Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
Average 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 | |
SoftsplatAug [190] | 2.6 | 1.98 1 | 2.91 1 | 1.06 3 | 2.55 2 | 3.38 2 | 1.14 2 | 1.87 3 | 2.69 2 | 1.06 2 | 3.88 3 | 4.65 3 | 2.70 3 | 7.24 1 | 8.90 1 | 2.98 6 | 3.90 3 | 7.06 3 | 1.97 3 | 5.24 3 | 11.4 3 | 1.38 5 | 5.22 2 | 8.02 2 | 1.50 4 |
SoftSplat [169] | 5.3 | 2.06 2 | 3.06 3 | 1.14 9 | 2.80 5 | 3.91 6 | 1.24 3 | 1.99 5 | 2.73 3 | 1.21 6 | 3.84 2 | 4.64 2 | 2.69 2 | 8.10 18 | 10.0 18 | 2.96 2 | 4.10 5 | 7.53 5 | 1.98 6 | 5.49 5 | 12.1 5 | 1.39 6 | 5.40 3 | 8.33 3 | 1.50 4 |
IFRNet [193] | 8.0 | 2.08 3 | 3.03 2 | 1.16 12 | 2.78 4 | 3.73 4 | 1.38 47 | 1.74 1 | 2.58 1 | 1.04 1 | 3.96 4 | 4.78 4 | 2.96 10 | 7.55 5 | 9.28 5 | 3.12 22 | 4.42 9 | 8.20 9 | 2.02 11 | 5.56 7 | 12.3 6 | 1.37 2 | 5.64 8 | 8.70 8 | 1.51 6 |
EAFI [186] | 8.2 | 2.10 5 | 3.19 4 | 1.08 5 | 2.54 1 | 3.23 1 | 1.13 1 | 1.77 2 | 2.79 5 | 1.08 3 | 3.82 1 | 4.51 1 | 2.64 1 | 9.04 26 | 11.3 25 | 3.01 9 | 4.82 23 | 9.09 23 | 1.97 3 | 5.89 14 | 13.1 15 | 1.37 2 | 5.77 10 | 8.91 10 | 1.51 6 |
DistillNet [184] | 10.0 | 2.11 6 | 3.29 5 | 1.15 11 | 2.71 3 | 3.64 3 | 1.28 16 | 1.96 4 | 2.73 3 | 1.14 4 | 4.05 5 | 4.96 6 | 2.81 5 | 7.81 9 | 9.66 9 | 3.06 14 | 4.79 21 | 9.03 20 | 2.01 9 | 6.04 16 | 13.4 18 | 1.43 14 | 6.05 11 | 9.33 11 | 1.56 16 |
SepConv++ [185] | 13.0 | 2.39 23 | 4.17 25 | 1.20 24 | 2.98 8 | 4.21 9 | 1.28 16 | 3.34 24 | 3.23 8 | 2.20 88 | 4.49 12 | 5.81 17 | 2.87 7 | 7.64 7 | 9.42 7 | 2.97 3 | 3.77 2 | 6.80 2 | 1.96 1 | 5.26 4 | 11.6 4 | 1.36 1 | 5.71 9 | 8.86 9 | 1.45 1 |
FGME [158] | 13.2 | 2.08 3 | 3.34 7 | 0.98 1 | 3.32 22 | 4.43 13 | 1.63 112 | 2.46 6 | 3.28 9 | 1.41 17 | 4.08 6 | 4.85 5 | 3.05 18 | 7.36 3 | 9.08 3 | 3.03 11 | 4.17 7 | 7.62 7 | 2.06 22 | 4.95 2 | 10.7 2 | 1.44 15 | 5.45 4 | 8.41 5 | 1.57 17 |
BMBC [171] | 15.0 | 2.30 15 | 3.40 9 | 1.20 24 | 3.07 9 | 4.25 10 | 1.41 59 | 3.17 20 | 4.19 31 | 1.66 39 | 4.24 8 | 5.28 8 | 2.85 6 | 7.79 8 | 9.62 8 | 3.14 24 | 4.08 4 | 7.47 4 | 2.02 11 | 5.63 8 | 12.4 8 | 1.40 8 | 5.55 6 | 8.58 6 | 1.61 26 |
IDIAL [192] | 15.9 | 2.23 8 | 3.62 12 | 1.14 9 | 3.22 13 | 4.54 21 | 1.46 76 | 2.79 9 | 2.97 6 | 1.23 7 | 4.49 12 | 5.64 13 | 2.94 9 | 8.36 20 | 10.4 20 | 2.97 3 | 4.53 12 | 8.43 12 | 1.99 7 | 6.17 18 | 13.3 17 | 1.50 24 | 6.31 17 | 9.67 15 | 1.58 21 |
STAR-Net [164] | 17.1 | 2.18 7 | 3.37 8 | 1.21 42 | 3.46 31 | 4.88 31 | 1.47 79 | 3.04 18 | 3.53 15 | 1.58 31 | 4.41 11 | 5.44 11 | 2.76 4 | 7.51 4 | 9.27 4 | 2.98 6 | 4.65 13 | 8.72 13 | 1.99 7 | 6.21 20 | 13.4 18 | 1.41 9 | 6.17 13 | 9.45 13 | 1.49 3 |
EDSC [173] | 18.8 | 2.32 19 | 3.90 17 | 1.16 12 | 3.10 10 | 4.38 12 | 1.51 88 | 2.98 15 | 3.54 16 | 1.36 15 | 4.49 12 | 5.74 14 | 3.16 31 | 8.05 17 | 9.96 17 | 3.08 16 | 4.89 24 | 9.28 24 | 2.02 11 | 5.55 6 | 12.3 6 | 1.41 9 | 6.42 22 | 9.99 23 | 1.55 15 |
AdaCoF [165] | 22.8 | 2.41 25 | 4.10 24 | 1.26 135 | 3.10 10 | 4.32 11 | 1.43 65 | 3.48 29 | 3.31 10 | 1.78 56 | 4.84 23 | 5.94 24 | 2.93 8 | 8.68 23 | 10.8 22 | 3.14 24 | 4.13 6 | 7.59 6 | 1.97 3 | 5.77 12 | 12.9 13 | 1.37 2 | 5.60 7 | 8.67 7 | 1.48 2 |
DSepConv [162] | 27.5 | 2.47 26 | 4.39 31 | 1.21 42 | 3.32 22 | 4.60 23 | 1.72 133 | 3.28 21 | 3.66 17 | 1.50 24 | 5.11 30 | 6.36 28 | 3.23 66 | 7.85 10 | 9.69 10 | 3.11 20 | 4.68 15 | 8.78 15 | 2.04 19 | 5.65 9 | 12.5 9 | 1.44 15 | 6.54 27 | 10.2 27 | 1.58 21 |
GDCN [172] | 29.6 | 2.31 17 | 3.98 21 | 1.10 7 | 3.80 87 | 5.17 48 | 1.54 93 | 2.92 13 | 3.78 22 | 1.43 19 | 5.59 82 | 6.01 26 | 3.24 70 | 9.02 25 | 11.3 25 | 3.10 18 | 4.66 14 | 8.75 14 | 2.08 23 | 5.75 11 | 12.7 10 | 1.42 12 | 6.40 21 | 9.98 22 | 1.53 10 |
STSR [170] | 29.9 | 2.31 17 | 3.82 15 | 1.19 17 | 2.94 6 | 3.90 5 | 1.93 169 | 2.92 13 | 3.44 14 | 1.81 57 | 4.29 10 | 5.41 9 | 3.27 79 | 9.51 29 | 11.9 29 | 3.06 14 | 5.38 34 | 10.3 34 | 2.10 24 | 6.75 29 | 15.3 31 | 1.50 24 | 6.43 24 | 9.99 23 | 1.54 11 |
ProBoost-Net [191] | 32.1 | 2.27 12 | 3.90 17 | 1.07 4 | 3.70 71 | 5.05 40 | 1.78 144 | 2.98 15 | 3.38 12 | 1.65 38 | 4.53 16 | 5.76 15 | 3.33 106 | 8.75 24 | 10.9 24 | 3.25 29 | 5.01 25 | 9.45 25 | 2.14 26 | 6.02 15 | 13.5 20 | 1.45 17 | 6.50 26 | 10.1 26 | 1.59 23 |
MAF-net [163] | 32.2 | 2.23 8 | 3.84 16 | 1.08 5 | 3.53 42 | 4.85 30 | 1.78 144 | 2.83 11 | 3.70 18 | 1.58 31 | 4.83 22 | 5.88 18 | 3.31 99 | 9.44 28 | 11.8 28 | 3.27 30 | 5.27 29 | 10.0 29 | 2.15 27 | 6.30 21 | 14.2 22 | 1.54 46 | 6.38 20 | 9.90 21 | 1.63 28 |
CtxSyn [134] | 32.7 | 2.24 10 | 3.72 13 | 1.04 2 | 2.96 7 | 4.16 8 | 1.35 42 | 4.32 104 | 3.42 13 | 3.18 149 | 4.21 7 | 5.46 12 | 3.00 12 | 9.59 32 | 11.9 29 | 3.46 35 | 5.22 26 | 9.76 26 | 2.22 30 | 7.02 34 | 15.4 32 | 1.58 67 | 6.66 30 | 10.2 27 | 1.69 37 |
FRUCnet [153] | 32.9 | 2.61 33 | 4.34 28 | 1.52 186 | 3.30 19 | 4.52 18 | 1.72 133 | 3.14 19 | 3.70 18 | 1.76 53 | 4.74 20 | 5.99 25 | 3.29 84 | 8.11 19 | 10.0 18 | 2.97 3 | 4.48 10 | 8.35 11 | 2.02 11 | 5.78 13 | 12.7 10 | 1.45 17 | 6.06 12 | 9.38 12 | 1.57 17 |
ADC [161] | 32.9 | 2.54 31 | 4.31 26 | 1.29 154 | 3.27 16 | 4.46 14 | 1.62 110 | 3.76 55 | 3.76 20 | 1.70 47 | 5.27 37 | 6.37 29 | 3.19 46 | 8.66 22 | 10.8 22 | 3.11 20 | 4.78 19 | 9.04 21 | 2.01 9 | 5.72 10 | 12.8 12 | 1.41 9 | 6.56 28 | 10.2 27 | 1.51 6 |
CyclicGen [149] | 33.2 | 2.26 11 | 3.32 6 | 1.42 181 | 3.19 12 | 4.01 7 | 2.21 184 | 2.76 8 | 4.05 29 | 1.62 35 | 4.97 25 | 5.92 21 | 3.79 169 | 8.00 16 | 9.84 16 | 3.13 23 | 3.36 1 | 5.65 1 | 2.17 28 | 4.55 1 | 9.68 1 | 1.42 12 | 4.48 1 | 6.84 1 | 1.52 9 |
FeFlow [167] | 34.1 | 2.28 13 | 3.73 14 | 1.18 16 | 3.50 39 | 4.78 29 | 2.09 180 | 2.82 10 | 3.13 7 | 1.66 39 | 4.75 21 | 5.78 16 | 3.72 162 | 7.62 6 | 9.40 6 | 3.04 12 | 4.74 18 | 8.88 17 | 2.03 16 | 6.07 17 | 13.1 15 | 1.59 71 | 6.78 33 | 10.5 33 | 1.65 29 |
MPRN [151] | 35.2 | 2.53 29 | 4.43 32 | 1.21 42 | 3.78 84 | 4.97 34 | 1.57 99 | 3.39 26 | 5.49 38 | 1.28 8 | 5.03 26 | 6.58 32 | 3.19 46 | 9.53 30 | 11.9 29 | 3.31 32 | 5.25 28 | 9.92 27 | 2.22 30 | 6.87 31 | 15.5 33 | 1.49 21 | 6.72 31 | 10.4 31 | 1.60 25 |
TC-GAN [166] | 35.2 | 2.34 20 | 3.96 20 | 1.25 119 | 3.26 15 | 4.51 17 | 1.81 149 | 3.49 30 | 3.80 24 | 2.20 88 | 4.65 17 | 5.90 20 | 3.44 128 | 7.87 11 | 9.73 12 | 3.00 8 | 4.78 19 | 9.00 19 | 2.03 16 | 6.34 23 | 14.2 22 | 1.50 24 | 6.28 16 | 9.73 18 | 1.54 11 |
MV_VFI [183] | 35.7 | 2.35 21 | 3.98 21 | 1.25 119 | 3.25 14 | 4.49 15 | 1.81 149 | 3.46 28 | 3.81 25 | 2.21 92 | 4.66 19 | 5.92 21 | 3.44 128 | 7.87 11 | 9.72 11 | 3.01 9 | 4.80 22 | 9.05 22 | 2.04 19 | 6.33 22 | 14.2 22 | 1.50 24 | 6.27 15 | 9.70 17 | 1.54 11 |
DAIN [152] | 35.8 | 2.38 22 | 4.05 23 | 1.26 135 | 3.28 17 | 4.53 20 | 1.79 147 | 3.32 23 | 3.77 21 | 2.05 78 | 4.65 17 | 5.88 18 | 3.41 124 | 7.88 13 | 9.74 13 | 3.04 12 | 4.73 17 | 8.90 18 | 2.04 19 | 6.36 24 | 14.3 26 | 1.51 32 | 6.25 14 | 9.68 16 | 1.54 11 |
MS-PFT [159] | 36.3 | 2.53 29 | 4.35 29 | 1.16 12 | 3.61 57 | 5.03 36 | 1.69 126 | 3.30 22 | 4.25 33 | 1.77 55 | 5.13 31 | 6.55 31 | 3.19 46 | 7.94 15 | 9.81 15 | 3.21 27 | 4.49 11 | 8.24 10 | 2.22 30 | 6.55 26 | 13.9 21 | 1.79 131 | 6.42 22 | 9.89 20 | 1.69 37 |
DAI [168] | 39.2 | 2.30 15 | 3.42 10 | 1.47 185 | 3.46 31 | 4.66 25 | 1.92 163 | 2.55 7 | 3.78 22 | 1.33 10 | 4.27 9 | 5.10 7 | 4.24 182 | 9.07 27 | 11.3 25 | 3.08 16 | 5.28 30 | 10.1 31 | 2.02 11 | 6.56 27 | 14.7 28 | 1.39 6 | 6.48 25 | 10.0 25 | 1.59 23 |
MEMC-Net+ [160] | 43.3 | 2.39 23 | 3.92 19 | 1.28 145 | 3.36 25 | 4.52 18 | 2.07 179 | 3.37 25 | 3.86 26 | 2.20 88 | 4.84 23 | 5.93 23 | 3.72 162 | 8.55 21 | 10.6 21 | 3.14 24 | 4.70 16 | 8.81 16 | 2.03 16 | 6.40 25 | 14.2 22 | 1.58 67 | 6.37 19 | 9.87 19 | 1.57 17 |
MDP-Flow2 [68] | 44.1 | 2.89 37 | 5.38 39 | 1.19 17 | 3.47 33 | 5.07 43 | 1.26 5 | 3.66 44 | 6.10 72 | 2.48 115 | 5.20 33 | 7.48 43 | 3.14 28 | 10.2 36 | 12.8 37 | 3.61 60 | 6.13 59 | 11.8 54 | 2.31 62 | 7.36 39 | 16.8 37 | 1.49 21 | 7.75 54 | 12.1 53 | 1.69 37 |
PMMST [112] | 44.5 | 2.90 39 | 5.43 41 | 1.20 24 | 3.50 39 | 5.05 40 | 1.27 10 | 3.56 34 | 5.46 36 | 1.82 60 | 5.38 50 | 7.92 70 | 3.41 124 | 10.2 36 | 12.8 37 | 3.60 53 | 5.76 36 | 11.0 36 | 2.26 38 | 7.39 41 | 16.9 40 | 1.53 39 | 7.57 39 | 11.8 39 | 1.72 68 |
