Submission ID: 00109
VL-DoGAff-SIFT-8k
Processed: 20-05-04. Download link: sid-00109-vl-dogaff-sift-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: dogaffine
- Descriptor: vlsift (128 float32: 512 bytes)
- Number of features: 8000
- Summary: VL-DoGAff-SIFT with 8000 features, using the built-in matcher (bidirectional filter with the both strategy, optimal inlier and ratio test thresholds) with DEGENSAC
- Paper: N/A
- Website: N/A
- Origin: Baseline
- Flags: is_baseline
Phototourism / Stereo track
mAA at 10 degrees: 0.46795 (±0.00075 over 3 run(s) / ±0.15156 over 9 scenes)
Rank (per category): 100 (of 147)
Scene | Features | Matches (matcher) |
Matches (filter) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
bm | 7976.8 | 407.9 | 407.9 | 263.6 | 0.560 Rank: 20/147 |
0.935 Rank: 78/147 |
0.15150 (±0.00150) Rank: 108/147 |
0.25493 (±0.00133) Rank: 109/147 |
fcs | 7916.0 | 429.1 | 429.1 | 290.9 | 0.441 Rank: 121/147 |
0.939 Rank: 41/147 |
0.57046 (±0.00384) Rank: 101/147 |
0.69668 (±0.00254) Rank: 95/147 |
lms | 7820.3 | 411.2 | 411.2 | 230.9 | 0.502 Rank: 20/147 |
0.715 Rank: 11/147 |
0.47733 (±0.00226) Rank: 103/147 |
0.58214 (±0.00208) Rank: 101/147 |
lb | 7969.7 | 315.8 | 315.8 | 180.6 | 0.479 Rank: 77/147 |
0.753 Rank: 70/147 |
0.35710 (±0.00150) Rank: 108/147 |
0.44363 (±0.00041) Rank: 104/147 |
mc | 7859.4 | 425.8 | 425.8 | 282.3 | 0.523 Rank: 120/147 |
0.962 Rank: 39/147 |
0.36206 (±0.00150) Rank: 108/147 |
0.50569 (±0.00328) Rank: 97/147 |
mr | 7814.4 | 412.4 | 412.4 | 311.1 | 0.460 Rank: 81/147 |
0.968 Rank: 61/147 |
0.28055 (±0.00240) Rank: 100/147 |
0.38825 (±0.00079) Rank: 98/147 |
psm | 7847.5 | 212.4 | 212.4 | 108.9 | 0.385 Rank: 123/147 |
0.500 Rank: 112/147 |
0.11900 (±0.00169) Rank: 106/147 |
0.21499 (±0.00108) Rank: 108/147 |
sf | 7936.6 | 564.6 | 564.6 | 384.1 | 0.488 Rank: 78/147 |
0.906 Rank: 6/147 |
0.47377 (±0.00247) Rank: 87/147 |
0.61607 (±0.00162) Rank: 82/147 |
spc | 7887.9 | 358.0 | 358.0 | 198.7 | 0.501 Rank: 25/147 |
0.864 Rank: 60/147 |
0.36192 (±0.00172) Rank: 107/147 |
0.50922 (±0.00080) Rank: 106/147 |
avg | 7892.1 | 393.0 | 393.0 | 250.1 | 0.482 Rank: 79/147 |
0.838 Rank: 74/147 |
0.35041 (±0.00111) Rank: 101/147 |
0.46795 (±0.00075) Rank: 100/147 |
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: 0.62964 (±0.00428 over 3 run(s) / ±0.17487 over 9 scenes)
Rank (per category): 112 (of 147)
Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
bm | 7976.8 | 307.54 | 99.71 Rank: 76/147 |
2329.58 Rank: 114/147 |
4.726 Rank: 116/147 |
0.65681 Rank: 121/147 |
0.29252 (±0.01093) Rank: 126/147 |
0.43552 (±0.01421) Rank: 126/147 |
fcs | 7916.0 | 355.51 | 97.80 Rank: 88/147 |
3450.66 Rank: 125/147 |
4.223 Rank: 116/147 |
0.28488 Rank: 124/147 |
0.69350 (±0.01168) Rank: 106/147 |
0.76159 (±0.01259) Rank: 111/147 |
lms | 7820.3 | 340.05 | 98.96 Rank: 79/147 |
3072.91 Rank: 97/147 |
4.365 Rank: 101/147 |
0.32152 Rank: 111/147 |
0.78343 (±0.01117) Rank: 108/147 |
0.84508 (±0.01265) Rank: 109/147 |
lb | 7969.7 | 286.41 | 96.92 Rank: 122/147 |
2509.77 Rank: 120/147 |
4.290 Rank: 120/147 |
0.52923 Rank: 112/147 |
0.53295 (±0.00870) Rank: 114/147 |
0.63266 (±0.00818) Rank: 117/147 |
mc | 7859.4 | 319.96 | 99.65 Rank: 76/147 |
3066.79 Rank: 119/147 |
4.359 Rank: 115/147 |
0.41678 Rank: 92/147 |
0.48243 (±0.00707) Rank: 102/147 |
0.63301 (±0.00887) Rank: 99/147 |
mr | 7814.4 | 343.31 | 93.54 Rank: 95/147 |
3630.27 Rank: 121/147 |
3.915 Rank: 119/147 |
0.55541 Rank: 120/147 |
0.38761 (±0.00379) Rank: 109/147 |
0.50252 (±0.00548) Rank: 108/147 |
psm | 7847.5 | 131.87 | 82.12 Rank: 123/147 |
1903.52 Rank: 126/147 |
2.838 Rank: 128/147 |
0.69660 Rank: 57/147 |
0.20179 (±0.00441) Rank: 127/147 |
0.29698 (±0.00762) Rank: 124/147 |
sf | 7936.6 | 455.50 | 98.11 Rank: 51/147 |
4587.50 Rank: 120/147 |
4.268 Rank: 97/147 |
0.34379 Rank: 104/147 |
0.71954 (±0.00637) Rank: 62/147 |
0.80996 (±0.00624) Rank: 50/147 |
spc | 7887.9 | 263.70 | 98.80 Rank: 89/147 |
3002.83 Rank: 114/147 |
3.961 Rank: 125/147 |
0.46642 Rank: 53/147 |
0.64334 (±0.00524) Rank: 100/147 |
0.74941 (±0.00361) Rank: 96/147 |
avg | 7892.1 | 311.54 | 96.18 Rank: 117/147 |
3061.54 Rank: 120/147 |
4.105 Rank: 121/147 |
0.47460 Rank: 114/147 |
0.52635 (±0.00320) Rank: 118/147 |
0.62964 (±0.00428) Rank: 112/147 |
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 —