 6 | 1.47 23 | 1.14 9 | 1.13 20 | 1.69 22 | 1.08 39 | 1.22 13 | 1.60 20 | 1.08 43 | 1.88 76 | 1.99 77 | 2.25 43 | 1.76 20 | 1.73 12 | 1.96 72 | 1.76 92 | 3.26 120 | 1.76 58 | 1.10 23 | 1.54 28 | 1.21 39 | 1.20 24 | 1.76 36 | 1.07 2 |
SepConv-v1 [127] | 38.4 | 0.94 1 | 1.31 1 | 0.98 1 | 1.17 39 | 1.78 39 | 1.12 81 | 1.13 1 | 1.51 7 | 1.26 121 | 1.92 94 | 1.90 37 | 2.26 59 | 1.74 3 | 1.70 2 | 1.95 35 | 1.63 1 | 1.62 1 | 1.71 2 | 1.15 108 | 1.55 35 | 1.30 126 | 1.14 1 | 1.42 1 | 1.15 125 |
PGM-C [120] | 38.7 | 1.11 19 | 1.56 63 | 1.15 25 | 1.15 28 | 1.71 26 | 1.08 39 | 1.25 56 | 1.76 60 | 1.07 21 | 1.84 42 | 1.95 63 | 2.24 19 | 1.77 51 | 1.75 35 | 1.96 72 | 1.71 41 | 2.24 41 | 1.75 38 | 1.09 7 | 1.58 57 | 1.20 1 | 1.20 24 | 1.81 73 | 1.08 27 |
OFLAF [77] | 38.7 | 1.10 6 | 1.39 7 | 1.14 9 | 1.08 2 | 1.51 5 | 1.06 6 | 1.22 13 | 1.59 17 | 1.04 1 | 1.80 2 | 1.81 2 | 2.21 1 | 1.77 51 | 1.76 53 | 1.96 72 | 1.75 86 | 2.93 114 | 1.76 58 | 1.12 81 | 1.86 110 | 1.21 39 | 1.24 84 | 1.83 83 | 1.08 27 |
DPOF [18] | 39.3 | 1.13 74 | 1.65 99 | 1.17 75 | 1.10 7 | 1.55 7 | 1.08 39 | 1.29 86 | 1.62 27 | 1.11 77 | 1.84 42 | 1.93 51 | 2.25 43 | 1.75 11 | 1.73 12 | 1.93 3 | 1.69 16 | 2.17 32 | 1.72 4 | 1.10 23 | 1.54 28 | 1.22 75 | 1.22 53 | 1.75 32 | 1.08 27 |
DeepFlow [86] | 39.9 | 1.12 39 | 1.50 32 | 1.15 25 | 1.25 62 | 2.00 65 | 1.12 81 | 1.24 44 | 1.87 82 | 1.08 43 | 1.87 65 | 1.92 47 | 2.26 59 | 1.76 20 | 1.73 12 | 1.96 72 | 1.71 41 | 1.88 6 | 1.78 92 | 1.09 7 | 1.50 10 | 1.20 1 | 1.19 10 | 1.70 16 | 1.08 27 |
CPM-Flow [116] | 40.0 | 1.12 39 | 1.57 68 | 1.15 25 | 1.15 28 | 1.72 30 | 1.08 39 | 1.24 44 | 1.73 56 | 1.07 21 | 1.87 65 | 2.02 90 | 2.26 59 | 1.76 20 | 1.75 35 | 1.96 72 | 1.70 25 | 2.08 19 | 1.76 58 | 1.10 23 | 1.58 57 | 1.20 1 | 1.20 24 | 1.76 36 | 1.08 27 |
FESL [72] | 40.4 | 1.12 39 | 1.49 31 | 1.15 25 | 1.15 28 | 1.75 35 | 1.07 18 | 1.23 36 | 1.66 41 | 1.08 43 | 1.83 24 | 1.88 28 | 2.24 19 | 1.77 51 | 1.76 53 | 1.96 72 | 1.75 86 | 2.85 108 | 1.76 58 | 1.10 23 | 1.57 45 | 1.20 1 | 1.22 53 | 1.78 51 | 1.07 2 |
S2D-Matching [84] | 40.7 | 1.12 39 | 1.55 57 | 1.15 25 | 1.24 58 | 2.03 72 | 1.07 18 | 1.22 13 | 1.60 20 | 1.07 21 | 1.83 24 | 1.85 17 | 2.27 77 | 1.77 51 | 1.76 53 | 1.94 14 | 1.76 92 | 2.84 106 | 1.76 58 | 1.10 23 | 1.53 23 | 1.20 1 | 1.21 37 | 1.78 51 | 1.08 27 |
Second-order prior [8] | 40.8 | 1.12 39 | 1.53 48 | 1.15 25 | 1.34 80 | 2.16 86 | 1.09 55 | 1.32 96 | 2.09 106 | 1.12 85 | 1.84 42 | 1.90 37 | 2.23 9 | 1.76 20 | 1.74 24 | 1.94 14 | 1.68 10 | 2.11 24 | 1.74 22 | 1.10 23 | 1.54 28 | 1.20 1 | 1.21 37 | 1.77 41 | 1.08 27 |
DF-Auto [115] | 41.0 | 1.13 74 | 1.50 32 | 1.18 84 | 1.31 76 | 2.01 67 | 1.21 97 | 1.22 13 | 1.59 17 | 1.06 9 | 1.85 53 | 1.93 51 | 2.24 19 | 1.76 20 | 1.73 12 | 1.96 72 | 1.68 10 | 2.04 12 | 1.75 38 | 1.10 23 | 1.59 62 | 1.21 39 | 1.21 37 | 1.77 41 | 1.08 27 |
EPPM w/o HM [88] | 41.2 | 1.09 2 | 1.41 11 | 1.13 2 | 1.16 38 | 1.83 42 | 1.06 6 | 1.31 90 | 2.09 106 | 1.10 60 | 1.83 24 | 1.93 51 | 2.24 19 | 1.75 11 | 1.74 24 | 1.95 35 | 1.72 49 | 2.29 48 | 1.76 58 | 1.11 59 | 1.64 81 | 1.22 75 | 1.21 37 | 1.79 58 | 1.07 2 |
Kuang [131] | 41.8 | 1.11 19 | 1.59 79 | 1.15 25 | 1.17 39 | 1.79 40 | 1.08 39 | 1.26 65 | 1.79 65 | 1.08 43 | 1.85 53 | 1.97 68 | 2.26 59 | 1.76 20 | 1.75 35 | 1.95 35 | 1.69 16 | 2.24 41 | 1.73 11 | 1.11 59 | 1.66 83 | 1.21 39 | 1.19 10 | 1.75 32 | 1.08 27 |