SuperSlomo [130] | 45.7 | 2.51 27 | 4.32 27 | 1.25 119 | 3.66 65 | 5.06 42 | 1.93 169 | 2.91 12 | 4.00 28 | 1.41 17 | 5.05 27 | 6.27 27 | 3.66 157 | 9.56 31 | 11.9 29 | 3.30 31 | 5.37 33 | 10.2 33 | 2.24 33 | 6.69 28 | 15.0 29 | 1.53 39 | 6.73 32 | 10.4 31 | 1.66 30 |
TOF-M [150] | 45.8 | 2.54 31 | 4.35 29 | 1.16 12 | 3.70 71 | 5.19 49 | 1.88 156 | 3.43 27 | 3.89 27 | 1.93 68 | 5.05 27 | 6.43 30 | 3.39 118 | 9.84 33 | 12.3 33 | 3.42 34 | 5.34 32 | 10.0 29 | 2.28 46 | 6.88 32 | 15.2 30 | 1.61 79 | 7.14 35 | 11.0 35 | 1.69 37 |
OFRI [154] | 48.4 | 2.28 13 | 3.45 11 | 1.35 174 | 3.44 28 | 4.57 22 | 2.13 182 | 3.02 17 | 3.34 11 | 1.73 50 | 4.51 15 | 5.42 10 | 3.88 170 | 7.89 14 | 9.76 14 | 3.10 18 | 5.24 27 | 9.92 27 | 2.10 24 | 6.78 30 | 14.3 26 | 1.82 136 | 6.32 18 | 9.62 14 | 1.75 110 |
CoT-AMFlow [174] | 48.8 | 2.89 37 | 5.43 41 | 1.19 17 | 3.48 34 | 5.11 46 | 1.25 4 | 3.86 63 | 6.56 95 | 2.48 115 | 5.19 32 | 7.47 42 | 3.10 22 | 10.3 41 | 12.8 37 | 3.61 60 | 6.15 63 | 11.9 63 | 2.31 62 | 7.41 45 | 17.0 45 | 1.48 19 | 7.76 58 | 12.1 53 | 1.73 77 |
FLAVR [188] | 52.4 | 3.02 59 | 4.65 33 | 1.34 172 | 3.70 71 | 4.49 15 | 1.71 131 | 3.52 33 | 4.19 31 | 1.68 44 | 8.08 183 | 9.60 161 | 3.65 156 | 7.35 2 | 9.04 2 | 2.94 1 | 4.20 8 | 7.73 8 | 1.96 1 | 6.17 18 | 13.0 14 | 1.62 89 | 5.53 5 | 8.40 4 | 1.57 17 |
SepConv-v1 [125] | 54.5 | 2.52 28 | 4.83 34 | 1.11 8 | 3.56 52 | 5.04 38 | 1.90 159 | 4.17 87 | 4.15 30 | 2.86 135 | 5.41 59 | 6.81 33 | 3.88 170 | 10.2 36 | 12.8 37 | 3.37 33 | 5.47 35 | 10.4 35 | 2.21 29 | 6.88 32 | 15.6 34 | 1.72 118 | 6.63 29 | 10.3 30 | 1.62 27 |
DeepFlow [85] | 55.3 | 2.98 50 | 5.67 56 | 1.22 74 | 3.88 99 | 5.78 98 | 1.52 89 | 3.62 37 | 5.93 64 | 1.34 11 | 5.39 55 | 7.20 37 | 3.17 35 | 11.0 74 | 13.9 81 | 3.63 74 | 5.91 42 | 11.3 41 | 2.29 51 | 7.14 35 | 16.3 35 | 1.49 21 | 7.80 63 | 12.2 61 | 1.70 45 |
CBF [12] | 60.8 | 2.83 34 | 5.20 35 | 1.23 95 | 3.97 112 | 5.79 100 | 1.56 95 | 3.62 37 | 5.47 37 | 1.60 34 | 5.21 34 | 7.12 34 | 3.29 84 | 10.1 34 | 12.6 34 | 3.62 67 | 5.97 45 | 11.5 45 | 2.31 62 | 7.76 77 | 17.8 76 | 1.61 79 | 7.60 42 | 11.9 42 | 1.76 124 |
DeepFlow2 [106] | 61.0 | 2.99 53 | 5.65 53 | 1.22 74 | 3.88 99 | 5.79 100 | 1.48 81 | 3.62 37 | 6.03 66 | 1.34 11 | 5.38 50 | 7.44 41 | 3.22 59 | 11.0 74 | 13.8 74 | 3.67 82 | 5.83 37 | 11.2 37 | 2.25 37 | 7.60 57 | 17.4 58 | 1.50 24 | 7.82 64 | 12.2 61 | 1.77 135 |
NN-field [71] | 62.2 | 2.98 50 | 5.70 57 | 1.20 24 | 3.31 21 | 4.73 27 | 1.26 5 | 4.69 127 | 5.91 62 | 2.03 77 | 5.99 126 | 9.13 143 | 3.57 148 | 10.3 41 | 12.8 37 | 3.60 53 | 6.24 71 | 12.0 70 | 2.31 62 | 7.39 41 | 16.9 40 | 1.54 46 | 7.69 50 | 12.0 48 | 1.72 68 |
NNF-Local [75] | 63.2 | 2.92 42 | 5.51 48 | 1.19 17 | 3.30 19 | 4.71 26 | 1.26 5 | 3.65 42 | 5.91 62 | 2.29 100 | 5.76 101 | 8.70 123 | 3.55 146 | 10.3 41 | 12.9 44 | 3.60 53 | 6.42 94 | 12.4 92 | 2.34 78 | 7.57 53 | 17.4 58 | 1.74 120 | 7.61 43 | 11.9 42 | 1.72 68 |
Aniso. Huber-L1 [22] | 64.9 | 2.95 45 | 5.44 44 | 1.24 109 | 4.42 151 | 6.27 150 | 1.67 122 | 3.79 56 | 5.70 46 | 1.50 24 | 5.31 40 | 7.42 40 | 3.24 70 | 11.1 85 | 14.0 93 | 3.61 60 | 5.91 42 | 11.4 43 | 2.24 33 | 7.60 57 | 17.3 52 | 1.51 32 | 7.62 45 | 11.9 42 | 1.73 77 |
IROF-TV [53] | 65.5 | 3.07 69 | 5.91 79 | 1.23 95 | 3.71 75 | 5.47 73 | 1.40 55 | 3.70 50 | 6.27 79 | 1.58 31 | 5.25 36 | 7.60 50 | 3.17 35 | 11.0 74 | 13.9 81 | 4.47 144 | 6.37 89 | 12.4 92 | 2.30 57 | 7.79 82 | 17.9 83 | 1.50 24 | 7.63 46 | 11.9 42 | 1.66 30 |
LME [70] | 65.8 | 2.95 45 | 5.59 51 | 1.19 17 | 3.68 68 | 5.50 76 | 1.38 47 | 4.06 77 | 7.00 118 | 1.71 49 | 5.38 50 | 7.92 70 | 3.18 39 | 11.2 99 | 14.1 102 | 4.51 175 | 6.29 76 | 12.2 77 | 2.31 62 | 7.33 37 | 16.8 37 | 1.51 32 | 7.83 65 | 12.3 65 | 1.70 45 |
CLG-TV [48] | 66.4 | 2.94 43 | 5.45 45 | 1.25 119 | 4.26 137 | 6.17 135 | 1.60 104 | 3.68 48 | 5.73 48 | 1.73 50 | 5.36 46 | 7.41 39 | 3.32 103 | 11.1 85 | 14.0 93 | 3.57 40 | 5.88 41 | 11.3 41 | 2.26 38 | 7.58 54 | 17.0 45 | 1.57 64 | 7.75 54 | 12.1 53 | 1.72 68 |
IROF++ [58] | 67.4 | 3.03 60 | 5.77 65 | 1.20 24 | 3.59 56 | 5.31 61 | 1.33 36 | 4.32 104 | 6.61 97 | 2.25 95 | 5.06 29 | 7.14 35 | 3.16 31 | 11.0 74 | 13.9 81 | 4.44 140 | 6.34 83 | 12.3 86 | 2.27 43 | 7.54 52 | 17.3 52 | 1.64 95 | 8.09 90 | 12.7 91 | 1.69 37 |
CombBMOF [111] | 68.4 | 3.16 98 | 5.88 74 | 1.24 109 | 3.54 46 | 5.24 53 | 1.34 40 | 4.01 72 | 6.45 90 | 2.20 88 | 5.62 90 | 8.22 88 | 3.29 84 | 10.7 56 | 13.5 57 | 3.62 67 | 6.20 67 | 11.9 63 | 2.27 43 | 7.78 81 | 17.3 52 | 1.56 59 | 7.75 54 | 12.1 53 | 1.71 57 |
NNF-EAC [101] | 68.7 | 3.01 56 | 5.60 52 | 1.25 119 | 3.63 60 | 5.36 66 | 1.29 21 | 4.17 87 | 7.03 120 | 2.99 139 | 5.50 69 | 7.96 72 | 3.28 81 | 11.2 99 | 14.1 102 | 3.60 53 | 5.86 40 | 11.2 37 | 2.26 38 | 7.43 46 | 17.0 45 | 1.54 46 | 7.79 62 | 12.2 61 | 1.73 77 |
ALD-Flow [66] | 70.3 | 3.28 128 | 6.45 129 | 1.24 109 | 3.81 89 | 5.73 95 | 1.41 59 | 3.62 37 | 6.28 80 | 1.35 14 | 5.58 79 | 8.39 102 | 3.04 16 | 10.8 59 | 13.5 57 | 4.15 120 | 5.96 44 | 11.4 43 | 2.29 51 | 7.34 38 | 16.8 37 | 1.51 32 | 8.25 116 | 12.9 109 | 1.70 45 |
DF-Auto [113] | 70.4 | 2.94 43 | 5.34 37 | 1.23 95 | 3.99 115 | 5.84 105 | 1.65 116 | 3.85 61 | 6.73 100 | 1.55 30 | 5.38 50 | 7.54 45 | 3.25 73 | 10.4 46 | 13.0 46 | 3.70 86 | 6.17 66 | 11.9 63 | 2.28 46 | 7.94 93 | 18.2 95 | 1.75 125 | 7.68 48 | 12.0 48 | 1.71 57 |
PH-Flow [99] | 72.2 | 3.12 84 | 6.01 94 | 1.20 24 | 3.39 26 | 4.94 33 | 1.28 16 | 3.70 50 | 6.43 86 | 2.48 115 | 5.23 35 | 7.58 49 | 3.22 59 | 10.4 46 | 13.1 49 | 3.62 67 | 6.84 153 | 13.3 151 | 2.47 138 | 7.84 86 | 18.1 91 | 1.58 67 | 7.87 71 | 12.3 65 | 1.73 77 |
WLIF-Flow [91] | 72.4 | 2.95 45 | 5.53 49 | 1.20 24 | 3.66 65 | 5.41 69 | 1.39 51 | 4.26 97 | 7.17 130 | 2.54 119 | 5.30 39 | 7.57 48 | 3.29 84 | 10.7 56 | 13.5 57 | 3.70 86 | 6.74 142 | 13.1 138 | 2.48 144 | 7.40 43 | 16.9 40 | 1.53 39 | 7.87 71 | 12.3 65 | 1.69 37 |
Second-order prior [8] | 73.4 | 2.91 41 | 5.39 40 | 1.24 109 | 4.26 137 | 6.21 143 | 1.56 95 | 3.82 58 | 6.34 83 | 1.62 35 | 5.39 55 | 7.68 52 | 3.04 16 | 11.1 85 | 13.9 81 | 3.59 44 | 6.14 61 | 11.9 63 | 2.31 62 | 7.61 59 | 17.4 58 | 1.63 94 | 7.90 73 | 12.4 75 | 1.78 143 |
p-harmonic [29] | 74.6 | 3.00 54 | 5.72 59 | 1.21 42 | 4.33 142 | 6.24 148 | 1.69 126 | 3.60 35 | 6.07 70 | 1.39 16 | 5.70 93 | 7.87 65 | 3.29 84 | 11.0 74 | 13.8 74 | 3.63 74 | 6.02 48 | 11.6 48 | 2.34 78 | 7.67 64 | 17.5 63 | 1.70 113 | 7.92 77 | 12.4 75 | 1.72 68 |
FMOF [92] | 75.7 | 3.16 98 | 5.92 82 | 1.23 95 | 3.48 34 | 5.07 43 | 1.28 16 | 4.59 122 | 6.82 104 | 2.78 130 | 5.71 95 | 8.42 103 | 3.40 121 | 10.4 46 | 13.0 46 | 3.67 82 | 6.49 101 | 12.6 102 | 2.28 46 | 7.64 61 | 17.5 63 | 1.48 19 | 8.06 88 | 12.6 86 | 1.67 33 |
Brox et al. [5] | 75.9 | 3.08 72 | 5.94 84 | 1.21 42 | 3.83 93 | 5.67 87 | 1.45 72 | 3.93 66 | 5.76 51 | 1.67 42 | 5.32 41 | 7.19 36 | 3.22 59 | 10.6 53 | 13.4 55 | 3.56 38 | 6.60 123 | 12.7 109 | 2.42 123 | 8.61 139 | 19.7 142 | 3.04 185 | 7.43 37 | 11.6 37 | 1.68 35 |
SIOF [67] | 77.3 | 3.06 67 | 5.74 63 | 1.24 109 | 4.40 150 | 6.40 161 | 1.63 112 | 4.17 87 | 7.43 144 | 1.93 68 | 5.40 58 | 7.75 57 | 3.44 128 | 10.1 34 | 12.6 34 | 3.58 42 | 6.10 54 | 11.8 54 | 2.29 51 | 7.52 50 | 17.2 50 | 1.53 39 | 7.96 82 | 12.5 85 | 1.73 77 |
MDP-Flow [26] | 79.2 | 2.86 35 | 5.34 37 | 1.20 24 | 3.49 38 | 5.15 47 | 1.34 40 | 4.01 72 | 5.51 39 | 2.28 97 | 5.58 79 | 7.91 69 | 3.33 106 | 11.2 99 | 14.0 93 | 4.49 155 | 6.72 136 | 13.1 138 | 2.54 162 | 7.71 68 | 17.7 72 | 1.74 120 | 7.83 65 | 12.3 65 | 1.70 45 |
HCFN [157] | 79.6 | 3.16 98 | 6.30 113 | 1.20 24 | 3.69 70 | 5.58 80 | 1.32 32 | 3.97 70 | 6.09 71 | 1.73 50 | 5.54 72 | 8.33 95 | 3.22 59 | 10.9 66 | 13.7 67 | 3.61 60 | 6.29 76 | 11.9 63 | 2.62 176 | 8.11 107 | 18.5 106 | 1.61 79 | 8.18 100 | 12.8 100 | 1.73 77 |
Local-TV-L1 [65] | 80.0 | 3.00 54 | 5.47 46 | 1.30 158 | 4.43 153 | 6.23 147 | 1.75 140 | 3.50 31 | 5.35 35 | 1.45 20 | 5.39 55 | 7.56 46 | 3.29 84 | 11.2 99 | 14.1 102 | 3.91 109 | 6.16 64 | 11.8 54 | 2.47 138 | 7.67 64 | 17.6 67 | 1.55 53 | 7.57 39 | 11.8 39 | 1.76 124 |
OAR-Flow [123] | 80.5 | 3.13 89 | 5.95 86 | 1.22 74 | 3.83 93 | 5.70 90 | 1.48 81 | 3.65 42 | 6.06 67 | 1.16 5 | 5.60 85 | 8.48 108 | 3.03 13 | 11.2 99 | 14.1 102 | 4.51 175 | 6.12 57 | 11.8 54 | 2.41 120 | 7.97 96 | 17.9 83 | 1.59 71 | 8.11 94 | 12.7 91 | 1.71 57 |
