Submission ID: 00074
L2-Net w/ MAGSAC (no FLANN)
Processed: 20-04-23. Download link: sid-00074-l2net-8k-both-magsac-no-flann.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: l2net (128 float32: 512 bytes)
- Number of features: 8000
- Summary: L2-Net descriptors on DoG features (OpenCV), extracted with a low detection threshold to generate up to 8000 points. Using the built-in matcher: bidirectional filter with the both strategy. MAGSAC for stereo. FLANN disabled.
- Paper: http://openaccess.thecvf.com/content_cvpr_2017/papers/Tian_L2-Net_Deep_Learning_CVPR_2017_paper.pdf
- Website: https://github.com/yuruntian/L2-Net
- Origin: Baseline
- Flags: is_baseline
Phototourism / Stereo track
mAA at 10 degrees: 0.52519 (±0.00039 over 3 run(s) / ±0.15197 over 9 scenes)
Rank (per category): 53 (of 147)
| Scene | Features | Matches (matcher) |
Matches (filter) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
| bm | 7968.3 | 536.1 | 536.1 | 457.9 | 0.527 Rank: 49/147 |
0.926 Rank: 95/147 |
0.19266 (±0.00254) Rank: 78/147 |
0.31298 (±0.00160) Rank: 74/147 |
| fcs | 7873.6 | 683.9 | 683.9 | 592.2 | 0.443 Rank: 91/147 |
0.928 Rank: 75/147 |
0.61310 (±0.00220) Rank: 60/147 |
0.73692 (±0.00224) Rank: 53/147 |
| lms | 7770.9 | 478.5 | 478.5 | 386.3 | 0.468 Rank: 23/147 |
0.670 Rank: 100/147 |
0.54224 (±0.00328) Rank: 50/147 |
0.65206 (±0.00284) Rank: 58/147 |
| lb | 7952.8 | 452.7 | 452.7 | 353.2 | 0.474 Rank: 92/147 |
0.756 Rank: 66/147 |
0.44722 (±0.00254) Rank: 78/147 |
0.54402 (±0.00124) Rank: 59/147 |
| mc | 7823.8 | 641.3 | 641.3 | 553.6 | 0.524 Rank: 99/147 |
0.943 Rank: 93/147 |
0.37571 (±0.00254) Rank: 78/147 |
0.52895 (±0.00225) Rank: 74/147 |
| mr | 7790.8 | 601.8 | 601.8 | 557.9 | 0.457 Rank: 99/147 |
0.956 Rank: 81/147 |
0.31889 (±0.00248) Rank: 64/147 |
0.43134 (±0.00365) Rank: 61/147 |
| psm | 7807.3 | 304.4 | 304.4 | 246.7 | 0.385 Rank: 102/147 |
0.562 Rank: 92/147 |
0.14982 (±0.00150) Rank: 65/147 |
0.26243 (±0.00104) Rank: 66/147 |
| sf | 7893.6 | 827.2 | 827.2 | 749.7 | 0.479 Rank: 102/147 |
0.882 Rank: 46/147 |
0.53069 (±0.00089) Rank: 36/147 |
0.66165 (±0.00098) Rank: 34/147 |
| spc | 7868.9 | 541.6 | 541.6 | 431.7 | 0.487 Rank: 102/147 |
0.842 Rank: 93/147 |
0.44364 (±0.00138) Rank: 52/147 |
0.59632 (±0.00213) Rank: 51/147 |
| avg | 7861.1 | 563.0 | 563.0 | 481.0 | 0.472 Rank: 103/147 |
0.830 Rank: 91/147 |
0.40155 (±0.00060) Rank: 53/147 |
0.52519 (±0.00039) Rank: 53/147 |
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: 0.66445 (±0.00213 over 3 run(s) / ±0.15616 over 9 scenes)
Rank (per category): 96 (of 147)
| Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
| bm | 7968.3 | 305.54 | 99.33 Rank: 129/147 |
2257.45 Rank: 120/147 |
4.864 Rank: 99/147 |
0.53247 Rank: 87/147 |
0.40376 (±0.00842) Rank: 89/147 |
0.55428 (±0.00838) Rank: 93/147 |
| fcs | 7873.6 | 428.34 | 97.82 Rank: 84/147 |
4078.05 Rank: 104/147 |
4.378 Rank: 91/147 |
0.24649 Rank: 41/147 |
0.70306 (±0.00528) Rank: 99/147 |
0.77432 (±0.00645) Rank: 96/147 |
| lms | 7770.9 | 278.83 | 98.70 Rank: 97/147 |
2887.34 Rank: 115/147 |
4.317 Rank: 115/147 |
0.27680 Rank: 40/147 |
0.80400 (±0.01065) Rank: 91/147 |
0.86392 (±0.01033) Rank: 90/147 |
| lb | 7952.8 | 320.69 | 98.40 Rank: 65/147 |
2833.02 Rank: 93/147 |
4.500 Rank: 90/147 |
0.51111 Rank: 92/147 |
0.62453 (±0.00223) Rank: 79/147 |
0.72475 (±0.00314) Rank: 79/147 |
| mc | 7823.8 | 364.17 | 99.38 Rank: 102/147 |
3684.43 Rank: 99/147 |
4.379 Rank: 112/147 |
0.43021 Rank: 109/147 |
0.48407 (±0.00684) Rank: 100/147 |
0.63054 (±0.00652) Rank: 104/147 |
| mr | 7790.8 | 411.59 | 92.79 Rank: 111/147 |
4232.90 Rank: 102/147 |
3.985 Rank: 111/147 |
0.54067 Rank: 112/147 |
0.41069 (±0.00608) Rank: 96/147 |
0.51801 (±0.00718) Rank: 97/147 |
| psm | 7807.3 | 122.15 | 82.92 Rank: 119/147 |
1913.19 Rank: 124/147 |
3.129 Rank: 95/147 |
0.73396 Rank: 63/147 |
0.28493 (±0.00821) Rank: 109/147 |
0.34724 (±0.00987) Rank: 111/147 |
| sf | 7893.6 | 536.25 | 97.84 Rank: 76/147 |
5565.18 Rank: 91/147 |
4.237 Rank: 111/147 |
0.34249 Rank: 101/147 |
0.71032 (±0.00295) Rank: 84/147 |
0.79551 (±0.00256) Rank: 83/147 |
| spc | 7868.9 | 283.42 | 98.94 Rank: 77/147 |
3372.91 Rank: 100/147 |
4.063 Rank: 111/147 |
0.41712 Rank: 11/147 |
0.66918 (±0.00566) Rank: 84/147 |
0.77146 (±0.00648) Rank: 85/147 |
| avg | 7861.1 | 339.00 | 96.23 Rank: 113/147 |
3424.94 Rank: 105/147 |
4.206 Rank: 105/147 |
0.44792 Rank: 90/147 |
0.56606 (±0.00238) Rank: 94/147 |
0.66445 (±0.00213) Rank: 96/147 |
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 —
