Submission ID: 00131
CV-DoG-AffNet-HardNet-kornia-PyRANSAC
Processed: 21-02-05. Download link: sid-00131-dog-affnethardnet-8k-both-pyransac.json
This page ranks the submission against all others using the same number of keypoints, regardless of descriptor size. Please hover over table headers for descriptions on metrics and full scene names.
Metadata
- Authors: Challenge organizers (contact)
- Keypoint: sift8k
- Descriptor: affnethardnet (128 float32: 512 bytes)
- Number of features: 8000
- Summary: OpenCV DoG keypoints, followed by AffNet shape estimation and HardNet descriptor. Implementation: OpenCV + kornia library
- Paper: https://arxiv.org/abs/1711.06704
- Website: https://kornia.readthedocs.io/en/latest/feature.html
- Origin: Baseline
- Flags: is_baseline
Phototourism / Stereo track
mAA at 10 degrees: 0.45050 (±0.00103 over 3 run(s) / ±0.15448 over 9 scenes)
Rank (per category): 113 (of 147)
| Scene | Features | Matches (matcher) |
Matches (filter) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
| bm | 7962.4 | 486.1 | 486.1 | 233.0 | 0.520 Rank: 124/147 |
0.963 Rank: 3/147 |
0.12628 (±0.00050) Rank: 118/147 |
0.22733 (±0.00129) Rank: 115/147 |
| fcs | 7839.9 | 622.6 | 622.6 | 310.4 | 0.465 Rank: 69/147 |
0.949 Rank: 5/147 |
0.51813 (±0.00163) Rank: 113/147 |
0.65216 (±0.00085) Rank: 113/147 |
| lms | 7722.3 | 402.6 | 402.6 | 159.6 | 0.464 Rank: 119/147 |
0.714 Rank: 13/147 |
0.45175 (±0.00041) Rank: 111/147 |
0.56909 (±0.00040) Rank: 108/147 |
| lb | 7938.5 | 412.4 | 412.4 | 187.2 | 0.492 Rank: 69/147 |
0.812 Rank: 1/147 |
0.41696 (±0.00050) Rank: 118/147 |
0.54633 (±0.00330) Rank: 58/147 |
| mc | 7790.2 | 673.7 | 673.7 | 334.3 | 0.550 Rank: 15/147 |
0.976 Rank: 1/147 |
0.30151 (±0.00050) Rank: 118/147 |
0.45344 (±0.00543) Rank: 116/147 |
| mr | 7765.5 | 749.0 | 749.0 | 390.0 | 0.479 Rank: 19/147 |
0.983 Rank: 2/147 |
0.26192 (±0.00103) Rank: 111/147 |
0.36245 (±0.00211) Rank: 109/147 |
| psm | 7771.1 | 358.7 | 358.7 | 179.1 | 0.407 Rank: 19/147 |
0.874 Rank: 1/147 |
0.10030 (±0.00057) Rank: 122/147 |
0.18378 (±0.00085) Rank: 122/147 |
| sf | 7865.6 | 928.5 | 928.5 | 429.0 | 0.499 Rank: 17/147 |
0.906 Rank: 5/147 |
0.45583 (±0.00051) Rank: 103/147 |
0.59901 (±0.00095) Rank: 93/147 |
| spc | 7850.3 | 429.8 | 429.8 | 188.4 | 0.502 Rank: 21/147 |
0.829 Rank: 105/147 |
0.31741 (±0.00455) Rank: 115/147 |
0.46097 (±0.00347) Rank: 116/147 |
| avg | 7834.0 | 562.6 | 562.6 | 267.9 | 0.486 Rank: 74/147 |
0.890 Rank: 1/147 |
0.32779 (±0.00157) Rank: 114/147 |
0.45050 (±0.00103) Rank: 113/147 |
We show the inliers that survive the robust estimation loop (i.e. RANSAC), or those supplied with the submission if using custom matches, and use the depth estimates to determine whether they are correct. We draw matches above a 5-pixel error threshold in red, and those below are color-coded by their error, from 0 (green) to 5 pixels (yellow). Matches for which we do not have depth estimates are drawn in blue. Please note that the depth maps are estimates and may contain errors.