JOF [136] | 81.4 | 3.08 72 | 5.89 76 | 1.24 109 | 3.48 34 | 5.04 38 | 1.37 45 | 3.85 61 | 5.98 65 | 2.07 79 | 5.43 62 | 7.81 63 | 3.28 81 | 11.3 118 | 14.2 118 | 4.51 175 | 6.72 136 | 13.1 138 | 2.37 94 | 7.48 48 | 17.1 48 | 1.54 46 | 8.01 84 | 12.6 86 | 1.73 77 |
SegFlow [156] | 82.1 | 3.23 116 | 6.50 132 | 1.21 42 | 3.55 49 | 5.27 58 | 1.31 28 | 4.03 75 | 5.73 48 | 1.34 11 | 6.09 133 | 9.56 159 | 3.37 113 | 11.1 85 | 14.0 93 | 4.50 160 | 6.10 54 | 11.8 54 | 2.40 108 | 7.51 49 | 17.2 50 | 1.66 102 | 8.06 88 | 12.6 86 | 1.73 77 |
PRAFlow_RVC [177] | 85.9 | 3.33 138 | 6.76 147 | 1.20 24 | 3.56 52 | 5.25 54 | 1.32 32 | 3.94 67 | 6.33 82 | 2.41 110 | 5.65 92 | 8.49 109 | 3.12 26 | 10.3 41 | 12.9 44 | 3.62 67 | 6.41 91 | 12.4 92 | 2.30 57 | 7.37 40 | 16.9 40 | 2.11 163 | 8.63 160 | 13.5 159 | 1.82 174 |
F-TV-L1 [15] | 86.0 | 3.30 130 | 6.36 122 | 1.29 154 | 4.39 149 | 6.32 156 | 1.62 110 | 3.80 57 | 5.90 61 | 1.76 53 | 5.61 87 | 7.97 74 | 3.31 99 | 10.9 66 | 13.6 62 | 3.59 44 | 5.84 38 | 11.2 37 | 2.33 74 | 7.70 66 | 17.6 67 | 1.79 131 | 7.61 43 | 11.9 42 | 1.78 143 |
CPM-Flow [114] | 86.5 | 3.17 105 | 6.31 117 | 1.21 42 | 3.54 46 | 5.26 56 | 1.31 28 | 4.22 94 | 5.88 60 | 1.45 20 | 6.11 135 | 9.48 155 | 3.31 99 | 11.1 85 | 13.9 81 | 4.50 160 | 6.28 75 | 12.1 74 | 2.32 71 | 7.66 62 | 17.6 67 | 1.74 120 | 8.18 100 | 12.8 100 | 1.76 124 |
Ad-TV-NDC [36] | 86.6 | 3.23 116 | 5.70 57 | 1.44 183 | 4.78 177 | 6.46 165 | 1.92 163 | 3.67 45 | 5.86 58 | 1.50 24 | 5.97 123 | 8.14 86 | 3.51 139 | 10.8 59 | 13.5 57 | 3.63 74 | 6.24 71 | 12.0 70 | 2.40 108 | 7.70 66 | 17.3 52 | 1.51 32 | 7.48 38 | 11.7 38 | 1.73 77 |
UnDAF [187] | 87.0 | 3.33 138 | 6.85 150 | 1.22 74 | 3.74 80 | 5.62 85 | 1.28 16 | 4.28 99 | 7.97 160 | 2.83 132 | 6.35 149 | 10.1 168 | 3.16 31 | 10.4 46 | 13.0 46 | 3.59 44 | 6.12 57 | 11.8 54 | 2.33 74 | 7.74 74 | 17.8 76 | 1.56 59 | 7.93 78 | 12.4 75 | 1.76 124 |
VCN_RVC [178] | 87.5 | 3.82 173 | 8.35 176 | 1.21 42 | 3.55 49 | 5.29 60 | 1.30 26 | 4.20 91 | 7.12 128 | 1.89 65 | 6.70 159 | 10.9 174 | 3.18 39 | 10.9 66 | 13.7 67 | 3.61 60 | 6.20 67 | 11.9 63 | 2.24 33 | 7.73 72 | 17.8 76 | 1.55 53 | 8.10 91 | 12.7 91 | 1.85 178 |
Modified CLG [34] | 87.8 | 2.87 36 | 5.32 36 | 1.24 109 | 4.51 159 | 6.21 143 | 1.96 173 | 4.15 85 | 6.45 90 | 2.67 127 | 5.56 76 | 7.69 53 | 3.64 155 | 10.8 59 | 13.5 57 | 3.63 74 | 6.36 88 | 12.3 86 | 2.39 104 | 7.46 47 | 17.1 48 | 1.56 59 | 7.86 68 | 12.3 65 | 1.75 110 |
2DHMM-SAS [90] | 88.2 | 3.10 79 | 5.91 79 | 1.21 42 | 4.10 125 | 6.05 124 | 1.46 76 | 4.38 109 | 7.10 125 | 2.07 79 | 5.38 50 | 7.78 61 | 3.22 59 | 11.3 118 | 14.3 128 | 4.42 136 | 6.33 80 | 12.2 77 | 2.26 38 | 7.95 95 | 18.2 95 | 1.64 95 | 8.19 103 | 12.8 100 | 1.70 45 |
TC/T-Flow [77] | 88.7 | 3.21 113 | 6.24 107 | 1.22 74 | 3.90 104 | 5.86 107 | 1.43 65 | 3.69 49 | 5.83 54 | 1.50 24 | 5.88 115 | 8.93 133 | 3.15 29 | 11.1 85 | 13.9 81 | 4.50 160 | 6.23 69 | 12.0 70 | 2.26 38 | 8.61 139 | 19.0 120 | 1.93 148 | 8.16 99 | 12.8 100 | 1.70 45 |
COFM [59] | 90.1 | 3.03 60 | 5.76 64 | 1.22 74 | 3.55 49 | 5.21 51 | 1.32 32 | 3.82 58 | 6.98 116 | 2.81 131 | 5.41 59 | 7.97 74 | 3.30 94 | 10.8 59 | 13.6 62 | 3.62 67 | 7.01 168 | 13.7 166 | 2.40 108 | 8.00 101 | 18.5 106 | 1.98 151 | 7.91 74 | 12.4 75 | 1.80 163 |
DMF_ROB [135] | 90.1 | 3.15 95 | 6.13 101 | 1.22 74 | 3.96 109 | 5.87 108 | 1.56 95 | 5.24 153 | 7.74 156 | 2.62 121 | 5.73 98 | 8.32 94 | 3.19 46 | 11.0 74 | 13.8 74 | 4.50 160 | 6.07 51 | 11.7 51 | 2.37 94 | 7.66 62 | 17.5 63 | 1.50 24 | 8.10 91 | 12.7 91 | 1.73 77 |
Layers++ [37] | 90.8 | 2.96 48 | 5.56 50 | 1.22 74 | 3.29 18 | 4.64 24 | 1.26 5 | 4.07 78 | 7.24 131 | 3.08 143 | 5.48 66 | 8.10 82 | 3.25 73 | 12.0 184 | 15.2 185 | 4.62 187 | 7.29 178 | 14.3 178 | 2.44 130 | 7.63 60 | 17.5 63 | 1.54 46 | 7.84 67 | 12.3 65 | 1.70 45 |
FlowFields [108] | 91.2 | 3.15 95 | 6.30 113 | 1.21 42 | 3.57 54 | 5.34 64 | 1.32 32 | 4.73 129 | 6.89 109 | 3.23 152 | 5.85 110 | 8.96 136 | 3.08 19 | 10.8 59 | 13.6 62 | 4.19 121 | 6.57 115 | 12.8 122 | 2.36 90 | 7.72 69 | 17.8 76 | 1.67 106 | 8.20 105 | 12.9 109 | 1.74 101 |
nLayers [57] | 91.7 | 3.03 60 | 5.72 59 | 1.21 42 | 3.48 34 | 5.09 45 | 1.31 28 | 5.60 159 | 7.52 147 | 4.26 174 | 5.61 87 | 8.33 95 | 3.29 84 | 11.6 162 | 14.6 161 | 4.31 127 | 6.66 129 | 12.9 131 | 2.40 108 | 7.58 54 | 17.3 52 | 1.59 71 | 7.94 79 | 12.4 75 | 1.69 37 |
LDOF [28] | 91.8 | 3.03 60 | 5.66 55 | 1.28 145 | 4.06 120 | 5.53 78 | 2.40 188 | 4.32 104 | 6.43 86 | 2.00 73 | 5.45 65 | 7.56 46 | 3.60 153 | 10.2 36 | 12.7 36 | 3.59 44 | 6.39 90 | 12.4 92 | 2.29 51 | 8.36 123 | 19.4 131 | 2.21 168 | 7.57 39 | 11.8 39 | 1.86 180 |
TV-L1-MCT [64] | 91.9 | 3.17 105 | 6.05 97 | 1.22 74 | 3.87 96 | 5.82 103 | 1.40 55 | 4.48 116 | 7.75 157 | 2.24 94 | 5.37 48 | 7.76 59 | 3.24 70 | 11.6 162 | 14.7 167 | 4.31 127 | 6.08 52 | 11.7 51 | 2.31 62 | 8.07 105 | 18.6 110 | 2.15 165 | 7.68 48 | 12.0 48 | 1.68 35 |
ComplOF-FED-GPU [35] | 92.2 | 3.23 116 | 6.40 124 | 1.22 74 | 3.73 78 | 5.62 85 | 1.44 68 | 5.23 152 | 6.06 67 | 3.23 152 | 5.53 70 | 8.25 89 | 3.29 84 | 11.1 85 | 13.9 81 | 4.21 122 | 6.11 56 | 11.8 54 | 2.32 71 | 8.16 110 | 18.5 106 | 1.61 79 | 8.29 124 | 12.9 109 | 1.71 57 |
TC-Flow [46] | 93.2 | 3.31 132 | 6.70 143 | 1.22 74 | 3.91 106 | 5.95 111 | 1.45 72 | 3.64 41 | 5.84 55 | 1.28 8 | 5.70 93 | 8.50 111 | 3.22 59 | 11.2 99 | 14.1 102 | 4.44 140 | 6.34 83 | 12.3 86 | 2.41 120 | 7.79 82 | 17.9 83 | 1.55 53 | 8.42 140 | 13.2 142 | 1.74 101 |
AGIF+OF [84] | 94.0 | 3.12 84 | 5.95 86 | 1.20 24 | 3.64 62 | 5.39 67 | 1.40 55 | 3.96 69 | 6.44 89 | 2.28 97 | 5.48 66 | 8.03 78 | 3.25 73 | 11.4 129 | 14.3 128 | 4.49 155 | 6.91 159 | 13.5 161 | 2.37 94 | 7.85 88 | 17.9 83 | 1.54 46 | 8.44 144 | 13.2 142 | 1.73 77 |
AdaConv-v1 [124] | 94.1 | 3.57 161 | 6.88 153 | 1.41 179 | 4.34 145 | 5.67 87 | 2.52 190 | 5.00 142 | 5.86 58 | 2.98 137 | 6.91 165 | 8.89 131 | 4.89 186 | 10.2 36 | 12.8 37 | 3.21 27 | 5.33 31 | 10.1 31 | 2.27 43 | 7.30 36 | 16.6 36 | 1.92 147 | 6.94 34 | 10.8 34 | 1.67 33 |
DPOF [18] | 94.2 | 3.34 141 | 6.82 148 | 1.29 154 | 3.40 27 | 4.93 32 | 1.29 21 | 5.00 142 | 6.36 84 | 3.40 155 | 5.86 111 | 8.94 134 | 3.51 139 | 11.0 74 | 13.8 74 | 3.59 44 | 6.56 112 | 12.7 109 | 2.28 46 | 7.99 98 | 18.2 95 | 1.55 53 | 8.24 113 | 12.9 109 | 1.70 45 |
CRTflow [81] | 94.2 | 3.09 77 | 5.91 79 | 1.27 141 | 4.35 147 | 6.31 154 | 1.68 124 | 4.15 85 | 7.26 132 | 1.84 61 | 5.33 43 | 7.51 44 | 3.38 115 | 11.0 74 | 13.8 74 | 4.48 148 | 6.09 53 | 11.7 51 | 2.30 57 | 8.55 136 | 19.8 143 | 1.55 53 | 8.19 103 | 12.8 100 | 1.72 68 |
PGM-C [118] | 95.3 | 3.17 105 | 6.29 111 | 1.21 42 | 3.58 55 | 5.32 62 | 1.33 36 | 5.01 144 | 6.14 75 | 1.90 66 | 6.14 138 | 9.63 162 | 3.23 66 | 11.2 99 | 14.1 102 | 4.50 160 | 6.14 61 | 11.8 54 | 2.34 78 | 8.20 112 | 18.9 117 | 1.59 71 | 8.46 147 | 13.3 148 | 1.73 77 |
Classic++ [32] | 96.2 | 3.05 65 | 5.85 70 | 1.24 109 | 4.08 123 | 6.08 126 | 1.52 89 | 3.74 53 | 5.58 42 | 1.53 29 | 5.72 97 | 8.12 84 | 3.21 54 | 11.4 129 | 14.3 128 | 3.74 97 | 6.68 131 | 13.0 133 | 2.42 123 | 8.35 122 | 19.2 124 | 1.62 89 | 8.21 107 | 12.9 109 | 1.73 77 |
EAI-Flow [147] | 96.5 | 3.37 144 | 6.27 109 | 1.32 165 | 3.79 85 | 5.59 82 | 1.52 89 | 4.30 102 | 7.09 123 | 2.39 108 | 5.60 85 | 8.34 97 | 2.96 10 | 11.2 99 | 14.1 102 | 4.34 130 | 6.04 50 | 11.6 48 | 2.34 78 | 7.72 69 | 17.6 67 | 3.12 186 | 7.77 60 | 12.1 53 | 1.82 174 |
RAFT-TF_RVC [179] | 96.8 | 3.56 159 | 7.63 166 | 1.19 17 | 3.51 41 | 5.21 51 | 1.27 10 | 3.61 36 | 6.19 78 | 1.84 61 | 5.77 103 | 8.80 127 | 3.18 39 | 10.5 51 | 13.1 49 | 3.60 53 | 7.04 171 | 13.3 151 | 2.74 189 | 7.80 84 | 17.9 83 | 1.66 102 | 8.69 163 | 13.7 164 | 1.82 174 |
Sparse-NonSparse [56] | 96.9 | 3.07 69 | 5.88 74 | 1.21 42 | 3.61 57 | 5.33 63 | 1.33 36 | 4.29 101 | 7.47 145 | 2.19 87 | 5.37 48 | 7.74 55 | 3.21 54 | 11.5 144 | 14.5 149 | 4.36 131 | 6.66 129 | 12.9 131 | 2.41 120 | 8.69 146 | 20.1 150 | 1.67 106 | 8.27 121 | 13.0 123 | 1.70 45 |