PMF [73] | 42.0 | 1.10 6 | 1.40 9 | 1.13 2 | 1.15 28 | 1.72 30 | 1.06 6 | 1.26 65 | 1.94 91 | 1.10 60 | 1.82 18 | 1.86 22 | 2.24 19 | 1.77 51 | 1.76 53 | 1.94 14 | 1.74 79 | 2.13 27 | 1.80 107 | 1.10 23 | 1.57 45 | 1.22 75 | 1.25 91 | 1.84 86 | 1.07 2 |
Brox et al. [5] | 42.3 | 1.12 39 | 1.52 42 | 1.15 25 | 1.25 62 | 1.95 56 | 1.10 63 | 1.28 80 | 1.98 97 | 1.11 77 | 1.85 53 | 1.87 25 | 2.24 19 | 1.76 20 | 1.75 35 | 1.95 35 | 1.71 41 | 2.34 50 | 1.74 22 | 1.11 59 | 1.60 65 | 1.20 1 | 1.19 10 | 1.69 12 | 1.08 27 |
AggregFlow [97] | 42.4 | 1.14 86 | 1.59 79 | 1.16 74 | 1.21 49 | 1.87 43 | 1.10 63 | 1.20 5 | 1.54 9 | 1.04 1 | 1.84 42 | 1.93 51 | 2.25 43 | 1.76 20 | 1.73 12 | 1.96 72 | 1.73 65 | 2.04 12 | 1.80 107 | 1.10 23 | 1.57 45 | 1.21 39 | 1.20 24 | 1.73 27 | 1.08 27 |
IROF-TV [53] | 42.5 | 1.12 39 | 1.57 68 | 1.15 25 | 1.15 28 | 1.76 36 | 1.06 6 | 1.25 56 | 1.95 92 | 1.08 43 | 1.83 24 | 1.89 31 | 2.26 59 | 1.78 83 | 1.77 76 | 1.97 101 | 1.69 16 | 2.35 52 | 1.72 4 | 1.10 23 | 1.57 45 | 1.21 39 | 1.20 24 | 1.72 24 | 1.08 27 |
Classic+CPF [83] | 43.2 | 1.12 39 | 1.47 23 | 1.14 9 | 1.15 28 | 1.77 38 | 1.06 6 | 1.22 13 | 1.65 39 | 1.07 21 | 1.81 8 | 1.81 2 | 2.22 4 | 1.79 100 | 1.80 108 | 1.95 35 | 1.76 92 | 2.90 112 | 1.76 58 | 1.11 59 | 1.63 76 | 1.20 1 | 1.23 70 | 1.86 93 | 1.07 2 |
Efficient-NL [60] | 44.2 | 1.12 39 | 1.46 20 | 1.15 25 | 1.19 44 | 1.88 45 | 1.07 18 | 1.31 90 | 1.66 41 | 1.12 85 | 1.83 24 | 1.88 28 | 2.23 9 | 1.75 11 | 1.74 24 | 1.94 14 | 1.72 49 | 2.80 99 | 1.73 11 | 1.11 59 | 1.62 75 | 1.21 39 | 1.25 91 | 1.86 93 | 1.08 27 |
p-harmonic [29] | 44.4 | 1.11 19 | 1.51 37 | 1.15 25 | 1.38 88 | 2.19 90 | 1.10 63 | 1.26 65 | 1.99 98 | 1.10 60 | 1.88 76 | 1.98 74 | 2.26 59 | 1.76 20 | 1.75 35 | 1.95 35 | 1.69 16 | 2.19 36 | 1.74 22 | 1.10 23 | 1.57 45 | 1.20 1 | 1.20 24 | 1.73 27 | 1.08 27 |
TC/T-Flow [76] | 45.7 | 1.12 39 | 1.52 42 | 1.15 25 | 1.20 48 | 1.92 52 | 1.08 39 | 1.22 13 | 1.66 41 | 1.07 21 | 1.83 24 | 1.89 31 | 2.25 43 | 1.77 51 | 1.76 53 | 1.96 72 | 1.71 41 | 2.11 24 | 1.75 38 | 1.12 81 | 1.73 98 | 1.22 75 | 1.22 53 | 1.80 66 | 1.08 27 |
SuperFlow [81] | 48.3 | 1.12 39 | 1.54 51 | 1.18 84 | 1.32 77 | 2.02 68 | 1.22 99 | 1.26 65 | 1.76 60 | 1.11 77 | 1.87 65 | 1.91 41 | 2.26 59 | 1.76 20 | 1.74 24 | 1.96 72 | 1.66 2 | 1.87 3 | 1.72 4 | 1.11 59 | 1.59 62 | 1.22 75 | 1.19 10 | 1.70 16 | 1.08 27 |
SIOF [67] | 48.6 | 1.14 86 | 1.60 85 | 1.17 75 | 1.45 95 | 2.27 106 | 1.20 93 | 1.24 44 | 1.76 60 | 1.10 60 | 1.84 42 | 1.93 51 | 2.24 19 | 1.74 3 | 1.71 6 | 1.94 14 | 1.70 25 | 2.07 18 | 1.75 38 | 1.09 7 | 1.54 28 | 1.20 1 | 1.23 70 | 1.79 58 | 1.09 82 |
Sparse Occlusion [54] | 49.9 | 1.12 39 | 1.58 76 | 1.15 25 | 1.28 68 | 2.13 81 | 1.08 39 | 1.23 36 | 1.63 30 | 1.08 43 | 1.84 42 | 1.93 51 | 2.24 19 | 1.77 51 | 1.76 53 | 1.95 35 | 1.74 79 | 2.82 104 | 1.76 58 | 1.10 23 | 1.61 70 | 1.20 1 | 1.23 70 | 1.82 78 | 1.08 27 |
ComplOF-FED-GPU [35] | 50.2 | 1.12 39 | 1.54 51 | 1.15 25 | 1.19 44 | 1.90 48 | 1.08 39 | 1.33 98 | 1.84 75 | 1.12 85 | 1.84 42 | 1.95 63 | 2.25 43 | 1.76 20 | 1.75 35 | 1.95 35 | 1.70 25 | 2.27 44 | 1.75 38 | 1.11 59 | 1.61 70 | 1.21 39 | 1.23 70 | 1.85 90 | 1.08 27 |
CLG-TV [48] | 50.9 | 1.13 74 | 1.56 63 | 1.17 75 | 1.36 84 | 2.20 92 | 1.11 76 | 1.27 77 | 1.88 87 | 1.11 77 | 1.86 61 | 1.92 47 | 2.27 77 | 1.76 20 | 1.74 24 | 1.95 35 | 1.68 10 | 1.97 10 | 1.74 22 | 1.10 23 | 1.54 28 | 1.21 39 | 1.22 53 | 1.77 41 | 1.08 27 |
