Submission ID: 00135
CV-DoG-AffNet-HardNet-kornia-PyRANSAC-2k
Processed: 21-02-05. Download link: sid-00135-dog-affnethardnet-2k-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: 2048
- 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: 0.35887 (±0.00090 over 3 run(s) / ±0.12711 over 9 scenes)
Rank (per category): 73 (of 108)
| Scene | Features | Matches (matcher) |
Matches (filter) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
| bm | 2048.0 | 373.1 | 373.1 | 163.8 | 0.461 Rank: 30/108 |
0.939 Rank: 31/108 |
0.07751 (±0.00414) Rank: 88/108 |
0.15436 (±0.00486) Rank: 88/108 |
| fcs | 2048.0 | 284.5 | 284.5 | 119.0 | 0.289 Rank: 80/108 |
0.890 Rank: 27/108 |
0.42132 (±0.00403) Rank: 81/108 |
0.55358 (±0.00329) Rank: 82/108 |
| lms | 2048.0 | 346.3 | 346.3 | 134.3 | 0.392 Rank: 26/108 |
0.721 Rank: 1/108 |
0.35421 (±0.00050) Rank: 79/108 |
0.45227 (±0.00027) Rank: 80/108 |
| lb | 2048.0 | 226.1 | 226.1 | 65.6 | 0.311 Rank: 75/108 |
0.695 Rank: 36/108 |
0.26326 (±0.00414) Rank: 88/108 |
0.35912 (±0.00147) Rank: 67/108 |
| mc | 2048.0 | 215.3 | 215.3 | 76.9 | 0.325 Rank: 77/108 |
0.919 Rank: 32/108 |
0.24046 (±0.00414) Rank: 88/108 |
0.37246 (±0.00095) Rank: 64/108 |
| mr | 2046.5 | 296.7 | 296.7 | 129.9 | 0.334 Rank: 47/108 |
0.954 Rank: 8/108 |
0.17090 (±0.00437) Rank: 74/108 |
0.26070 (±0.00536) Rank: 72/108 |
| psm | 2048.0 | 148.4 | 148.4 | 48.6 | 0.274 Rank: 60/108 |
0.429 Rank: 49/108 |
0.09589 (±0.00144) Rank: 48/108 |
0.18628 (±0.00094) Rank: 47/108 |
| sf | 2048.0 | 347.3 | 347.3 | 126.8 | 0.336 Rank: 76/108 |
0.860 Rank: 1/108 |
0.33796 (±0.00369) Rank: 60/108 |
0.47963 (±0.00237) Rank: 58/108 |
| spc | 2048.0 | 253.9 | 253.9 | 85.2 | 0.328 Rank: 47/108 |
0.796 Rank: 59/108 |
0.27332 (±0.00390) Rank: 76/108 |
0.41141 (±0.00374) Rank: 74/108 |
| avg | 2047.8 | 276.8 | 276.8 | 105.6 | 0.339 Rank: 49/108 |
0.800 Rank: 30/108 |
0.24831 (±0.00086) Rank: 74/108 |
0.35887 (±0.00090) Rank: 73/108 |
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: 0.58536 (±0.00125 over 3 run(s) / ±0.19507 over 9 scenes)
Rank (per category): 64 (of 108)
| Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
| bm | 2048.0 | 370.58 | 99.51 Rank: 71/108 |
1541.76 Rank: 34/108 |
5.258 Rank: 24/108 |
0.71416 Rank: 79/108 |
0.26098 (±0.00505) Rank: 80/108 |
0.39730 (±0.00522) Rank: 80/108 |
| fcs | 2048.0 | 297.20 | 97.84 Rank: 26/108 |
2082.91 Rank: 30/108 |
4.169 Rank: 67/108 |
0.27521 Rank: 47/108 |
0.66667 (±0.00342) Rank: 57/108 |
0.75423 (±0.00516) Rank: 52/108 |
| lms | 2048.0 | 369.35 | 99.24 Rank: 14/108 |
2121.07 Rank: 7/108 |
4.752 Rank: 64/108 |
0.28829 Rank: 13/108 |
0.81167 (±0.00721) Rank: 16/108 |
0.87676 (±0.00639) Rank: 14/108 |
| lb | 2048.0 | 263.96 | 97.17 Rank: 58/108 |
1527.98 Rank: 33/108 |
4.120 Rank: 77/108 |
0.52835 Rank: 69/108 |
0.44481 (±0.01040) Rank: 75/108 |
0.57670 (±0.01052) Rank: 72/108 |
| mc | 2048.0 | 210.23 | 96.45 Rank: 68/108 |
1382.04 Rank: 38/108 |
3.929 Rank: 80/108 |
0.51353 Rank: 73/108 |
0.39147 (±0.00438) Rank: 66/108 |
0.52484 (±0.00583) Rank: 68/108 |
| mr | 2046.5 | 299.55 | 92.18 Rank: 46/108 |
1994.88 Rank: 11/108 |
4.011 Rank: 60/108 |
0.56082 Rank: 49/108 |
0.32980 (±0.00583) Rank: 62/108 |
0.44382 (±0.00814) Rank: 58/108 |
| psm | 2048.0 | 145.18 | 84.51 Rank: 42/108 |
1618.39 Rank: 41/108 |
2.746 Rank: 84/108 |
0.74018 Rank: 63/108 |
0.13258 (±0.00562) Rank: 77/108 |
0.23623 (±0.01246) Rank: 73/108 |
| sf | 2048.0 | 346.38 | 98.76 Rank: 16/108 |
2132.31 Rank: 23/108 |
4.446 Rank: 54/108 |
0.32253 Rank: 30/108 |
0.68768 (±0.00666) Rank: 32/108 |
0.78683 (±0.00955) Rank: 30/108 |
| spc | 2048.0 | 254.10 | 95.96 Rank: 87/108 |
1696.94 Rank: 38/108 |
4.287 Rank: 58/108 |
0.67310 Rank: 89/108 |
0.56862 (±0.00105) Rank: 76/108 |
0.67154 (±0.00193) Rank: 78/108 |
| avg | 2047.8 | 284.06 | 95.74 Rank: 45/108 |
1788.70 Rank: 30/108 |
4.191 Rank: 72/108 |
0.51291 Rank: 67/108 |
0.47714 (±0.00047) Rank: 65/108 |
0.58536 (±0.00125) Rank: 64/108 |
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 —