ProFlow_ROB [142] | 97.7 | 3.16 98 | 6.30 113 | 1.21 42 | 3.77 83 | 5.71 92 | 1.39 51 | 4.12 82 | 5.27 34 | 1.62 35 | 6.15 139 | 9.68 163 | 3.11 24 | 11.5 144 | 14.5 149 | 4.50 160 | 5.85 39 | 11.2 37 | 2.24 33 | 8.50 132 | 19.4 131 | 1.56 59 | 8.70 164 | 13.6 162 | 1.85 178 |
ProbFlowFields [126] | 97.8 | 3.15 95 | 6.32 119 | 1.21 42 | 3.53 42 | 5.26 56 | 1.29 21 | 5.03 146 | 7.35 139 | 3.73 162 | 5.43 62 | 7.97 74 | 3.25 73 | 11.1 85 | 14.0 93 | 4.50 160 | 6.48 99 | 12.6 102 | 2.55 165 | 7.99 98 | 18.4 105 | 2.57 177 | 7.78 61 | 12.2 61 | 1.75 110 |
OFLAF [78] | 98.2 | 3.10 79 | 5.98 91 | 1.20 24 | 3.44 28 | 5.03 36 | 1.26 5 | 3.73 52 | 5.82 53 | 1.66 39 | 5.33 43 | 7.74 55 | 3.10 22 | 11.6 162 | 14.7 167 | 4.50 160 | 6.58 120 | 12.8 122 | 2.48 144 | 9.33 172 | 21.6 173 | 2.06 159 | 8.45 146 | 13.2 142 | 1.80 163 |
S2F-IF [121] | 98.5 | 3.26 123 | 6.66 140 | 1.20 24 | 3.53 42 | 5.25 54 | 1.29 21 | 4.11 81 | 6.64 98 | 2.34 102 | 5.89 116 | 9.06 141 | 3.08 19 | 11.4 129 | 14.3 128 | 4.51 175 | 6.41 91 | 12.4 92 | 2.40 108 | 7.84 86 | 18.1 91 | 1.76 128 | 8.33 131 | 13.1 133 | 1.75 110 |
Sparse Occlusion [54] | 98.9 | 3.16 98 | 6.18 105 | 1.23 95 | 4.14 132 | 6.24 148 | 1.45 72 | 3.67 45 | 5.84 55 | 1.52 28 | 5.61 87 | 8.26 90 | 3.15 29 | 11.5 144 | 14.4 139 | 4.48 148 | 6.26 73 | 12.1 74 | 2.46 135 | 8.52 134 | 19.6 140 | 1.54 46 | 8.28 123 | 13.0 123 | 1.75 110 |
MLDP_OF [87] | 99.0 | 3.08 72 | 5.98 91 | 1.21 42 | 4.01 116 | 6.01 120 | 1.49 84 | 3.67 45 | 6.14 75 | 1.47 22 | 5.78 104 | 8.13 85 | 3.95 174 | 11.3 118 | 14.2 118 | 3.87 105 | 6.71 134 | 13.0 133 | 2.51 154 | 7.73 72 | 17.7 72 | 1.71 115 | 8.18 100 | 12.8 100 | 1.76 124 |
PMF [73] | 99.3 | 3.14 91 | 6.13 101 | 1.20 24 | 3.73 78 | 5.60 83 | 1.27 10 | 5.24 153 | 8.98 176 | 3.76 163 | 5.75 99 | 8.56 117 | 3.28 81 | 10.8 59 | 13.6 62 | 3.62 67 | 6.55 108 | 12.7 109 | 2.35 87 | 8.41 129 | 19.5 137 | 1.64 95 | 8.57 155 | 13.4 154 | 1.70 45 |
HAST [107] | 99.5 | 3.01 56 | 5.73 61 | 1.21 42 | 3.45 30 | 5.01 35 | 1.27 10 | 6.39 173 | 8.24 166 | 4.09 168 | 5.43 62 | 7.96 72 | 3.03 13 | 11.2 99 | 14.2 118 | 3.59 44 | 7.47 182 | 14.7 182 | 2.47 138 | 8.68 145 | 20.1 150 | 1.53 39 | 8.35 134 | 13.1 133 | 1.77 135 |
TF+OM [98] | 99.9 | 3.33 138 | 6.83 149 | 1.25 119 | 3.65 63 | 5.43 71 | 1.47 79 | 3.82 58 | 6.43 86 | 1.68 44 | 6.01 128 | 9.04 140 | 3.19 46 | 11.2 99 | 14.1 102 | 4.38 133 | 6.46 98 | 12.5 98 | 2.34 78 | 8.30 121 | 19.2 124 | 1.86 140 | 8.05 87 | 12.6 86 | 1.75 110 |
FlowFields+ [128] | 100.0 | 3.14 91 | 6.26 108 | 1.22 74 | 3.54 46 | 5.27 58 | 1.30 26 | 4.74 132 | 7.10 125 | 3.20 150 | 6.01 128 | 9.35 151 | 3.11 24 | 11.1 85 | 13.9 81 | 4.50 160 | 6.57 115 | 12.8 122 | 2.40 108 | 7.89 92 | 18.2 95 | 1.80 133 | 8.22 109 | 12.9 109 | 1.73 77 |
BlockOverlap [61] | 100.4 | 2.98 50 | 5.47 46 | 1.33 168 | 4.38 148 | 6.09 127 | 1.88 156 | 4.26 97 | 5.57 41 | 3.14 146 | 5.56 76 | 7.32 38 | 4.14 179 | 11.1 85 | 13.9 81 | 3.77 100 | 6.41 91 | 12.3 86 | 2.54 162 | 7.75 75 | 17.4 58 | 3.02 184 | 7.32 36 | 11.4 36 | 1.78 143 |
FlowNetS+ft+v [110] | 101.2 | 3.07 69 | 5.81 67 | 1.28 145 | 4.57 166 | 6.29 152 | 2.41 189 | 4.01 72 | 5.64 44 | 2.13 84 | 5.55 74 | 7.77 60 | 3.88 170 | 11.3 118 | 14.2 118 | 4.46 143 | 5.99 47 | 11.5 45 | 2.35 87 | 8.63 142 | 20.0 147 | 1.62 89 | 7.70 51 | 12.0 48 | 1.74 101 |
C-RAFT_RVC [181] | 101.5 | 4.01 177 | 8.57 181 | 1.25 119 | 3.81 89 | 5.74 96 | 1.44 68 | 4.30 102 | 7.14 129 | 2.34 102 | 5.90 117 | 8.92 132 | 3.37 113 | 10.5 51 | 13.1 49 | 3.59 44 | 6.55 108 | 12.7 109 | 2.31 62 | 7.76 77 | 17.8 76 | 1.66 102 | 8.15 98 | 12.8 100 | 1.77 135 |
Filter Flow [19] | 102.5 | 3.13 89 | 5.90 77 | 1.28 145 | 4.56 165 | 6.38 160 | 1.85 154 | 4.22 94 | 6.28 80 | 2.10 82 | 5.91 118 | 7.97 74 | 3.44 128 | 10.4 46 | 13.1 49 | 3.69 85 | 6.43 96 | 12.5 98 | 2.40 108 | 8.17 111 | 18.8 115 | 1.62 89 | 7.94 79 | 12.4 75 | 1.78 143 |
LSM [39] | 104.5 | 3.12 84 | 6.05 97 | 1.21 42 | 3.68 68 | 5.47 73 | 1.33 36 | 4.38 109 | 7.66 154 | 2.01 74 | 5.55 74 | 8.19 87 | 3.19 46 | 11.5 144 | 14.5 149 | 4.43 137 | 6.83 150 | 13.3 151 | 2.37 94 | 8.70 147 | 20.1 150 | 1.72 118 | 8.34 133 | 13.1 133 | 1.71 57 |
EpicFlow [100] | 104.8 | 3.17 105 | 6.34 120 | 1.21 42 | 3.79 85 | 5.70 90 | 1.44 68 | 4.28 99 | 5.73 48 | 1.67 42 | 6.37 152 | 10.1 168 | 3.39 118 | 11.2 99 | 14.1 102 | 4.50 160 | 6.23 69 | 12.0 70 | 2.38 101 | 8.11 107 | 18.5 106 | 1.76 128 | 8.76 168 | 13.8 168 | 1.74 101 |
Black & Anandan [4] | 105.8 | 3.22 115 | 5.87 72 | 1.30 158 | 4.82 180 | 6.55 170 | 1.78 144 | 7.16 177 | 7.10 125 | 3.93 165 | 6.25 145 | 8.49 109 | 3.35 111 | 10.9 66 | 13.7 67 | 3.56 38 | 6.33 80 | 12.2 77 | 2.37 94 | 8.23 115 | 18.6 110 | 1.64 95 | 7.67 47 | 11.9 42 | 1.69 37 |
RNLOD-Flow [119] | 106.2 | 3.06 67 | 5.87 72 | 1.21 42 | 3.96 109 | 5.97 117 | 1.42 62 | 4.39 111 | 8.08 163 | 2.44 112 | 5.35 45 | 7.75 57 | 3.18 39 | 11.5 144 | 14.5 149 | 4.49 155 | 6.71 134 | 13.1 138 | 2.43 126 | 7.85 88 | 18.0 89 | 2.18 166 | 8.44 144 | 13.2 142 | 1.73 77 |
TCOF [69] | 106.6 | 3.12 84 | 5.94 84 | 1.21 42 | 4.60 169 | 6.64 176 | 1.76 142 | 4.13 83 | 7.30 134 | 1.81 57 | 5.42 61 | 7.88 66 | 3.25 73 | 11.3 118 | 14.2 118 | 3.63 74 | 6.42 94 | 12.4 92 | 2.36 90 | 9.08 169 | 21.0 169 | 1.59 71 | 8.37 136 | 13.1 133 | 1.76 124 |
Ramp [62] | 107.0 | 3.11 83 | 5.96 88 | 1.22 74 | 3.61 57 | 5.34 64 | 1.40 55 | 4.91 138 | 8.45 169 | 3.20 150 | 5.29 38 | 7.66 51 | 3.21 54 | 11.5 144 | 14.5 149 | 4.31 127 | 6.88 158 | 13.4 156 | 2.48 144 | 8.73 154 | 20.2 154 | 1.52 38 | 8.29 124 | 13.0 123 | 1.73 77 |
Fusion [6] | 108.1 | 3.04 64 | 5.86 71 | 1.22 74 | 3.75 82 | 5.47 73 | 1.42 62 | 4.08 79 | 5.55 40 | 3.08 143 | 5.80 106 | 8.10 82 | 3.19 46 | 11.4 129 | 14.3 128 | 3.73 94 | 6.99 165 | 13.7 166 | 2.60 171 | 8.40 128 | 19.4 131 | 1.65 100 | 8.50 149 | 13.3 148 | 1.80 163 |
ComponentFusion [94] | 108.1 | 3.41 146 | 7.08 156 | 1.20 24 | 3.63 60 | 5.44 72 | 1.27 10 | 4.20 91 | 6.49 92 | 2.43 111 | 5.59 82 | 8.38 101 | 3.32 103 | 11.4 129 | 14.4 139 | 4.11 118 | 6.26 73 | 12.1 74 | 2.35 87 | 9.30 171 | 21.6 173 | 2.80 182 | 8.68 161 | 13.6 162 | 1.73 77 |
Classic+NL [31] | 108.8 | 3.10 79 | 5.92 82 | 1.23 95 | 3.66 65 | 5.40 68 | 1.39 51 | 4.78 134 | 8.42 168 | 3.01 141 | 5.36 46 | 7.78 61 | 3.30 94 | 11.5 144 | 14.5 149 | 4.24 124 | 6.73 138 | 13.1 138 | 2.40 108 | 8.74 155 | 20.2 154 | 1.70 113 | 8.29 124 | 13.0 123 | 1.71 57 |
AggregFlow [95] | 108.9 | 3.80 172 | 8.08 172 | 1.23 95 | 3.87 96 | 5.83 104 | 1.43 65 | 4.21 93 | 6.79 102 | 2.85 134 | 6.11 135 | 9.36 152 | 3.31 99 | 10.6 53 | 13.3 53 | 3.67 82 | 6.13 59 | 11.8 54 | 2.34 78 | 8.70 147 | 19.8 143 | 2.30 172 | 8.27 121 | 13.0 123 | 1.75 110 |
Bartels [41] | 110.5 | 3.48 153 | 7.24 160 | 1.30 158 | 4.02 117 | 6.12 132 | 1.68 124 | 3.74 53 | 5.80 52 | 1.95 71 | 5.87 113 | 8.44 105 | 3.78 168 | 10.3 41 | 12.8 37 | 3.75 99 | 6.77 145 | 13.0 133 | 2.73 188 | 7.53 51 | 17.3 52 | 2.72 180 | 8.13 95 | 12.7 91 | 1.77 135 |
Occlusion-TV-L1 [63] | 111.0 | 3.14 91 | 6.13 101 | 1.25 119 | 4.47 157 | 6.61 173 | 1.66 119 | 3.51 32 | 5.71 47 | 1.70 47 | 6.33 147 | 9.58 160 | 3.51 139 | 11.0 74 | 13.9 81 | 3.57 40 | 6.48 99 | 12.6 102 | 2.52 159 | 8.36 123 | 18.1 91 | 2.00 154 | 8.32 130 | 13.0 123 | 1.79 157 |
HBM-GC [103] | 111.1 | 3.08 72 | 5.90 77 | 1.26 135 | 3.97 112 | 6.04 123 | 1.41 59 | 3.92 65 | 5.62 43 | 2.87 136 | 5.54 72 | 8.03 78 | 3.21 54 | 11.7 171 | 14.7 167 | 4.58 186 | 7.66 186 | 15.0 186 | 2.69 185 | 8.36 123 | 19.3 127 | 1.55 53 | 7.86 68 | 12.3 65 | 1.76 124 |
Classic+CPF [82] | 111.3 | 3.12 84 | 5.96 88 | 1.21 42 | 3.72 77 | 5.51 77 | 1.39 51 | 4.39 111 | 7.38 142 | 2.27 96 | 5.32 41 | 7.70 54 | 3.18 39 | 11.7 171 | 14.8 173 | 4.50 160 | 7.18 176 | 14.0 176 | 2.45 132 | 8.79 156 | 20.2 154 | 1.57 64 | 8.71 166 | 13.7 164 | 1.73 77 |
LFNet_ROB [145] | 111.5 | 3.65 166 | 7.73 167 | 1.23 95 | 3.88 99 | 5.80 102 | 1.49 84 | 4.57 119 | 8.96 175 | 2.02 76 | 5.62 90 | 8.44 105 | 3.18 39 | 11.0 74 | 13.8 74 | 4.47 144 | 7.19 177 | 14.1 177 | 2.47 138 | 7.59 56 | 17.4 58 | 1.82 136 | 8.10 91 | 12.7 91 | 1.78 143 |
FC-2Layers-FF [74] | 112.0 | 3.18 109 | 6.16 104 | 1.22 74 | 3.33 24 | 4.73 27 | 1.35 42 | 4.34 108 | 7.09 123 | 3.11 145 | 5.56 76 | 8.29 91 | 3.29 84 | 11.5 144 | 14.5 149 | 4.48 148 | 7.00 166 | 13.7 166 | 2.48 144 | 8.92 161 | 20.6 162 | 1.71 115 | 8.30 127 | 13.0 123 | 1.73 77 |
