Submission ID: 00130
CV-DoG-AffNet-HardNet-kornia-DEGENSAC
Processed: 21-02-05. Download link: sid-00130-dog-affnethardnet-8k-both-degensac.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: 0.54468 (±0.00090 over 3 run(s) / ±0.14058 over 9 scenes)
Rank (per category): 37 (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 | 348.0 | 0.520 Rank: 124/147 |
0.957 Rank: 7/147 |
0.23528 (±0.00169) Rank: 43/147 |
0.35685 (±0.00226) Rank: 43/147 |
| fcs | 7839.9 | 622.6 | 622.6 | 460.3 | 0.465 Rank: 69/147 |
0.945 Rank: 15/147 |
0.61808 (±0.00054) Rank: 53/147 |
0.73168 (±0.00047) Rank: 63/147 |
| lms | 7722.3 | 402.6 | 402.6 | 241.4 | 0.464 Rank: 119/147 |
0.703 Rank: 29/147 |
0.55144 (±0.00202) Rank: 37/147 |
0.67276 (±0.00135) Rank: 38/147 |
| lb | 7938.5 | 412.4 | 412.4 | 280.8 | 0.492 Rank: 69/147 |
0.805 Rank: 4/147 |
0.52303 (±0.00169) Rank: 43/147 |
0.62417 (±0.00041) Rank: 22/147 |
| mc | 7790.2 | 673.7 | 673.7 | 504.2 | 0.550 Rank: 15/147 |
0.973 Rank: 2/147 |
0.41231 (±0.00169) Rank: 43/147 |
0.56333 (±0.00304) Rank: 29/147 |
| mr | 7765.5 | 749.0 | 749.0 | 577.6 | 0.479 Rank: 19/147 |
0.981 Rank: 6/147 |
0.34373 (±0.00114) Rank: 29/147 |
0.46026 (±0.00217) Rank: 28/147 |
| psm | 7771.1 | 358.7 | 358.7 | 265.1 | 0.407 Rank: 19/147 |
0.856 Rank: 2/147 |
0.16775 (±0.00085) Rank: 36/147 |
0.28848 (±0.00135) Rank: 37/147 |
| sf | 7865.6 | 928.5 | 928.5 | 667.4 | 0.499 Rank: 17/147 |
0.903 Rank: 9/147 |
0.52487 (±0.00226) Rank: 38/147 |
0.65294 (±0.00184) Rank: 41/147 |
| spc | 7850.3 | 429.8 | 429.8 | 286.0 | 0.502 Rank: 21/147 |
0.825 Rank: 109/147 |
0.41418 (±0.00117) Rank: 73/147 |
0.55167 (±0.00071) Rank: 83/147 |
| avg | 7834.0 | 562.6 | 562.6 | 403.4 | 0.486 Rank: 74/147 |
0.883 Rank: 2/147 |
0.42119 (±0.00092) Rank: 34/147 |
0.54468 (±0.00090) Rank: 37/147 |
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 |
0.44701 Rank: 43/147 |
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 |
0.24825 Rank: 47/147 |
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 |
0.26147 Rank: 10/147 |
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 |
0.49125 Rank: 59/147 |
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: 22/147 |
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 |
0.47881 Rank: 33/147 |
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 |
0.50110 Rank: 12/147 |
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 |
0.30710 Rank: 26/147 |
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 |
0.51616 Rank: 100/147 |
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 |
0.40208 Rank: 26/147 |
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 —