SVFilterOh [111] | 50.9 | 1.11 19 | 1.45 16 | 1.15 25 | 1.12 12 | 1.61 12 | 1.07 18 | 1.23 36 | 1.55 10 | 1.09 58 | 1.83 24 | 1.84 13 | 2.31 105 | 1.79 100 | 1.78 89 | 2.00 114 | 1.73 65 | 2.33 49 | 1.76 58 | 1.11 59 | 1.49 7 | 1.25 111 | 1.23 70 | 1.77 41 | 1.11 111 |
ALD-Flow [66] | 51.2 | 1.13 74 | 1.57 68 | 1.17 75 | 1.21 49 | 1.93 53 | 1.10 63 | 1.24 44 | 1.84 75 | 1.08 43 | 1.83 24 | 1.90 37 | 2.26 59 | 1.77 51 | 1.75 35 | 1.96 72 | 1.70 25 | 1.96 9 | 1.77 82 | 1.09 7 | 1.51 14 | 1.21 39 | 1.23 70 | 1.82 78 | 1.09 82 |
CostFilter [40] | 53.8 | 1.10 6 | 1.46 20 | 1.13 2 | 1.15 28 | 1.71 26 | 1.06 6 | 1.28 80 | 2.12 108 | 1.10 60 | 1.83 24 | 1.91 41 | 2.24 19 | 1.78 83 | 1.78 89 | 1.95 35 | 1.79 107 | 2.18 35 | 1.86 122 | 1.11 59 | 1.61 70 | 1.22 75 | 1.25 91 | 1.89 103 | 1.07 2 |
OAR-Flow [125] | 54.2 | 1.13 74 | 1.55 57 | 1.15 25 | 1.23 57 | 1.96 58 | 1.10 63 | 1.24 44 | 1.83 72 | 1.07 21 | 1.82 18 | 1.91 41 | 2.25 43 | 1.77 51 | 1.76 53 | 1.96 72 | 1.73 65 | 2.45 60 | 1.77 82 | 1.12 81 | 1.68 88 | 1.22 75 | 1.21 37 | 1.76 36 | 1.08 27 |
EpicFlow [102] | 54.5 | 1.11 19 | 1.57 68 | 1.15 25 | 1.21 49 | 1.95 56 | 1.09 55 | 1.25 56 | 1.81 68 | 1.08 43 | 1.86 61 | 2.00 80 | 2.27 77 | 1.77 51 | 1.76 53 | 1.96 72 | 1.71 41 | 2.50 65 | 1.75 38 | 1.10 23 | 1.66 83 | 1.21 39 | 1.22 53 | 1.90 105 | 1.08 27 |
TCOF [69] | 54.7 | 1.12 39 | 1.54 51 | 1.15 25 | 1.45 95 | 2.31 111 | 1.12 81 | 1.22 13 | 1.63 30 | 1.05 7 | 1.84 42 | 1.92 47 | 2.27 77 | 1.76 20 | 1.75 35 | 1.94 14 | 1.72 49 | 2.58 79 | 1.74 22 | 1.11 59 | 1.66 83 | 1.21 39 | 1.26 101 | 1.88 99 | 1.10 95 |
TC-Flow [46] | 56.8 | 1.11 19 | 1.53 48 | 1.15 25 | 1.22 55 | 1.98 62 | 1.10 63 | 1.26 65 | 1.84 75 | 1.08 43 | 1.87 65 | 2.00 80 | 2.29 91 | 1.77 51 | 1.77 76 | 1.96 72 | 1.73 65 | 2.45 60 | 1.77 82 | 1.10 23 | 1.55 35 | 1.21 39 | 1.22 53 | 1.85 90 | 1.08 27 |
FlowNet2 [122] | 57.8 | 1.23 114 | 1.79 117 | 1.22 106 | 1.28 68 | 1.90 48 | 1.21 97 | 1.27 77 | 1.82 71 | 1.10 60 | 1.85 53 | 2.02 90 | 2.26 59 | 1.78 83 | 1.77 76 | 1.95 35 | 1.70 25 | 2.16 30 | 1.74 22 | 1.10 23 | 1.61 70 | 1.20 1 | 1.20 24 | 1.76 36 | 1.07 2 |
LDOF [28] | 57.8 | 1.17 99 | 1.58 76 | 1.21 101 | 1.34 80 | 1.91 51 | 1.25 106 | 1.30 89 | 2.01 100 | 1.12 85 | 1.88 76 | 2.00 80 | 2.27 77 | 1.76 20 | 1.74 24 | 1.95 35 | 1.69 16 | 2.02 11 | 1.75 38 | 1.10 23 | 1.58 57 | 1.21 39 | 1.21 37 | 1.77 41 | 1.08 27 |
RFlow [90] | 58.6 | 1.12 39 | 1.59 79 | 1.15 25 | 1.34 80 | 2.24 103 | 1.08 39 | 1.25 56 | 1.87 82 | 1.09 58 | 1.87 65 | 2.02 90 | 2.25 43 | 1.77 51 | 1.76 53 | 1.95 35 | 1.68 10 | 2.36 54 | 1.72 4 | 1.11 59 | 1.63 76 | 1.21 39 | 1.25 91 | 1.86 93 | 1.09 82 |
MLDP_OF [89] | 60.4 | 1.11 19 | 1.45 16 | 1.15 25 | 1.21 49 | 1.97 59 | 1.07 18 | 1.22 13 | 1.63 30 | 1.07 21 | 1.87 65 | 1.89 31 | 2.30 97 | 1.78 83 | 1.76 53 | 1.97 101 | 1.85 125 | 2.69 92 | 1.88 124 | 1.11 59 | 1.58 57 | 1.22 75 | 1.23 70 | 1.81 73 | 1.10 95 |
IAOF [50] | 60.9 | 1.21 112 | 1.66 102 | 1.23 112 | 1.89 126 | 2.64 130 | 1.28 110 | 1.26 65 | 1.87 82 | 1.10 60 | 1.91 90 | 1.92 47 | 2.26 59 | 1.76 20 | 1.75 35 | 1.95 35 | 1.70 25 | 2.34 50 | 1.73 11 | 1.10 23 | 1.57 45 | 1.20 1 | 1.21 37 | 1.79 58 | 1.08 27 |