Efficient-NL [60] | 112.2 | 3.05 65 | 5.77 65 | 1.21 42 | 3.90 104 | 5.84 105 | 1.38 47 | 5.90 165 | 6.94 113 | 4.19 171 | 5.59 82 | 8.09 81 | 3.20 53 | 11.5 144 | 14.4 139 | 4.40 135 | 6.87 154 | 13.4 156 | 2.40 108 | 8.85 157 | 20.5 159 | 1.68 110 | 8.57 155 | 13.4 154 | 1.66 30 |
CNN-flow-warp+ref [115] | 112.5 | 2.90 39 | 5.43 41 | 1.25 119 | 4.10 125 | 5.95 111 | 1.83 153 | 4.92 139 | 7.63 152 | 2.45 113 | 6.13 137 | 7.85 64 | 3.72 162 | 11.3 118 | 14.2 118 | 4.51 175 | 6.03 49 | 11.6 48 | 2.46 135 | 9.00 162 | 20.8 167 | 1.65 100 | 7.91 74 | 12.4 75 | 1.76 124 |
FESL [72] | 113.0 | 3.16 98 | 6.02 95 | 1.21 42 | 3.65 63 | 5.42 70 | 1.35 42 | 4.39 111 | 7.61 151 | 2.18 86 | 5.71 95 | 8.35 99 | 3.30 94 | 11.6 162 | 14.7 167 | 4.51 175 | 6.73 138 | 13.1 138 | 2.47 138 | 8.70 147 | 20.1 150 | 1.56 59 | 8.42 140 | 13.2 142 | 1.75 110 |
Horn & Schunck [3] | 113.1 | 3.16 98 | 5.83 68 | 1.26 135 | 4.91 181 | 6.65 177 | 1.92 163 | 6.13 168 | 6.85 105 | 3.53 158 | 6.80 162 | 9.10 142 | 3.57 148 | 10.9 66 | 13.7 67 | 3.59 44 | 6.16 64 | 11.9 63 | 2.32 71 | 8.63 142 | 19.5 137 | 1.84 139 | 7.91 74 | 12.3 65 | 1.73 77 |
2D-CLG [1] | 113.5 | 3.01 56 | 5.65 53 | 1.28 145 | 4.59 168 | 6.17 135 | 1.95 172 | 5.18 150 | 6.06 67 | 3.15 148 | 6.01 128 | 7.88 66 | 3.97 175 | 11.4 129 | 14.4 139 | 4.69 188 | 5.98 46 | 11.5 45 | 2.45 132 | 8.89 160 | 20.5 159 | 1.67 106 | 7.74 53 | 12.0 48 | 1.71 57 |
SRR-TVOF-NL [89] | 113.5 | 3.32 136 | 6.46 130 | 1.23 95 | 3.96 109 | 5.96 114 | 1.59 100 | 4.68 125 | 7.90 159 | 3.52 157 | 5.99 126 | 8.77 125 | 3.23 66 | 11.2 99 | 14.1 102 | 4.45 142 | 6.79 148 | 13.2 148 | 2.31 62 | 7.88 90 | 18.0 89 | 1.50 24 | 8.37 136 | 13.1 133 | 1.75 110 |
RFlow [88] | 115.0 | 3.08 72 | 5.99 93 | 1.23 95 | 4.33 142 | 6.31 154 | 1.66 119 | 4.83 135 | 7.32 135 | 3.14 146 | 5.87 113 | 8.72 124 | 3.47 134 | 11.1 85 | 14.0 93 | 3.60 53 | 6.54 107 | 12.7 109 | 2.39 104 | 8.54 135 | 19.8 143 | 1.61 79 | 8.26 118 | 12.9 109 | 1.80 163 |
TriFlow [93] | 115.6 | 3.71 169 | 7.95 171 | 1.25 119 | 4.31 141 | 6.36 159 | 1.71 131 | 4.05 76 | 6.86 107 | 1.84 61 | 6.21 144 | 9.44 154 | 3.17 35 | 11.3 118 | 14.2 118 | 4.48 148 | 6.76 144 | 13.1 138 | 2.29 51 | 8.01 103 | 18.2 95 | 1.75 125 | 8.24 113 | 12.9 109 | 1.70 45 |
OFH [38] | 115.9 | 3.18 109 | 6.29 111 | 1.23 95 | 4.11 127 | 5.96 114 | 1.61 107 | 4.68 125 | 8.40 167 | 1.68 44 | 5.84 108 | 8.99 137 | 3.03 13 | 11.3 118 | 14.2 118 | 4.25 126 | 6.30 78 | 12.2 77 | 2.40 108 | 8.59 137 | 19.3 127 | 1.89 143 | 8.55 152 | 13.4 154 | 1.97 186 |
PWC-Net_RVC [143] | 116.2 | 3.66 168 | 7.76 168 | 1.21 42 | 3.91 106 | 5.97 117 | 1.37 45 | 3.88 64 | 6.73 100 | 1.48 23 | 6.36 150 | 10.1 168 | 3.13 27 | 11.8 177 | 14.9 178 | 4.49 155 | 6.78 147 | 13.1 138 | 2.34 78 | 7.72 69 | 17.7 72 | 1.66 102 | 8.57 155 | 13.5 159 | 1.88 181 |
3DFlow [133] | 116.6 | 3.26 123 | 6.37 123 | 1.21 42 | 3.70 71 | 5.55 79 | 1.46 76 | 4.51 117 | 6.52 93 | 2.28 97 | 5.84 108 | 8.84 129 | 3.59 151 | 11.2 99 | 14.1 102 | 3.79 102 | 7.04 171 | 13.7 166 | 2.68 184 | 8.59 137 | 19.4 131 | 1.82 136 | 8.26 118 | 12.9 109 | 1.77 135 |
CostFilter [40] | 117.8 | 3.46 152 | 7.24 160 | 1.19 17 | 3.71 75 | 5.60 83 | 1.27 10 | 5.63 161 | 9.41 183 | 3.86 164 | 6.37 152 | 10.1 168 | 3.23 66 | 11.2 99 | 14.0 93 | 3.78 101 | 6.35 86 | 12.2 77 | 2.40 108 | 8.86 159 | 20.6 162 | 1.69 111 | 8.80 170 | 13.8 168 | 1.74 101 |
SVFilterOh [109] | 117.8 | 3.23 116 | 6.35 121 | 1.23 95 | 3.53 42 | 5.19 49 | 1.31 28 | 5.91 166 | 8.20 165 | 4.22 172 | 5.75 99 | 8.52 113 | 3.43 126 | 11.4 129 | 14.3 128 | 4.53 182 | 6.97 163 | 13.6 164 | 2.38 101 | 7.94 93 | 18.3 102 | 1.57 64 | 8.31 129 | 13.0 123 | 1.79 157 |
Nguyen [33] | 118.0 | 3.26 123 | 6.11 100 | 1.33 168 | 4.94 182 | 6.51 168 | 1.91 162 | 4.09 80 | 7.32 135 | 1.96 72 | 6.19 143 | 8.53 114 | 3.60 153 | 11.1 85 | 13.9 81 | 3.58 42 | 6.55 108 | 12.7 109 | 2.36 90 | 9.44 174 | 21.8 177 | 1.80 133 | 7.86 68 | 12.3 65 | 1.74 101 |
S2D-Matching [83] | 118.1 | 3.21 113 | 6.22 106 | 1.22 74 | 3.97 112 | 5.95 111 | 1.48 81 | 4.57 119 | 7.70 155 | 2.84 133 | 5.48 66 | 8.06 80 | 3.48 136 | 11.4 129 | 14.3 128 | 4.14 119 | 6.97 163 | 13.6 164 | 2.56 169 | 8.09 106 | 18.6 110 | 1.74 120 | 8.21 107 | 12.9 109 | 1.76 124 |
Adaptive [20] | 119.5 | 3.24 120 | 6.44 127 | 1.25 119 | 4.57 166 | 6.61 173 | 1.72 133 | 3.94 67 | 6.12 74 | 1.81 57 | 5.86 111 | 8.66 122 | 3.47 134 | 11.6 162 | 14.6 161 | 3.59 44 | 6.55 108 | 12.7 109 | 2.51 154 | 9.03 165 | 20.6 162 | 1.59 71 | 8.13 95 | 12.7 91 | 1.78 143 |
FlowNet2 [120] | 120.2 | 4.84 186 | 10.1 187 | 1.29 154 | 4.11 127 | 6.13 133 | 1.61 107 | 4.73 129 | 7.06 121 | 2.36 105 | 6.36 150 | 10.0 166 | 3.38 115 | 11.2 99 | 14.1 102 | 3.71 89 | 6.44 97 | 12.5 98 | 2.33 74 | 8.45 130 | 19.4 131 | 1.61 79 | 8.03 86 | 12.6 86 | 1.77 135 |
Steered-L1 [116] | 120.4 | 2.97 49 | 5.73 61 | 1.21 42 | 3.81 89 | 5.72 94 | 1.60 104 | 8.15 180 | 9.24 180 | 6.46 188 | 6.42 154 | 9.21 149 | 4.28 183 | 11.4 129 | 14.3 128 | 3.80 103 | 6.52 105 | 12.7 109 | 2.43 126 | 8.20 112 | 19.0 120 | 2.54 175 | 8.33 131 | 13.1 133 | 1.70 45 |
IAOF [50] | 120.5 | 3.53 158 | 6.60 137 | 1.32 165 | 5.39 190 | 7.19 190 | 1.96 173 | 5.81 163 | 7.32 135 | 3.63 160 | 6.15 139 | 8.34 97 | 3.72 162 | 11.1 85 | 14.0 93 | 3.60 53 | 6.50 102 | 12.6 102 | 2.34 78 | 8.28 120 | 19.0 120 | 1.53 39 | 7.94 79 | 12.4 75 | 1.73 77 |
PBOFVI [189] | 120.5 | 3.31 132 | 6.60 137 | 1.21 42 | 4.34 145 | 6.42 163 | 1.69 126 | 4.98 141 | 8.07 162 | 2.35 104 | 5.76 101 | 8.63 120 | 3.45 132 | 11.5 144 | 14.5 149 | 4.50 160 | 6.34 83 | 12.2 77 | 2.30 57 | 8.39 127 | 18.8 115 | 1.80 133 | 8.26 118 | 13.0 123 | 1.74 101 |
Complementary OF [21] | 121.3 | 3.48 153 | 7.32 164 | 1.20 24 | 3.89 102 | 5.96 114 | 1.45 72 | 8.94 184 | 6.94 113 | 5.45 182 | 6.33 147 | 10.0 166 | 3.09 21 | 11.3 118 | 14.2 118 | 4.24 124 | 6.33 80 | 12.3 86 | 2.42 123 | 8.62 141 | 19.3 127 | 1.75 125 | 9.07 179 | 14.3 180 | 1.72 68 |
CompactFlow_ROB [155] | 121.3 | 3.91 176 | 8.50 180 | 1.24 109 | 3.94 108 | 5.94 110 | 1.54 93 | 5.28 155 | 8.58 171 | 2.62 121 | 8.69 186 | 14.5 188 | 3.26 78 | 10.9 66 | 13.7 67 | 3.64 81 | 6.87 154 | 13.4 156 | 2.33 74 | 8.50 132 | 19.6 140 | 1.53 39 | 8.22 109 | 12.9 109 | 1.75 110 |
FF++_ROB [141] | 123.0 | 3.27 126 | 6.67 141 | 1.20 24 | 3.74 80 | 5.58 80 | 1.38 47 | 4.86 137 | 7.42 143 | 2.99 139 | 6.57 158 | 10.4 172 | 3.54 144 | 11.5 144 | 14.5 149 | 4.51 175 | 6.62 126 | 12.8 122 | 2.47 138 | 7.97 96 | 18.3 102 | 1.90 144 | 8.24 113 | 12.9 109 | 1.78 143 |
TVL1_RVC [175] | 123.1 | 3.32 136 | 6.27 109 | 1.36 176 | 5.03 184 | 6.77 184 | 1.94 171 | 4.84 136 | 6.87 108 | 2.98 137 | 6.16 142 | 8.51 112 | 3.58 150 | 10.9 66 | 13.7 67 | 3.63 74 | 6.57 115 | 12.7 109 | 2.43 126 | 9.00 162 | 20.6 162 | 2.20 167 | 7.72 52 | 12.1 53 | 1.71 57 |
AugFNG_ROB [139] | 123.3 | 3.73 170 | 7.90 170 | 1.25 119 | 4.12 130 | 6.02 121 | 1.74 137 | 4.70 128 | 8.79 173 | 1.94 70 | 8.14 184 | 13.4 185 | 3.29 84 | 12.0 184 | 15.1 183 | 4.50 160 | 6.50 102 | 12.6 102 | 2.28 46 | 8.03 104 | 18.3 102 | 1.62 89 | 7.75 54 | 12.1 53 | 1.75 110 |
TV-L1-improved [17] | 123.8 | 3.09 77 | 6.03 96 | 1.25 119 | 4.55 164 | 6.59 172 | 1.70 129 | 5.88 164 | 5.66 45 | 4.09 168 | 5.53 70 | 7.88 66 | 3.22 59 | 11.4 129 | 14.4 139 | 3.61 60 | 6.73 138 | 13.1 138 | 2.51 154 | 9.48 175 | 22.1 179 | 1.94 149 | 8.25 116 | 12.9 109 | 1.79 157 |
TI-DOFE [24] | 124.7 | 3.41 146 | 6.44 127 | 1.44 183 | 5.20 188 | 6.82 187 | 2.01 177 | 4.19 90 | 6.41 85 | 1.88 64 | 6.98 166 | 9.50 156 | 3.70 160 | 10.8 59 | 13.6 62 | 3.61 60 | 6.59 121 | 12.8 122 | 2.36 90 | 8.13 109 | 18.2 95 | 1.77 130 | 8.53 151 | 12.4 75 | 2.33 190 |
EPPM w/o HM [86] | 125.0 | 3.35 142 | 6.86 152 | 1.21 42 | 3.85 95 | 5.88 109 | 1.29 21 | 7.03 175 | 9.47 186 | 3.97 167 | 6.15 139 | 9.51 157 | 3.38 115 | 10.6 53 | 13.3 53 | 3.62 67 | 7.00 166 | 13.7 166 | 2.37 94 | 8.85 157 | 20.5 159 | 2.62 179 | 8.42 140 | 13.2 142 | 1.76 124 |