— british museum —
— florence cathedral side —
— lincoln memorial statue —
— london bridge —
— milan cathedral —
— mount rushmore —
— piazza san marco —
— sagrada familia —
— saint paul's cathedral —
Phototourism / Multiview track
mAA at 10 degrees: 0.72668 (±0.00115 over 3 run(s) / ±0.10796 over 9 scenes)
Rank (per category): 30 (of 147)
| Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
| bm | 7962.4 | 482.17 | 99.71 Rank: 76/147 |
3158.26 Rank: 62/147 |
4.955 Rank: 73/147 |
0.44672 Rank: 42/147 |
0.49437 (±0.00466) Rank: 36/147 |
0.64080 (±0.00920) Rank: 37/147 |
| fcs | 7839.9 | 660.76 | 98.37 Rank: 61/147 |
5280.11 Rank: 52/147 |
4.614 Rank: 46/147 |
0.24972 Rank: 52/147 |
0.74699 (±0.00489) Rank: 19/147 |
0.81172 (±0.00391) Rank: 18/147 |
| lms | 7722.3 | 441.50 | 99.47 Rank: 18/147 |
3693.84 Rank: 48/147 |
4.572 Rank: 35/147 |
0.25946 Rank: 7/147 |
0.85268 (±0.00647) Rank: 6/147 |
0.90690 (±0.00687) Rank: 5/147 |
| lb | 7938.5 | 516.60 | 98.61 Rank: 28/147 |
3624.41 Rank: 36/147 |
4.826 Rank: 29/147 |
0.48881 Rank: 54/147 |
0.69496 (±0.00343) Rank: 35/147 |
0.78784 (±0.00431) Rank: 34/147 |
| mc | 7790.2 | 664.56 | 99.96 Rank: 18/147 |
4848.43 Rank: 36/147 |
4.913 Rank: 29/147 |
0.36762 Rank: 21/147 |
0.53032 (±0.00120) Rank: 28/147 |
0.67341 (±0.00117) Rank: 30/147 |
| mr | 7765.5 | 757.13 | 94.96 Rank: 30/147 |
5962.96 Rank: 24/147 |
4.381 Rank: 29/147 |
0.48132 Rank: 40/147 |
0.46276 (±0.00861) Rank: 32/147 |
0.57800 (±0.01089) Rank: 31/147 |
| psm | 7771.1 | 354.58 | 98.34 Rank: 9/147 |
3944.86 Rank: 45/147 |
3.814 Rank: 3/147 |
0.51483 Rank: 14/147 |
0.50490 (±0.00582) Rank: 23/147 |
0.58884 (±0.00670) Rank: 20/147 |
| sf | 7865.6 | 917.76 | 98.83 Rank: 29/147 |
7252.75 Rank: 22/147 |
4.658 Rank: 26/147 |
0.30321 Rank: 18/147 |
0.74472 (±0.00686) Rank: 21/147 |
0.82735 (±0.00725) Rank: 19/147 |
| spc | 7850.3 | 429.13 | 94.31 Rank: 139/147 |
4276.50 Rank: 59/147 |
4.349 Rank: 60/147 |
0.51805 Rank: 101/147 |
0.63468 (±0.00073) Rank: 108/147 |
0.72526 (±0.00070) Rank: 117/147 |
| avg | 7834.0 | 580.47 | 98.06 Rank: 39/147 |
4671.35 Rank: 38/147 |
4.565 Rank: 33/147 |
0.40330 Rank: 29/147 |
0.62960 (±0.00083) Rank: 31/147 |
0.72668 (±0.00115) Rank: 30/147 |
In the multi-view track we reconstruct the scene with Structure-from-Motion (Colmap) with small sets of images. We show the results for one bag of 25 images (displaying: 10). Keypoints are drawn in blue if they are part of the model, and in red otherwise.
— british museum —
— florence cathedral side —
— lincoln memorial statue —
— london bridge —
— milan cathedral —
— mount rushmore —
— piazza san marco —
— sagrada familia —
— saint paul's cathedral —