OFH [38] | 61.5 | 1.12 39 | 1.57 68 | 1.15 25 | 1.29 71 | 2.02 68 | 1.09 55 | 1.28 80 | 2.06 103 | 1.10 60 | 1.84 42 | 1.97 68 | 2.24 19 | 1.77 51 | 1.76 53 | 1.94 14 | 1.72 49 | 2.54 68 | 1.76 58 | 1.12 81 | 1.84 107 | 1.22 75 | 1.24 84 | 1.94 112 | 1.08 27 |
Fusion [6] | 62.6 | 1.12 39 | 1.66 102 | 1.15 25 | 1.19 44 | 1.82 41 | 1.08 39 | 1.24 44 | 1.66 41 | 1.10 60 | 1.89 84 | 2.04 98 | 2.25 43 | 1.77 51 | 1.80 108 | 1.93 3 | 1.72 49 | 3.03 118 | 1.72 4 | 1.13 93 | 1.74 100 | 1.22 75 | 1.28 111 | 1.89 103 | 1.08 27 |
CBF [12] | 62.6 | 1.12 39 | 1.55 57 | 1.18 84 | 1.29 71 | 2.02 68 | 1.11 76 | 1.25 56 | 1.66 41 | 1.08 43 | 1.89 84 | 1.93 51 | 2.39 112 | 1.76 20 | 1.73 12 | 2.00 114 | 1.70 25 | 2.13 27 | 1.75 38 | 1.12 81 | 1.60 65 | 1.24 106 | 1.24 84 | 1.73 27 | 1.14 122 |
TF+OM [100] | 63.0 | 1.12 39 | 1.57 68 | 1.17 75 | 1.18 42 | 1.76 36 | 1.15 88 | 1.24 44 | 1.85 78 | 1.07 21 | 1.87 65 | 1.98 74 | 2.26 59 | 1.78 83 | 1.77 76 | 1.96 72 | 1.72 49 | 2.20 37 | 1.77 82 | 1.12 81 | 1.66 83 | 1.22 75 | 1.22 53 | 1.76 36 | 1.10 95 |
ROF-ND [107] | 64.0 | 1.12 39 | 1.47 23 | 1.15 25 | 1.26 64 | 2.08 76 | 1.10 63 | 1.22 13 | 1.63 30 | 1.07 21 | 1.96 103 | 2.24 118 | 2.27 77 | 1.76 20 | 1.74 24 | 1.96 72 | 1.73 65 | 2.91 113 | 1.74 22 | 1.15 108 | 1.71 94 | 1.25 111 | 1.28 111 | 2.01 117 | 1.08 27 |
Modified CLG [34] | 65.7 | 1.13 74 | 1.51 37 | 1.19 93 | 1.58 113 | 2.23 99 | 1.34 114 | 1.31 90 | 2.32 114 | 1.13 93 | 1.88 76 | 2.00 80 | 2.24 19 | 1.77 51 | 1.76 53 | 1.96 72 | 1.72 49 | 2.49 62 | 1.76 58 | 1.10 23 | 1.57 45 | 1.21 39 | 1.21 37 | 1.79 58 | 1.08 27 |
Complementary OF [21] | 66.6 | 1.11 19 | 1.60 85 | 1.14 9 | 1.18 42 | 1.90 48 | 1.08 39 | 1.38 108 | 1.81 68 | 1.15 97 | 1.86 61 | 1.99 77 | 2.26 59 | 1.77 51 | 1.78 89 | 1.94 14 | 1.72 49 | 2.54 68 | 1.76 58 | 1.13 93 | 1.83 106 | 1.21 39 | 1.29 114 | 2.17 124 | 1.09 82 |
TriFlow [95] | 66.8 | 1.15 91 | 1.70 108 | 1.18 84 | 1.37 87 | 2.09 77 | 1.24 103 | 1.25 56 | 1.87 82 | 1.07 21 | 1.85 53 | 1.97 68 | 2.24 19 | 1.79 100 | 1.79 103 | 1.96 72 | 1.73 65 | 2.35 52 | 1.75 38 | 1.11 59 | 1.61 70 | 1.21 39 | 1.23 70 | 1.79 58 | 1.08 27 |
Local-TV-L1 [65] | 67.7 | 1.19 105 | 1.61 89 | 1.23 112 | 1.49 103 | 2.21 94 | 1.23 101 | 1.23 36 | 1.69 50 | 1.07 21 | 1.92 94 | 1.96 67 | 2.39 112 | 1.77 51 | 1.75 35 | 1.96 72 | 1.82 116 | 2.12 26 | 1.89 125 | 1.10 23 | 1.56 40 | 1.21 39 | 1.19 10 | 1.68 9 | 1.10 95 |
FlowNetS+ft+v [112] | 68.8 | 1.15 91 | 1.56 63 | 1.20 95 | 1.48 100 | 2.24 103 | 1.25 106 | 1.28 80 | 1.96 93 | 1.11 77 | 1.86 61 | 1.94 60 | 2.26 59 | 1.78 83 | 1.77 76 | 1.96 72 | 1.70 25 | 2.14 29 | 1.75 38 | 1.12 81 | 1.68 88 | 1.21 39 | 1.22 53 | 1.78 51 | 1.08 27 |
Occlusion-TV-L1 [63] | 68.8 | 1.12 39 | 1.56 63 | 1.17 75 | 1.40 90 | 2.33 113 | 1.10 63 | 1.26 65 | 1.96 93 | 1.11 77 | 1.91 90 | 2.10 102 | 2.29 91 | 1.76 20 | 1.74 24 | 1.95 35 | 1.74 79 | 2.57 76 | 1.79 102 | 1.12 81 | 1.57 45 | 1.22 75 | 1.22 53 | 1.81 73 | 1.08 27 |
F-TV-L1 [15] | 68.8 | 1.18 101 | 1.64 97 | 1.21 101 | 1.43 94 | 2.23 99 | 1.13 87 | 1.28 80 | 1.97 96 | 1.12 85 | 1.88 76 | 2.00 80 | 2.29 91 | 1.76 20 | 1.77 76 | 1.93 3 | 1.70 25 | 2.10 22 | 1.76 58 | 1.11 59 | 1.63 76 | 1.22 75 | 1.21 37 | 1.71 19 | 1.10 95 |
Classic++ [32] | 70.4 | 1.13 74 | 1.59 79 | 1.17 75 | 1.29 71 | 2.10 78 | 1.09 55 | 1.26 65 | 1.86 81 | 1.10 60 | 1.89 84 | 2.01 88 | 2.27 77 | 1.77 51 | 1.76 53 | 1.95 35 | 1.77 100 | 2.55 72 | 1.81 110 | 1.11 59 | 1.60 65 | 1.21 39 | 1.23 70 | 1.80 66 | 1.09 82 |