GraphCuts [14] | 126.9 | 3.65 166 | 7.01 155 | 1.27 141 | 3.89 102 | 5.71 92 | 1.59 100 | 7.54 178 | 5.84 55 | 4.31 175 | 5.98 125 | 8.42 103 | 3.45 132 | 11.4 129 | 14.4 139 | 4.09 116 | 6.56 112 | 12.8 122 | 2.30 57 | 8.70 147 | 20.2 154 | 1.98 151 | 8.59 159 | 13.5 159 | 1.73 77 |
BriefMatch [122] | 127.7 | 3.25 122 | 6.49 131 | 1.25 119 | 3.87 96 | 5.67 87 | 1.97 175 | 6.16 169 | 6.17 77 | 4.79 178 | 6.83 164 | 8.37 100 | 5.73 189 | 11.0 74 | 13.8 74 | 3.73 94 | 6.75 143 | 13.0 133 | 2.61 173 | 7.99 98 | 17.9 83 | 3.29 187 | 8.22 109 | 12.8 100 | 2.32 189 |
LSM_FLOW_RVC [182] | 128.0 | 4.28 183 | 9.20 183 | 1.31 162 | 4.09 124 | 6.17 135 | 1.50 87 | 5.13 148 | 9.21 179 | 2.39 108 | 7.80 178 | 13.2 184 | 3.16 31 | 11.2 99 | 14.1 102 | 4.47 144 | 6.31 79 | 12.2 77 | 2.39 104 | 8.26 116 | 19.0 120 | 1.58 67 | 8.52 150 | 13.3 148 | 1.80 163 |
NL-TV-NCC [25] | 128.6 | 3.37 144 | 6.58 136 | 1.24 109 | 4.23 136 | 6.41 162 | 1.49 84 | 4.39 111 | 6.68 99 | 2.07 79 | 7.19 174 | 11.2 178 | 3.35 111 | 10.7 56 | 13.4 55 | 4.00 113 | 6.95 160 | 13.4 156 | 2.44 130 | 9.06 166 | 20.0 147 | 2.13 164 | 8.42 140 | 13.1 133 | 1.78 143 |
IAOF2 [51] | 129.8 | 3.43 149 | 6.70 143 | 1.28 145 | 4.62 171 | 6.77 184 | 1.74 137 | 4.41 115 | 6.89 109 | 2.12 83 | 5.97 123 | 8.53 114 | 3.33 106 | 11.6 162 | 14.7 167 | 4.06 115 | 6.87 154 | 13.4 156 | 2.51 154 | 8.26 116 | 18.7 114 | 1.61 79 | 8.22 109 | 12.9 109 | 1.74 101 |
EPMNet [131] | 130.0 | 4.90 187 | 10.5 191 | 1.28 145 | 4.04 119 | 5.98 119 | 1.60 104 | 4.73 129 | 7.06 121 | 2.36 105 | 8.74 188 | 15.0 189 | 3.48 136 | 11.2 99 | 14.1 102 | 3.71 89 | 6.70 133 | 13.0 133 | 2.34 78 | 8.45 130 | 19.4 131 | 1.61 79 | 8.38 138 | 13.1 133 | 1.78 143 |
TriangleFlow [30] | 131.5 | 3.24 120 | 6.31 117 | 1.26 135 | 4.29 140 | 6.29 152 | 1.66 119 | 4.67 124 | 6.85 105 | 2.48 115 | 5.78 104 | 8.47 107 | 3.30 94 | 11.4 129 | 14.4 139 | 3.47 36 | 6.63 128 | 12.8 122 | 2.37 94 | 9.67 179 | 22.5 180 | 2.08 161 | 9.69 187 | 15.2 187 | 1.90 183 |
ResPWCR_ROB [140] | 131.9 | 3.52 157 | 7.36 165 | 1.23 95 | 4.06 120 | 6.18 140 | 1.53 92 | 4.57 119 | 6.90 111 | 1.91 67 | 7.44 177 | 12.2 182 | 3.40 121 | 11.5 144 | 14.6 161 | 4.39 134 | 7.10 174 | 13.7 166 | 2.54 162 | 7.81 85 | 17.8 76 | 1.67 106 | 9.04 178 | 14.2 177 | 1.71 57 |
LocallyOriented [52] | 132.5 | 3.29 129 | 6.53 134 | 1.26 135 | 4.64 172 | 6.69 179 | 1.74 137 | 5.61 160 | 7.56 148 | 3.67 161 | 6.73 160 | 9.84 165 | 3.18 39 | 11.5 144 | 14.4 139 | 3.71 89 | 6.57 115 | 12.7 109 | 2.45 132 | 8.71 151 | 19.3 127 | 1.71 115 | 8.40 139 | 13.1 133 | 1.72 68 |
Correlation Flow [76] | 133.7 | 3.27 126 | 6.50 132 | 1.20 24 | 4.42 151 | 6.56 171 | 1.65 116 | 3.98 71 | 6.10 72 | 2.30 101 | 5.93 120 | 8.94 134 | 3.32 103 | 11.6 162 | 14.6 161 | 3.84 104 | 7.63 185 | 14.8 183 | 2.65 182 | 9.95 183 | 23.0 183 | 2.01 156 | 8.73 167 | 13.7 164 | 1.71 57 |
ContinualFlow_ROB [148] | 134.0 | 3.79 171 | 8.09 173 | 1.25 119 | 4.03 118 | 6.11 130 | 1.61 107 | 4.76 133 | 7.58 149 | 2.38 107 | 7.09 169 | 11.7 179 | 3.17 35 | 12.2 188 | 15.4 188 | 4.49 155 | 6.35 86 | 12.3 86 | 2.29 51 | 8.71 151 | 20.0 147 | 1.61 79 | 9.02 176 | 14.2 177 | 1.78 143 |
ACK-Prior [27] | 135.0 | 3.30 130 | 6.56 135 | 1.21 42 | 3.81 89 | 5.78 98 | 1.42 62 | 7.13 176 | 6.90 111 | 5.04 179 | 6.02 131 | 8.78 126 | 3.70 160 | 11.7 171 | 14.7 167 | 4.57 185 | 6.95 160 | 13.5 161 | 2.50 150 | 8.36 123 | 19.2 124 | 2.53 174 | 8.56 154 | 13.4 154 | 1.73 77 |
ROF-ND [105] | 135.3 | 3.18 109 | 5.83 68 | 1.21 42 | 4.13 131 | 6.13 133 | 1.92 163 | 4.22 94 | 7.51 146 | 2.22 93 | 7.10 170 | 10.8 173 | 3.53 142 | 11.4 129 | 14.3 128 | 4.48 148 | 6.95 160 | 13.5 161 | 2.53 160 | 8.21 114 | 18.6 110 | 1.90 144 | 9.08 180 | 14.2 177 | 1.81 172 |
HBpMotionGpu [43] | 136.2 | 3.63 164 | 7.28 162 | 1.35 174 | 4.78 177 | 6.69 179 | 1.92 163 | 4.33 107 | 7.01 119 | 2.56 120 | 6.46 155 | 9.81 164 | 3.40 121 | 11.5 144 | 14.4 139 | 5.69 193 | 6.83 150 | 13.3 151 | 2.55 165 | 7.40 43 | 16.9 40 | 1.51 32 | 8.30 127 | 13.0 123 | 1.79 157 |
StereoOF-V1MT [117] | 136.5 | 3.56 159 | 7.20 159 | 1.22 74 | 4.27 139 | 6.18 140 | 1.70 129 | 6.10 167 | 6.80 103 | 3.43 156 | 7.17 173 | 9.52 158 | 4.01 178 | 11.2 99 | 14.1 102 | 4.43 137 | 6.61 125 | 12.5 98 | 2.60 171 | 9.49 176 | 21.6 173 | 2.05 157 | 8.01 84 | 12.4 75 | 1.78 143 |
H+S_RVC [176] | 137.0 | 3.43 149 | 6.69 142 | 1.28 145 | 4.50 158 | 6.02 121 | 1.90 159 | 5.12 147 | 7.34 138 | 2.66 125 | 7.02 168 | 8.60 119 | 3.54 144 | 11.5 144 | 14.5 149 | 3.88 106 | 6.62 126 | 12.8 122 | 2.43 126 | 8.64 144 | 19.5 137 | 2.06 159 | 8.36 135 | 12.8 100 | 1.76 124 |
Dynamic MRF [7] | 141.2 | 3.19 112 | 6.41 125 | 1.22 74 | 4.11 127 | 6.21 143 | 1.56 95 | 5.37 157 | 7.35 139 | 2.70 128 | 6.74 161 | 9.18 147 | 4.19 180 | 11.1 85 | 13.9 81 | 4.48 148 | 7.02 169 | 13.7 166 | 2.62 176 | 9.26 170 | 21.4 172 | 2.23 169 | 8.57 155 | 13.3 148 | 1.80 163 |
LiteFlowNet [138] | 141.9 | 3.86 174 | 8.34 175 | 1.22 74 | 3.80 87 | 5.75 97 | 1.44 68 | 5.33 156 | 9.45 185 | 2.66 125 | 8.72 187 | 14.4 187 | 3.88 170 | 11.8 177 | 14.8 173 | 4.50 160 | 7.03 170 | 13.7 166 | 2.40 108 | 9.07 168 | 20.4 158 | 1.69 111 | 8.13 95 | 12.7 91 | 1.78 143 |
FOLKI [16] | 142.3 | 3.64 165 | 7.12 157 | 1.65 188 | 5.22 189 | 6.72 182 | 2.36 187 | 5.20 151 | 8.08 163 | 3.96 166 | 7.93 180 | 9.33 150 | 5.52 188 | 11.2 99 | 14.0 93 | 3.70 86 | 6.56 112 | 12.6 102 | 2.74 189 | 8.00 101 | 18.2 95 | 2.88 183 | 7.96 82 | 12.3 65 | 1.78 143 |
Shiralkar [42] | 142.7 | 3.57 161 | 7.31 163 | 1.22 74 | 4.46 156 | 6.33 158 | 1.65 116 | 5.49 158 | 6.98 116 | 2.73 129 | 7.42 176 | 10.9 174 | 3.43 126 | 11.5 144 | 14.4 139 | 3.73 94 | 6.57 115 | 12.7 109 | 2.48 144 | 9.58 177 | 21.9 178 | 1.88 142 | 9.18 183 | 14.4 182 | 1.75 110 |
SimpleFlow [49] | 143.0 | 3.10 79 | 5.97 90 | 1.22 74 | 4.19 134 | 6.11 130 | 1.64 115 | 9.91 187 | 9.43 184 | 6.53 189 | 5.58 79 | 8.29 91 | 3.30 94 | 11.6 162 | 14.6 161 | 4.43 137 | 7.42 180 | 14.6 181 | 2.56 169 | 10.7 187 | 25.2 187 | 2.73 181 | 9.16 182 | 14.4 182 | 1.73 77 |
Rannacher [23] | 143.5 | 3.31 132 | 6.72 146 | 1.25 119 | 4.60 169 | 6.66 178 | 1.72 133 | 6.36 172 | 6.54 94 | 4.25 173 | 5.91 118 | 8.87 130 | 3.49 138 | 11.5 144 | 14.5 149 | 3.63 74 | 6.73 138 | 13.1 138 | 2.53 160 | 9.35 173 | 21.7 176 | 1.98 151 | 8.70 164 | 13.7 164 | 1.75 110 |
SILK [80] | 143.8 | 3.45 151 | 6.85 150 | 1.36 176 | 5.11 186 | 6.70 181 | 2.21 184 | 11.1 189 | 9.96 187 | 6.24 187 | 6.49 156 | 8.82 128 | 3.59 151 | 11.4 129 | 14.3 128 | 3.54 37 | 6.87 154 | 13.3 151 | 2.63 178 | 7.76 77 | 17.7 72 | 1.87 141 | 8.20 105 | 12.7 91 | 1.80 163 |
Learning Flow [11] | 144.0 | 3.14 91 | 6.09 99 | 1.27 141 | 4.51 159 | 6.53 169 | 1.67 122 | 11.5 192 | 12.9 192 | 7.17 192 | 6.31 146 | 8.30 93 | 3.66 157 | 11.7 171 | 14.8 173 | 3.89 107 | 6.59 121 | 12.8 122 | 2.48 144 | 8.27 119 | 18.9 117 | 1.96 150 | 8.68 161 | 13.4 154 | 1.80 163 |
OFRF [132] | 147.3 | 4.02 178 | 8.26 174 | 1.33 168 | 4.53 162 | 6.49 166 | 1.81 149 | 4.60 123 | 7.27 133 | 2.13 84 | 6.02 131 | 9.15 144 | 3.39 118 | 11.8 177 | 14.9 178 | 4.23 123 | 7.13 175 | 13.9 174 | 2.39 104 | 9.02 164 | 20.8 167 | 1.59 71 | 8.79 169 | 13.8 168 | 1.77 135 |
Adaptive flow [45] | 147.7 | 3.60 163 | 6.30 113 | 1.54 187 | 5.14 187 | 6.79 186 | 2.14 183 | 4.52 118 | 6.60 96 | 3.01 141 | 6.54 157 | 8.64 121 | 4.23 181 | 12.1 187 | 15.2 185 | 4.09 116 | 7.57 183 | 14.9 185 | 2.64 180 | 7.75 75 | 17.8 76 | 2.28 171 | 8.47 148 | 13.3 148 | 1.71 57 |
UnFlow [127] | 148.9 | 4.05 179 | 8.73 182 | 1.31 162 | 4.44 155 | 6.28 151 | 1.87 155 | 4.92 139 | 7.36 141 | 2.62 121 | 5.95 122 | 9.00 138 | 3.27 79 | 12.0 184 | 15.2 185 | 4.37 132 | 7.59 184 | 14.8 183 | 2.61 173 | 7.77 80 | 17.6 67 | 1.64 95 | 10.4 188 | 15.4 188 | 2.33 190 |
StereoFlow [44] | 149.1 | 5.35 192 | 10.3 189 | 1.42 181 | 5.03 184 | 7.21 191 | 1.76 142 | 4.14 84 | 6.94 113 | 2.01 74 | 5.83 107 | 8.55 116 | 3.33 106 | 13.7 190 | 17.3 190 | 4.70 189 | 8.71 191 | 17.2 191 | 2.70 186 | 7.88 90 | 18.1 91 | 1.61 79 | 8.82 172 | 13.9 173 | 1.79 157 |
IRR-PWC_RVC [180] | 149.5 | 4.57 184 | 10.0 186 | 1.28 145 | 4.06 120 | 6.17 135 | 1.63 112 | 5.02 145 | 8.82 174 | 2.47 114 | 9.64 190 | 16.3 190 | 3.21 54 | 11.7 171 | 14.8 173 | 4.56 184 | 7.08 173 | 13.9 174 | 2.38 101 | 8.71 151 | 19.9 146 | 1.59 71 | 9.08 180 | 14.3 180 | 1.77 135 |
