Submission ID: 00073
L2-Net-Upright w/ MAGSAC (no FLANN)
Processed: 20-04-22. Download link: sid-00073-l2net-upright-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-upright (128 float32: 512 bytes)
- Number of features: 8000
- Summary: Upright 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: 0.53911 (±0.00062 over 3 run(s) / ±0.14139 over 9 scenes)
Rank (per category): 43 (of 147)
| Scene | Features | Matches (matcher) |
Matches (filter) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
| bm | 7956.3 | 541.4 | 541.4 | 464.8 | 0.520 Rank: 93/147 |
0.930 Rank: 89/147 |
0.22928 (±0.00158) Rank: 45/147 |
0.35759 (±0.00164) Rank: 42/147 |
| fcs | 7838.2 | 778.5 | 778.5 | 691.8 | 0.465 Rank: 40/147 |
0.913 Rank: 97/147 |
0.61167 (±0.00047) Rank: 65/147 |
0.72670 (±0.00058) Rank: 71/147 |
| lms | 7720.4 | 518.3 | 518.3 | 428.8 | 0.467 Rank: 74/147 |
0.662 Rank: 111/147 |
0.55728 (±0.00194) Rank: 32/147 |
0.67513 (±0.00147) Rank: 34/147 |
| lb | 7935.2 | 519.5 | 519.5 | 419.1 | 0.492 Rank: 25/147 |
0.755 Rank: 68/147 |
0.48454 (±0.00158) Rank: 45/147 |
0.58868 (±0.00354) Rank: 36/147 |
| mc | 7779.6 | 794.8 | 794.8 | 710.7 | 0.549 Rank: 42/147 |
0.947 Rank: 84/147 |
0.38784 (±0.00158) Rank: 45/147 |
0.54395 (±0.00231) Rank: 48/147 |
| mr | 7758.9 | 824.4 | 824.4 | 774.2 | 0.479 Rank: 30/147 |
0.957 Rank: 80/147 |
0.33713 (±0.00343) Rank: 32/147 |
0.45078 (±0.00342) Rank: 32/147 |
| psm | 7768.4 | 372.8 | 372.8 | 316.7 | 0.407 Rank: 44/147 |
0.671 Rank: 43/147 |
0.15623 (±0.00093) Rank: 53/147 |
0.27858 (±0.00229) Rank: 50/147 |
| sf | 7860.0 | 1032.2 | 1032.2 | 954.8 | 0.498 Rank: 42/147 |
0.857 Rank: 101/147 |
0.53635 (±0.00091) Rank: 27/147 |
0.65724 (±0.00101) Rank: 40/147 |
| spc | 7849.5 | 533.7 | 533.7 | 440.3 | 0.501 Rank: 51/147 |
0.838 Rank: 97/147 |
0.42435 (±0.00166) Rank: 70/147 |
0.57333 (±0.00214) Rank: 71/147 |
| avg | 7829.6 | 657.3 | 657.3 | 577.9 | 0.486 Rank: 45/147 |
0.837 Rank: 78/147 |
0.41385 (±0.00031) Rank: 42/147 |
0.53911 (±0.00062) Rank: 43/147 |
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: 0.68491 (±0.00338 over 3 run(s) / ±0.13083 over 9 scenes)
Rank (per category): 81 (of 147)
| Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
| bm | 7956.3 | 302.15 | 99.84 Rank: 43/147 |
2116.91 Rank: 125/147 |
4.912 Rank: 85/147 |
0.47690 Rank: 59/147 |
0.45229 (±0.00571) Rank: 60/147 |
0.60108 (±0.00648) Rank: 63/147 |
| fcs | 7838.2 | 470.98 | 96.64 Rank: 128/147 |
4036.14 Rank: 108/147 |
4.570 Rank: 54/147 |
0.25851 Rank: 79/147 |
0.69314 (±0.01178) Rank: 109/147 |
0.76760 (±0.01276) Rank: 104/147 |
| lms | 7720.4 | 297.00 | 98.60 Rank: 102/147 |
2834.02 Rank: 118/147 |
4.434 Rank: 80/147 |
0.30785 Rank: 99/147 |
0.82194 (±0.00256) Rank: 62/147 |
0.87993 (±0.00363) Rank: 58/147 |
| lb | 7935.2 | 367.58 | 98.20 Rank: 91/147 |
2951.73 Rank: 81/147 |
4.684 Rank: 57/147 |
0.49998 Rank: 73/147 |
0.66029 (±0.00696) Rank: 62/147 |
0.75770 (±0.00929) Rank: 63/147 |
| mc | 7779.6 | 452.30 | 99.68 Rank: 67/147 |
3990.37 Rank: 80/147 |
4.666 Rank: 68/147 |
0.39223 Rank: 51/147 |
0.50064 (±0.00535) Rank: 74/147 |
0.64922 (±0.00564) Rank: 75/147 |
| mr | 7758.9 | 567.51 | 92.49 Rank: 114/147 |
4866.95 Rank: 65/147 |
4.149 Rank: 72/147 |
0.48534 Rank: 50/147 |
0.43868 (±0.00712) Rank: 60/147 |
0.54714 (±0.00964) Rank: 68/147 |
| psm | 7768.4 | 162.72 | 87.25 Rank: 107/147 |
2406.04 Rank: 102/147 |
3.428 Rank: 56/147 |
0.68028 Rank: 51/147 |
0.36201 (±0.00582) Rank: 85/147 |
0.43279 (±0.00583) Rank: 92/147 |
| sf | 7860.0 | 663.44 | 96.18 Rank: 125/147 |
6139.30 Rank: 69/147 |
4.427 Rank: 65/147 |
0.33040 Rank: 79/147 |
0.69840 (±0.00255) Rank: 100/147 |
0.77882 (±0.00319) Rank: 108/147 |
| spc | 7849.5 | 276.08 | 97.30 Rank: 128/147 |
3093.16 Rank: 109/147 |
4.165 Rank: 98/147 |
0.66777 Rank: 133/147 |
0.64922 (±0.00756) Rank: 92/147 |
0.74989 (±0.00670) Rank: 94/147 |
| avg | 7829.6 | 395.53 | 96.24 Rank: 111/147 |
3603.85 Rank: 88/147 |
4.382 Rank: 64/147 |
0.45547 Rank: 96/147 |
0.58629 (±0.00295) Rank: 81/147 |
0.68491 (±0.00338) Rank: 81/147 |
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 —