SimpleFlow [49] | 70.7 | 1.12 39 | 1.55 57 | 1.15 25 | 1.27 66 | 2.02 68 | 1.08 39 | 1.37 107 | 1.85 78 | 1.12 85 | 1.83 24 | 1.89 31 | 2.26 59 | 1.77 51 | 1.76 53 | 1.95 35 | 1.77 100 | 3.34 121 | 1.76 58 | 1.17 118 | 2.76 128 | 1.24 106 | 1.26 101 | 2.07 120 | 1.08 27 |
Black & Anandan [4] | 73.6 | 1.19 105 | 1.64 97 | 1.22 106 | 1.64 115 | 2.37 117 | 1.24 103 | 1.41 112 | 2.17 110 | 1.17 105 | 1.92 94 | 2.01 88 | 2.25 43 | 1.78 83 | 1.78 89 | 1.96 72 | 1.69 16 | 2.17 32 | 1.74 22 | 1.11 59 | 1.63 76 | 1.20 1 | 1.22 53 | 1.77 41 | 1.08 27 |
Aniso-Texture [82] | 74.5 | 1.11 19 | 1.52 42 | 1.15 25 | 1.40 90 | 2.30 108 | 1.10 63 | 1.33 98 | 1.73 56 | 1.10 60 | 1.91 90 | 2.14 110 | 2.30 97 | 1.79 100 | 1.79 103 | 1.97 101 | 1.82 116 | 3.74 131 | 1.79 102 | 1.10 23 | 1.55 35 | 1.20 1 | 1.25 91 | 1.88 99 | 1.08 27 |
HBM-GC [105] | 74.6 | 1.15 91 | 1.57 68 | 1.19 93 | 1.22 55 | 1.97 59 | 1.09 55 | 1.20 5 | 1.45 2 | 1.08 43 | 1.87 65 | 1.94 60 | 2.29 91 | 1.81 112 | 1.80 108 | 2.02 122 | 1.81 112 | 3.58 125 | 1.79 102 | 1.12 81 | 1.52 18 | 1.25 111 | 1.23 70 | 1.74 31 | 1.11 111 |
Steered-L1 [118] | 75.0 | 1.11 19 | 1.59 79 | 1.15 25 | 1.21 49 | 1.94 55 | 1.10 63 | 1.33 98 | 1.76 60 | 1.15 97 | 1.93 98 | 2.04 98 | 2.34 107 | 1.78 83 | 1.78 89 | 1.95 35 | 1.73 65 | 2.51 66 | 1.78 92 | 1.13 93 | 1.72 96 | 1.22 75 | 1.24 84 | 1.82 78 | 1.10 95 |
GraphCuts [14] | 75.0 | 1.20 109 | 1.76 115 | 1.20 95 | 1.28 68 | 1.88 45 | 1.23 101 | 1.55 121 | 1.64 36 | 1.19 106 | 1.93 98 | 2.03 97 | 2.29 91 | 1.76 20 | 1.75 35 | 1.93 3 | 1.67 3 | 2.42 55 | 1.70 1 | 1.14 101 | 1.78 105 | 1.23 101 | 1.26 101 | 1.88 99 | 1.10 95 |
CRTflow [80] | 75.5 | 1.15 91 | 1.62 91 | 1.18 84 | 1.34 80 | 2.21 94 | 1.10 63 | 1.32 96 | 2.08 104 | 1.19 106 | 1.87 65 | 1.95 63 | 2.32 106 | 1.78 83 | 1.77 76 | 1.96 72 | 1.71 41 | 2.06 14 | 1.76 58 | 1.11 59 | 1.63 76 | 1.22 75 | 1.22 53 | 1.80 66 | 1.10 95 |
Adaptive [20] | 75.8 | 1.14 86 | 1.63 94 | 1.18 84 | 1.46 97 | 2.36 116 | 1.11 76 | 1.26 65 | 1.88 87 | 1.10 60 | 1.87 65 | 1.97 68 | 2.27 77 | 1.78 83 | 1.77 76 | 1.95 35 | 1.74 79 | 2.52 67 | 1.78 92 | 1.11 59 | 1.66 83 | 1.20 1 | 1.24 84 | 1.85 90 | 1.10 95 |
2D-CLG [1] | 77.5 | 1.18 101 | 1.58 76 | 1.22 106 | 1.67 117 | 2.26 105 | 1.41 121 | 1.38 108 | 2.08 104 | 1.19 106 | 1.94 101 | 2.02 90 | 2.25 43 | 1.77 51 | 1.75 35 | 1.95 35 | 1.71 41 | 2.63 86 | 1.75 38 | 1.13 93 | 1.84 107 | 1.22 75 | 1.22 53 | 1.77 41 | 1.08 27 |
Nguyen [33] | 77.8 | 1.25 116 | 1.63 94 | 1.30 120 | 1.77 124 | 2.38 119 | 1.36 115 | 1.31 90 | 2.42 116 | 1.14 95 | 1.96 103 | 2.06 101 | 2.26 59 | 1.77 51 | 1.76 53 | 1.94 14 | 1.69 16 | 2.43 59 | 1.73 11 | 1.14 101 | 1.92 112 | 1.22 75 | 1.21 37 | 1.79 58 | 1.08 27 |
AdaConv-v1 [126] | 78.9 | 1.30 121 | 1.76 115 | 1.33 121 | 1.57 111 | 2.05 73 | 1.58 127 | 1.55 121 | 2.33 115 | 1.48 129 | 2.16 124 | 2.37 123 | 2.46 120 | 1.72 1 | 1.68 1 | 1.92 1 | 1.67 3 | 1.92 8 | 1.73 11 | 1.15 108 | 1.73 98 | 1.31 129 | 1.18 4 | 1.60 2 | 1.16 128 |
Correlation Flow [75] | 79.1 | 1.11 19 | 1.51 37 | 1.13 2 | 1.33 79 | 2.23 99 | 1.08 39 | 1.24 44 | 1.63 30 | 1.08 43 | 1.87 65 | 1.91 41 | 2.30 97 | 1.81 112 | 1.78 89 | 2.06 127 | 1.82 116 | 3.47 123 | 1.79 102 | 1.15 108 | 1.97 113 | 1.25 111 | 1.26 101 | 1.91 107 | 1.10 95 |