2bit-BM-tele [96] | 150.5 | 3.31 132 | 6.41 125 | 1.34 172 | 4.53 162 | 6.62 175 | 1.80 148 | 6.23 170 | 9.24 180 | 6.19 186 | 5.94 121 | 8.59 118 | 3.55 146 | 11.3 118 | 14.2 118 | 4.03 114 | 7.72 187 | 15.1 187 | 3.02 191 | 12.2 191 | 28.7 192 | 4.77 193 | 7.76 58 | 12.1 53 | 1.82 174 |
IIOF-NLDP [129] | 151.7 | 3.36 143 | 6.62 139 | 1.21 42 | 4.22 135 | 6.32 156 | 1.59 100 | 5.16 149 | 7.63 152 | 2.63 124 | 6.10 134 | 9.20 148 | 3.53 142 | 11.6 162 | 14.6 161 | 4.79 191 | 7.42 180 | 14.5 180 | 2.71 187 | 12.0 190 | 28.2 190 | 3.38 188 | 8.93 174 | 13.9 173 | 1.74 101 |
SPSA-learn [13] | 155.8 | 3.89 175 | 7.79 169 | 1.27 141 | 4.43 153 | 6.17 135 | 1.81 149 | 9.03 185 | 8.47 170 | 5.47 183 | 6.80 162 | 9.40 153 | 3.72 162 | 11.5 144 | 14.5 149 | 3.91 109 | 6.51 104 | 12.6 102 | 2.46 135 | 11.9 188 | 27.9 189 | 4.54 191 | 10.5 190 | 16.5 190 | 1.75 110 |
FFV1MT [104] | 157.1 | 4.09 181 | 8.38 177 | 1.31 162 | 4.68 174 | 6.18 140 | 2.02 178 | 6.95 174 | 11.5 189 | 3.35 154 | 7.12 171 | 9.16 145 | 3.98 176 | 11.3 118 | 14.1 102 | 3.74 97 | 6.77 145 | 12.7 109 | 2.50 150 | 9.59 178 | 21.0 169 | 2.05 157 | 8.87 173 | 13.8 168 | 1.90 183 |
SegOF [10] | 158.8 | 3.51 155 | 7.12 157 | 1.32 165 | 4.17 133 | 6.10 128 | 1.59 100 | 8.69 182 | 7.75 157 | 5.15 180 | 8.58 185 | 14.3 186 | 4.29 184 | 11.7 171 | 14.8 173 | 4.50 160 | 6.79 148 | 13.2 148 | 2.50 150 | 10.1 184 | 23.5 184 | 2.55 176 | 8.80 170 | 13.8 168 | 1.72 68 |
PGAM+LK [55] | 162.1 | 4.08 180 | 8.41 178 | 1.65 188 | 4.74 176 | 6.45 164 | 2.27 186 | 8.87 183 | 12.2 190 | 6.88 190 | 8.06 182 | 10.9 174 | 4.83 185 | 11.4 129 | 14.3 128 | 3.90 108 | 6.83 150 | 13.2 148 | 2.55 165 | 8.26 116 | 18.9 117 | 2.27 170 | 8.55 152 | 13.3 148 | 1.90 183 |
Heeger++ [102] | 162.2 | 4.76 185 | 9.63 185 | 1.33 168 | 4.65 173 | 6.22 146 | 1.90 159 | 7.84 179 | 9.26 182 | 3.57 159 | 7.12 171 | 9.16 145 | 3.98 176 | 11.9 181 | 15.0 181 | 4.47 144 | 6.52 105 | 12.2 77 | 2.61 173 | 9.82 180 | 20.6 162 | 2.00 154 | 9.02 176 | 14.0 175 | 1.79 157 |
SLK [47] | 163.3 | 3.51 155 | 6.96 154 | 1.41 179 | 4.72 175 | 6.10 128 | 1.98 176 | 9.84 186 | 7.59 150 | 5.20 181 | 7.98 181 | 11.0 177 | 6.14 190 | 11.8 177 | 14.9 178 | 3.71 89 | 6.60 123 | 12.7 109 | 2.50 150 | 9.87 182 | 22.8 182 | 2.08 161 | 8.94 175 | 14.0 175 | 2.03 187 |
WRT [146] | 165.4 | 3.42 148 | 6.71 145 | 1.23 95 | 4.33 142 | 6.06 125 | 1.89 158 | 9.93 188 | 8.00 161 | 5.95 185 | 6.98 166 | 9.01 139 | 3.77 167 | 11.9 181 | 15.1 183 | 3.97 112 | 7.82 188 | 15.4 188 | 2.64 180 | 12.5 192 | 29.5 193 | 3.47 189 | 10.5 190 | 16.6 191 | 1.80 163 |
HCIC-L [97] | 166.2 | 4.98 189 | 9.28 184 | 1.77 191 | 4.97 183 | 6.87 189 | 2.11 181 | 5.70 162 | 10.0 188 | 4.41 177 | 7.85 179 | 11.8 180 | 3.68 159 | 10.9 66 | 13.7 67 | 3.72 93 | 8.18 190 | 16.1 190 | 2.55 165 | 9.06 166 | 21.0 169 | 2.58 178 | 9.57 186 | 15.0 186 | 1.81 172 |
WOLF_ROB [144] | 168.3 | 5.06 190 | 10.3 189 | 1.30 158 | 4.79 179 | 6.72 182 | 1.75 140 | 6.29 171 | 9.03 177 | 4.14 170 | 7.37 175 | 11.8 180 | 3.33 106 | 11.9 181 | 15.0 181 | 4.48 148 | 7.40 179 | 14.3 178 | 2.51 154 | 10.5 186 | 23.9 185 | 1.74 120 | 9.44 184 | 14.8 184 | 1.78 143 |
Pyramid LK [2] | 176.7 | 4.16 182 | 8.44 179 | 1.74 190 | 5.83 191 | 6.82 187 | 2.76 191 | 11.4 190 | 8.60 172 | 5.89 184 | 12.4 192 | 16.7 191 | 7.03 192 | 14.3 191 | 18.1 191 | 3.92 111 | 6.69 132 | 12.2 77 | 2.63 178 | 10.3 185 | 24.0 186 | 2.45 173 | 11.1 192 | 17.4 192 | 2.55 192 |
GroupFlow [9] | 179.8 | 4.94 188 | 10.2 188 | 1.36 176 | 4.51 159 | 6.50 167 | 1.92 163 | 8.67 181 | 9.13 178 | 4.38 176 | 8.83 189 | 13.0 183 | 5.40 187 | 12.9 189 | 16.3 189 | 4.53 182 | 7.89 189 | 15.5 189 | 2.65 182 | 9.85 181 | 22.6 181 | 1.91 146 | 9.52 185 | 14.9 185 | 1.88 181 |
Periodicity [79] | 190.7 | 5.27 191 | 11.1 192 | 1.83 192 | 7.09 192 | 7.33 192 | 2.86 192 | 11.4 190 | 12.2 190 | 7.13 191 | 10.5 191 | 17.1 192 | 6.14 190 | 14.9 192 | 19.0 192 | 4.71 190 | 9.13 192 | 17.9 192 | 3.16 192 | 11.9 188 | 27.8 188 | 3.76 190 | 10.4 188 | 15.8 189 | 2.29 188 |
AVG_FLOW_ROB [137] | 192.8 | 14.6 193 | 20.0 193 | 3.66 193 | 11.3 193 | 12.1 193 | 4.33 193 | 13.4 193 | 14.1 193 | 7.93 193 | 19.0 193 | 25.3 193 | 10.2 193 | 18.3 193 | 23.1 193 | 5.58 192 | 16.7 193 | 32.2 193 | 4.90 193 | 16.6 193 | 28.6 191 | 4.56 192 | 15.9 193 | 19.8 193 | 4.61 193 |
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 | Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012. | |
[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 | Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153. | |
[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 | Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012. | |
[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 | Zhuoyuan Chen, Jiang Wang, and Ying 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 | Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. 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 | Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014. | |
[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] NNF-Local | 673 | 2 | color | Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[76] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code. | |
[77] TC/T-Flow | 341 | 5 | color | M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013. | |
[78] OFLAF | 1530 | 2 | color | T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013. | |
[79] Periodicity | 8000 | 4 | color | Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014. | |
[80] SILK | 572 | 2 | gray | Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014. | |
[81] 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. | |
[82] Classic+CPF | 640 | 2 | gray | Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014. | |
[83] S2D-Matching | 1200 | 2 | color | Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013. | |
[84] AGIF+OF | 438 | 2 | gray | Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016. | |
[85] DeepFlow | 13 | 2 | color | P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[86] 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. | |
[87] 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. | |
[88] 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. | |
[89] 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. | |
[90] 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. | |
[91] 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. | |
[92] FMOF | 215 | 2 | color | N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014. | |
[93] TriFlow | 150 | 2 | color | TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914. | |
[94] ComponentFusion | 6.5 | 2 | color | Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941. | |
[95] 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. | |
[96] 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. | |
[97] HCIC-L | 330 | 2 | color | Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114. | |
[98] TF+OM | 600 | 2 | color | R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015. | |
[99] PH-Flow | 800 | 2 | color | J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015. | |
[100] EpicFlow | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015. | |
[101] NNF-EAC | 380 | 2 | color | Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336. | |
[102] Heeger++ | 6600 | 5 | gray | Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238. | |
[103] HBM-GC | 330 | 2 | color | A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015. | |
[104] 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. | |
[105] 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. | |
[106] DeepFlow2 | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015. | |
[107] HAST | 2667 | 2 | color | Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221. | |
[108] 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. | |
[109] SVFilterOh | 1.56 | 2 | color | Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788. | |
[110] FlowNetS+ft+v | 0.5 | 2 | color | Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235. | |
[111] 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.) | |