CNN-flow-warp+ref [117] | 79.3 | 1.12 39 | 1.47 23 | 1.18 84 | 1.36 84 | 2.14 82 | 1.15 88 | 1.35 101 | 2.22 111 | 1.14 95 | 2.05 117 | 2.19 115 | 2.41 116 | 1.78 83 | 1.77 76 | 1.97 101 | 1.72 49 | 2.49 62 | 1.76 58 | 1.14 101 | 1.99 114 | 1.22 75 | 1.21 37 | 1.80 66 | 1.08 27 |
TriangleFlow [30] | 80.1 | 1.15 91 | 1.66 102 | 1.17 75 | 1.32 77 | 2.11 79 | 1.09 55 | 1.29 86 | 1.81 68 | 1.13 93 | 1.89 84 | 2.02 90 | 2.30 97 | 1.76 20 | 1.76 53 | 1.93 3 | 1.74 79 | 2.67 89 | 1.75 38 | 1.14 101 | 2.02 115 | 1.24 106 | 1.31 118 | 2.13 122 | 1.09 82 |
BriefMatch [124] | 80.2 | 1.12 39 | 1.55 57 | 1.15 25 | 1.24 58 | 1.93 53 | 1.15 88 | 1.36 103 | 1.73 56 | 1.19 106 | 2.04 116 | 2.11 105 | 2.53 127 | 1.77 51 | 1.76 53 | 1.98 111 | 1.92 128 | 2.59 80 | 1.97 128 | 1.11 59 | 1.60 65 | 1.22 75 | 1.23 70 | 1.82 78 | 1.10 95 |
Shiralkar [42] | 81.1 | 1.13 74 | 1.63 94 | 1.15 25 | 1.41 92 | 2.21 94 | 1.09 55 | 1.36 103 | 2.54 119 | 1.15 97 | 1.98 111 | 2.23 117 | 2.24 19 | 1.77 51 | 1.78 89 | 1.92 1 | 1.76 92 | 2.85 108 | 1.78 92 | 1.15 108 | 2.13 120 | 1.22 75 | 1.25 91 | 2.02 118 | 1.07 2 |
HBpMotionGpu [43] | 81.1 | 1.24 115 | 1.80 119 | 1.28 118 | 1.68 119 | 2.42 123 | 1.38 116 | 1.23 36 | 1.69 50 | 1.10 60 | 1.95 102 | 2.15 113 | 2.30 97 | 1.77 51 | 1.77 76 | 1.96 72 | 1.75 86 | 2.57 76 | 1.78 92 | 1.09 7 | 1.50 10 | 1.20 1 | 1.26 101 | 1.86 93 | 1.12 114 |
IAOF2 [51] | 82.1 | 1.19 105 | 1.69 107 | 1.20 95 | 1.50 107 | 2.41 121 | 1.20 93 | 1.25 56 | 1.83 72 | 1.11 77 | 1.91 90 | 2.02 90 | 2.28 88 | 1.81 112 | 1.85 119 | 1.96 72 | 1.74 79 | 2.88 111 | 1.75 38 | 1.10 23 | 1.57 45 | 1.20 1 | 1.26 101 | 1.84 86 | 1.09 82 |
BlockOverlap [61] | 83.9 | 1.20 109 | 1.60 85 | 1.25 115 | 1.49 103 | 2.18 88 | 1.32 113 | 1.26 65 | 1.60 20 | 1.12 85 | 1.96 103 | 1.97 68 | 2.48 121 | 1.80 106 | 1.77 76 | 2.04 126 | 1.80 109 | 2.27 44 | 1.86 122 | 1.12 81 | 1.54 28 | 1.26 118 | 1.19 10 | 1.66 4 | 1.12 114 |
ACK-Prior [27] | 83.9 | 1.11 19 | 1.54 51 | 1.14 9 | 1.17 39 | 1.87 43 | 1.07 18 | 1.38 108 | 1.74 59 | 1.15 97 | 1.88 76 | 1.98 74 | 2.27 77 | 1.81 112 | 1.80 108 | 2.02 122 | 1.81 112 | 2.70 93 | 1.82 116 | 1.17 118 | 1.69 92 | 1.27 121 | 1.33 122 | 1.93 110 | 1.13 118 |
Ad-TV-NDC [36] | 85.9 | 1.34 122 | 1.70 108 | 1.38 122 | 1.68 119 | 2.33 113 | 1.38 116 | 1.26 65 | 1.87 82 | 1.10 60 | 1.97 109 | 1.99 77 | 2.34 107 | 1.80 106 | 1.79 103 | 1.97 101 | 1.75 86 | 2.06 14 | 1.82 116 | 1.11 59 | 1.59 62 | 1.21 39 | 1.22 53 | 1.73 27 | 1.10 95 |
LocallyOriented [52] | 86.3 | 1.15 91 | 1.62 91 | 1.20 95 | 1.48 100 | 2.30 108 | 1.15 88 | 1.31 90 | 1.96 93 | 1.11 77 | 1.92 94 | 2.10 102 | 2.29 91 | 1.77 51 | 1.77 76 | 1.95 35 | 1.82 116 | 2.56 74 | 1.85 120 | 1.12 81 | 1.68 88 | 1.21 39 | 1.25 91 | 1.87 98 | 1.09 82 |
TV-L1-improved [17] | 86.7 | 1.13 74 | 1.62 91 | 1.18 84 | 1.46 97 | 2.35 115 | 1.12 81 | 1.35 101 | 1.80 66 | 1.15 97 | 1.88 76 | 2.00 80 | 2.27 77 | 1.78 83 | 1.78 89 | 1.95 35 | 1.75 86 | 2.70 93 | 1.77 82 | 1.14 101 | 2.09 118 | 1.22 75 | 1.25 91 | 1.86 93 | 1.10 95 |
StereoOF-V1MT [119] | 90.1 | 1.14 86 | 1.72 112 | 1.15 25 | 1.36 84 | 2.15 83 | 1.08 39 | 1.46 116 | 2.45 117 | 1.19 106 | 2.11 123 | 2.33 122 | 2.37 111 | 1.80 106 | 1.83 117 | 1.95 35 | 1.81 112 | 2.84 106 | 1.82 116 | 1.17 118 | 2.07 117 | 1.24 106 | 1.21 37 | 1.80 66 | 1.07 2 |
Filter Flow [19] | 92.5 | 1.18 101 | 1.61 89 | 1.21 101 | 1.57 111 | 2.27 106 | 1.38 116 | 1.27 77 | 1.85 78 | 1.12 85 | 1.96 103 | 1.97 68 | 2.35 110 | 1.79 100 | 1.78 89 | 2.00 114 | 1.73 65 | 2.28 46 | 1.78 92 | 1.13 93 | 1.68 88 | 1.22 75 | 1.27 109 | 1.84 86 | 1.13 118 |
Rannacher [23] | 92.8 | 1.14 86 | 1.65 99 | 1.18 84 | 1.47 99 | 2.39 120 | 1.12 81 | 1.36 103 | 2.00 99 | 1.16 104 | 1.88 76 | 2.04 98 | 2.28 88 | 1.79 100 | 1.78 89 | 1.95 35 | 1.76 92 | 2.74 97 | 1.78 92 | 1.14 101 | 2.05 116 | 1.22 75 | 1.25 91 | 1.91 107 | 1.10 95 |
TI-DOFE [24] | 92.8 | 1.37 124 | 1.74 113 | 1.41 125 | 1.91 127 | 2.51 128 | 1.51 125 | 1.41 112 | 2.56 120 | 1.20 115 | 2.06 119 | 2.13 108 | 2.30 97 | 1.78 83 | 1.79 103 | 1.95 35 | 1.69 16 | 2.16 30 | 1.73 11 | 1.13 93 | 1.71 94 | 1.22 75 | 1.27 109 | 1.83 83 | 1.09 82 |
Horn & Schunck [3] | 94.0 | 1.19 105 | 1.65 99 | 1.22 106 | 1.68 119 | 2.41 121 | 1.28 110 | 1.47 117 | 2.45 117 | 1.22 117 | 2.02 113 | 2.14 110 | 2.27 77 | 1.80 106 | 1.80 108 | 1.97 101 | 1.70 25 | 2.28 46 | 1.74 22 | 1.14 101 | 1.77 103 | 1.22 75 | 1.25 91 | 1.84 86 | 1.09 82 |
SegOF [10] | 94.1 | 1.15 91 | 1.60 85 | 1.20 95 | 1.38 88 | 2.07 75 | 1.20 93 | 1.48 118 | 2.29 112 | 1.21 116 | 1.93 98 | 2.30 121 | 2.25 43 | 1.78 83 | 1.78 89 | 1.96 72 | 1.77 100 | 3.01 117 | 1.78 92 | 1.18 123 | 2.46 127 | 1.25 111 | 1.23 70 | 1.94 112 | 1.08 27 |
StereoFlow [44] | 94.7 | 1.47 127 | 2.09 130 | 1.38 122 | 1.76 123 | 2.42 123 | 1.38 116 | 1.26 65 | 2.03 102 | 1.10 60 | 1.89 84 | 2.00 80 | 2.26 59 | 2.00 129 | 2.23 129 | 1.98 111 | 1.84 124 | 3.59 126 | 1.76 58 | 1.09 7 | 1.55 35 | 1.21 39 | 1.33 122 | 2.05 119 | 1.09 82 |
UnFlow [129] | 96.5 | 1.22 113 | 1.80 119 | 1.22 106 | 1.54 109 | 2.19 90 | 1.22 99 | 1.40 111 | 2.64 121 | 1.19 106 | 1.89 84 | 2.11 105 | 2.24 19 | 1.83 117 | 1.87 121 | 1.96 72 | 1.79 107 | 3.47 123 | 1.75 38 | 1.12 81 | 1.77 103 | 1.21 39 | 1.38 126 | 2.23 125 | 1.09 82 |
NL-TV-NCC [25] | 96.8 | 1.13 74 | 1.59 79 | 1.15 25 | 1.27 66 | 2.15 83 | 1.09 55 | 1.31 90 | 1.91 90 | 1.15 97 | 1.96 103 | 2.13 108 | 2.39 112 | 1.85 122 | 1.80 108 | 2.13 129 | 1.77 100 | 2.81 102 | 1.78 92 | 1.16 117 | 1.76 101 | 1.28 123 | 1.31 118 | 1.90 105 | 1.15 125 |
Dynamic MRF [7] | 97.5 | 1.12 39 | 1.68 105 | 1.15 25 | 1.30 74 | 2.21 94 | 1.10 63 | 1.41 112 | 2.71 122 | 1.19 106 | 2.10 122 | 2.38 124 | 2.42 118 | 1.78 83 | 1.80 108 | 1.95 35 | 1.82 116 | 3.60 127 | 1.80 107 | 1.17 118 | 2.24 122 | 1.23 101 | 1.28 111 | 1.95 114 | 1.10 95 |
SPSA-learn [13] | 98.2 | 1.18 101 | 1.70 108 | 1.21 101 | 1.50 107 | 2.22 98 | 1.25 106 | 1.44 115 | 2.14 109 | 1.19 106 | 1.96 103 | 2.02 90 | 2.25 43 | 1.80 106 | 1.82 115 | 1.96 72 | 1.73 65 | 2.80 99 | 1.75 38 | 1.27 130 | 3.84 131 | 1.32 130 | 1.44 128 | 2.80 130 | 1.08 27 |
Bartels [41] | 99.5 | 1.16 98 | 1.68 105 | 1.21 101 | 1.30 74 | 2.11 79 | 1.20 93 | 1.28 80 | 1.80 66 | 1.15 97 | 2.00 112 | 2.14 110 | 2.51 125 | 1.84 118 | 1.78 89 | 2.14 131 | 2.07 130 | 2.72 95 | 2.13 131 | 1.13 93 | 1.56 40 | 1.30 126 | 1.26 101 | 1.80 66 | 1.17 129 |
GroupFlow [9] | 109.2 | 1.28 120 | 2.00 127 | 1.26 117 | 1.49 103 | 2.16 86 | 1.28 110 | 1.62 125 | 2.95 127 | 1.31 123 | 1.97 109 | 2.26 120 | 2.30 97 | 1.87 128 | 1.94 128 | 1.97 101 | 1.83 121 | 3.65 129 | 1.78 92 | 1.15 108 | 2.15 121 | 1.22 75 | 1.34 124 | 2.29 127 | 1.07 2 |