[112] 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. | |
[113] DF-Auto | 70 | 2 | color | N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015. | |
[114] CPM-Flow | 3 | 2 | color | Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241. | |
[115] 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. | |
[116] Steered-L1 | 804 | 2 | color | Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016. | |
[117] 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. | |
[118] PGM-C | 5 | 2 | color | Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016. | |
[119] 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. IEEE TIP 26(8):4055-4067, 2017. | |
[120] FlowNet2 | 0.091 | 2 | color | Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900. | |
[121] S2F-IF | 20 | 2 | color | Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765. | |
[122] 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. | |
[123] OAR-Flow | 60 | 2 | color | Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20. | |
[124] AdaConv-v1 | 2.8 | 2 | color | Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017. | |
[125] SepConv-v1 | 0.2 | 2 | color | Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017. | |
[126] ProbFlowFields | 37 | 2 | color | A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017. | |
[127] UnFlow | 0.12 | 2 | color | Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018. | |
[128] 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. | |
[129] IIOF-NLDP | 150 | 2 | color | D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017. | |
[130] SuperSlomo | 0.5 | 2 | color | Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325. | |
[131] EPMNet | 0.061 | 2 | color | Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119. | |
[132] OFRF | 90 | 2 | color | Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020. | |
[133] 3DFlow | 328 | 2 | color | J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018. | |
[134] CtxSyn | 0.07 | 2 | color | Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018. | |
[135] DMF_ROB | 10 | 2 | color | ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[136] JOF | 657 | 2 | gray | C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018. | |
[137] AVG_FLOW_ROB | N/A | 2 | N/A | Average flow field of ROB 2018 training set. | |
[138] LiteFlowNet | 0.06 | 2 | color | T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018. | |
[139] AugFNG_ROB | 0.10 | all | color | Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834. | |
[140] ResPWCR_ROB | 0.2 | 2 | color | Anonymous. Learning optical flow with residual connections. ROB 2018 submission. | |
[141] FF++_ROB | 17.43 | 2 | color | R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018. | |
[142] ProFlow_ROB | 76 | 3 | color | Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277. | |
[143] PWC-Net_RVC | 0.069 | 2 | color | D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018. Also RVC 2020 baseline submission. | |
[144] WOLF_ROB | 0.02 | 2 | color | Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission. | |
[145] LFNet_ROB | 0.068 | 2 | color | Anonymous. Learning a flow network. ROB 2018 submission. | |
[146] WRT | 9 | 2 | color | L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018. | |
[147] EAI-Flow | 2.1 | 2 | color | Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678. | |
[148] ContinualFlow_ROB | 0.5 | all | color | Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018. | |
[149] CyclicGen | 0.088 | 2 | color | Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323. | |
[150] TOF-M | 0.393 | 2 | color | Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017. | |
[151] MPRN | 0.32 | 4 | color | Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361. | |
[152] DAIN | 0.13 | 2 | color | Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019. | |
[153] FRUCnet | 0.65 | 2 | color | Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019. | |
[154] OFRI | 0.31 | 2 | color | Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743. | |
[155] CompactFlow_ROB | 0.05 | 2 | color | Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387. | |
[156] SegFlow | 3.2 | 2 | color | Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018. | |
[157] HCFN | 0.18 | 2 | color | Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116. | |
[158] FGME | 0.23 | 2 | color | Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020. | |
[159] MS-PFT | 0.44 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020. | |
[160] MEMC-Net+ | 0.12 | 2 | color | Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018. | |
[161] ADC | 0.01 | 2 | color | Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424. | |
[162] DSepConv | 0.3 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020. | |
[163] MAF-net | 0.3 | 2 | color | Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021. | |
[164] STAR-Net | 0.049 | 2 | color | Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430. | |
[165] AdaCoF | 0.03 | 2 | color | Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available. | |
[166] TC-GAN | 0.13 | 2 | color | Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111. | |
[167] FeFlow | 0.52 | 2 | color | Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) |
|
[168] DAI | 0.23 | 2 | color | Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404. | |
[169] SoftSplat | 0.1 | 2 | color | Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020. | |
[170] STSR | 5.35 | 2 | color | Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340. | |
[171] BMBC | 0.77 | 2 | color | Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095. | |
[172] GDCN | 1.0 | 2 | color | Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347. | |
[173] EDSC | 0.56 | 2 | color | Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020. | |
[174] CoT-AMFlow | 0.04 | 2 | color | Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36. | |
[175] TVL1_RVC | 11.6 | 2 | color | RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013. | |
[176] H+S_RVC | 44.7 | 2 | color | RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013. | |
[177] PRAFlow_RVC | 0.34 | 2 | color | Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission. | |
[178] VCN_RVC | 0.84 | 2 | color | Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission. | |
[179] RAFT-TF_RVC | 1.51 | 2 | color | Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission. | |
[180] IRR-PWC_RVC | 0.18 | 2 | color | Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission. | |
[181] C-RAFT_RVC | 0.60 | 2 | color | Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission. | |
[182] LSM_FLOW_RVC | 0.2 | 2 | color | Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission. | |
[183] MV_VFI | 0.23 | 2 | color | Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission. | |
[184] DistillNet | 0.12 | 2 | color | Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534. | |
[185] SepConv++ | 0.1 | 2 | color | Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021. | |
[186] EAFI | 0.18 | 2 | color | Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020. | |
[187] UnDAF | 0.04 | 2 | color | Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236. | |
[188] FLAVR | 0.029 | all | color | Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300. | |
[189] PBOFVI | 150 | 2 | color | Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021. | |
[190] SoftsplatAug | 0.17 | 2 | color | Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245. | |
[191] ProBoost-Net | 0.6 | 2 | color | Anonymous. (Interpolation results only.) Progressive Boosting Video Frame Interpolation. ACMMM 2021 submission 358. | |
[192] IDIAL | 0.05 | 2 | color | Anonymous. (Interpolation results only.) Video frame interpolation via inter-frame distillation and intra-frame aggregation learning. AAAI 2022 submission 705. | |
[193] IFRNet | 0.029 | 2 | color | Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Xiaoming Huang, Ying Tai, Chengjie Wang, and Jie Yang. (Interpolation results only.) IFRNet: Intermediate feature refine network for efficient frame interpolation. CVPR 2022. |