2bit-BM-tele [98] | 110.7 | 1.20 109 | 1.71 111 | 1.25 115 | 1.49 103 | 2.37 117 | 1.26 109 | 1.29 86 | 1.70 52 | 1.19 106 | 2.02 113 | 2.16 114 | 2.52 126 | 1.86 127 | 1.84 118 | 2.10 128 | 2.00 129 | 3.60 127 | 2.00 129 | 1.29 131 | 3.46 130 | 1.38 131 | 1.24 84 | 1.75 32 | 1.18 130 |
Learning Flow [11] | 111.0 | 1.17 99 | 1.75 114 | 1.20 95 | 1.48 100 | 2.32 112 | 1.15 88 | 1.51 120 | 2.81 125 | 1.22 117 | 2.05 117 | 2.24 118 | 2.40 115 | 1.85 122 | 1.88 122 | 2.03 124 | 1.78 105 | 2.67 89 | 1.81 110 | 1.15 108 | 1.87 111 | 1.23 101 | 1.34 124 | 1.97 115 | 1.12 114 |
SILK [79] | 111.4 | 1.26 118 | 1.80 119 | 1.29 119 | 1.78 125 | 2.43 125 | 1.38 116 | 1.59 124 | 2.72 123 | 1.26 121 | 2.08 120 | 2.21 116 | 2.41 116 | 1.80 106 | 1.82 115 | 1.97 101 | 1.85 125 | 2.59 80 | 1.92 127 | 1.13 93 | 1.76 101 | 1.23 101 | 1.26 101 | 1.88 99 | 1.09 82 |
Heeger++ [104] | 112.4 | 1.26 118 | 1.96 126 | 1.22 106 | 1.55 110 | 2.15 83 | 1.24 103 | 1.96 128 | 3.35 129 | 1.39 127 | 2.27 125 | 2.43 125 | 2.50 123 | 1.85 122 | 1.90 126 | 1.98 111 | 1.83 121 | 2.97 116 | 1.81 110 | 1.20 125 | 2.36 123 | 1.23 101 | 1.29 114 | 2.16 123 | 1.07 2 |
SLK [47] | 113.1 | 1.34 122 | 1.79 117 | 1.39 124 | 1.72 122 | 2.23 99 | 1.45 123 | 1.65 127 | 2.79 124 | 1.31 123 | 2.30 127 | 2.55 129 | 2.45 119 | 1.84 118 | 1.91 127 | 1.94 14 | 1.77 100 | 2.81 102 | 1.77 82 | 1.20 125 | 2.38 124 | 1.26 118 | 1.30 116 | 2.12 121 | 1.11 111 |
HCIC-L [99] | 113.7 | 1.68 131 | 2.05 129 | 1.76 131 | 1.59 114 | 2.05 73 | 1.57 126 | 1.48 118 | 2.02 101 | 1.25 120 | 2.03 115 | 2.12 107 | 2.34 107 | 1.81 112 | 1.79 103 | 2.03 124 | 1.81 112 | 2.59 80 | 1.82 116 | 1.17 118 | 1.72 96 | 1.28 123 | 1.48 129 | 2.25 126 | 1.13 118 |
Adaptive flow [45] | 115.8 | 1.46 125 | 1.85 122 | 1.50 126 | 1.91 127 | 2.49 126 | 1.66 129 | 1.36 103 | 1.90 89 | 1.22 117 | 2.08 120 | 2.10 102 | 2.49 122 | 1.85 122 | 1.88 122 | 2.00 114 | 1.83 121 | 3.46 122 | 1.81 110 | 1.15 108 | 1.65 82 | 1.28 123 | 1.30 116 | 1.93 110 | 1.14 122 |
FFV1MT [106] | 118.5 | 1.25 116 | 1.93 124 | 1.24 114 | 1.65 116 | 2.20 92 | 1.41 121 | 1.96 128 | 4.00 130 | 1.44 128 | 2.27 125 | 2.43 125 | 2.50 123 | 1.85 122 | 1.88 122 | 2.00 114 | 1.80 109 | 2.65 88 | 1.81 110 | 1.21 127 | 2.44 126 | 1.25 111 | 1.42 127 | 2.32 128 | 1.13 118 |
FOLKI [16] | 119.9 | 1.59 128 | 1.94 125 | 1.70 128 | 1.92 129 | 2.49 126 | 1.58 127 | 1.56 123 | 3.12 128 | 1.34 126 | 2.42 129 | 2.47 127 | 2.74 130 | 1.84 118 | 1.89 125 | 2.00 114 | 1.80 109 | 2.42 55 | 1.85 120 | 1.18 123 | 2.09 118 | 1.26 118 | 1.32 120 | 1.92 109 | 1.14 122 |
PGAM+LK [55] | 120.7 | 1.46 125 | 2.04 128 | 1.50 126 | 1.67 117 | 2.30 108 | 1.47 124 | 1.62 125 | 2.93 126 | 1.33 125 | 2.38 128 | 2.52 128 | 2.71 128 | 1.84 118 | 1.86 120 | 2.00 114 | 1.88 127 | 3.05 119 | 1.89 125 | 1.15 108 | 1.84 107 | 1.25 111 | 1.32 120 | 1.97 115 | 1.15 125 |
Pyramid LK [2] | 122.5 | 1.63 129 | 1.88 123 | 1.73 130 | 2.11 130 | 2.56 129 | 1.80 130 | 2.58 130 | 2.31 113 | 1.71 130 | 3.26 131 | 5.81 130 | 3.03 131 | 2.01 130 | 2.30 130 | 1.97 101 | 1.78 105 | 2.59 80 | 1.81 110 | 1.21 127 | 2.42 125 | 1.27 121 | 1.63 130 | 3.08 131 | 1.12 114 |
Periodicity [78] | 130.0 | 1.64 130 | 2.35 131 | 1.70 128 | 2.45 131 | 2.65 131 | 2.00 131 | 2.96 131 | 4.90 131 | 2.28 131 | 2.73 130 | 5.99 131 | 2.71 128 | 2.16 131 | 2.49 131 | 2.13 129 | 2.13 131 | 3.66 130 | 2.11 130 | 1.24 129 | 2.90 129 | 1.30 126 | 1.66 131 | 2.56 129 | 1.28 131 |
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. |