Submission ID: fba151a3
R2D2-mega-wasf-n16-8k
Processed: 21-07-25. Download link: fba151a3541e7aec-r2d2-wasf-n16-8k.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.
- Phototourism dataset: Stereo track / Multiview track
- Prague Parks dataset: Stereo track / Multiview track
- Google Urban dataset: Stereo track / Multiview track
Metadata
- Authors: Anonymous (to be released: 2021-6-18)
- Keypoint: r2d2-mega
- Descriptor: r2d2-mega (128 float32: 512 bytes)
- Number of features: 8000
- Summary: R2D2-mega-wasf-n16-8k
- Paper: N/A
- Website: N/A
- Processing date: 21-07-25
Phototourism dataset / Stereo track
mAA at 10 degrees: 0.01376 (±0.00000 over 1 run(s) / ±0.00735 over 9 scenes)
Rank (per category): 50 (of 51)
| Scene | Features | Matches (raw) |
Matches (final) |
Rep. @ 3 px. | MS @ 3 px. | mAA(5o) | mAA(10o) |
| BM | 7960.6 | 338.0 | 338.0 | 0.614 Rank: 25/51 |
0.882 Rank: 41/51 |
0.00531 (±0.00000) Rank: 44/51 |
0.01897 (±0.00000) Rank: 45/51 |
| FCS | 7855.9 | 276.5 | 276.3 | 0.496 Rank: 27/51 |
0.763 Rank: 45/51 |
0.00583 (±0.00000) Rank: 50/51 |
0.02042 (±0.00000) Rank: 50/51 |
| LMS | 7796.3 | 255.9 | 255.9 | 0.448 Rank: 34/51 |
0.622 Rank: 42/51 |
0.00236 (±0.00000) Rank: 50/51 |
0.00891 (±0.00000) Rank: 48/51 |
| LB | 7950.8 | 167.5 | 167.3 | 0.442 Rank: 45/51 |
0.617 Rank: 44/51 |
0.00077 (±0.00000) Rank: 44/51 |
0.00266 (±0.00000) Rank: 45/51 |
| MC | 7824.5 | 290.3 | 290.3 | 0.596 Rank: 33/51 |
0.851 Rank: 41/51 |
0.00281 (±0.00000) Rank: 44/51 |
0.01161 (±0.00000) Rank: 48/51 |
| MR | 7775.6 | 367.5 | 367.5 | 0.579 Rank: 21/51 |
0.908 Rank: 31/51 |
0.00822 (±0.00000) Rank: 50/51 |
0.02635 (±0.00000) Rank: 50/51 |
| PSM | 7785.2 | 150.4 | 150.1 | 0.422 Rank: 25/51 |
0.496 Rank: 44/51 |
0.00492 (±0.00000) Rank: 50/51 |
0.01932 (±0.00000) Rank: 47/51 |
| SF | 7839.0 | 304.8 | 304.5 | 0.528 Rank: 21/51 |
0.703 Rank: 44/51 |
0.00390 (±0.00000) Rank: 50/51 |
0.00901 (±0.00000) Rank: 50/51 |
| SPC | 7870.8 | 210.8 | 210.6 | 0.503 Rank: 33/51 |
0.681 Rank: 43/51 |
0.00189 (±0.00000) Rank: 50/51 |
0.00662 (±0.00000) Rank: 49/51 |
| Avg | 7851.0 | 262.4 | 262.3 | 0.514 Rank: 26/51 |
0.725 Rank: 43/51 |
0.00400 (±0.00000) Rank: 50/51 |
0.01376 (±0.00000) Rank: 50/51 |
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 dataset / Multiview track
mAA at 10 degrees: N/A (±0.00000 over 1 run(s) / ±0.11782 over 9 scenes)
Rank (per category): 37 (of 51)
| Scene | Features | Matches (input) |
RegistrationRatio (%) | Number of Landmarks |
Track Length | ATE | mAA(50) | mAA(100) |
| BM | 7960.6 | 339.91 | 99.73 Rank: 31/51 |
2320.13 Rank: 40/51 |
4.791 Rank: 33/51 |
0.50674 Rank: 35/51 |
0.44753 (±0.00000) Rank: 32/51 |
0.59438 (±0.00000) Rank: 33/51 |
| FCS | 7855.9 | 287.49 | 96.31 Rank: 37/51 |
3110.17 Rank: 46/51 |
3.996 Rank: 40/51 |
0.30368 Rank: 42/51 |
0.66470 (±0.00000) Rank: 36/51 |
0.73707 (±0.00000) Rank: 37/51 |
| LMS | 7796.3 | 282.82 | 98.52 Rank: 35/51 |
2632.68 Rank: 35/51 |
4.135 Rank: 42/51 |
0.30900 Rank: 21/51 |
0.76129 (±0.00000) Rank: 34/51 |
0.82715 (±0.00000) Rank: 34/51 |
| LB | 7950.8 | 204.12 | 96.49 Rank: 44/51 |
1759.41 Rank: 41/51 |
4.257 Rank: 39/51 |
0.57305 Rank: 45/51 |
0.55139 (±0.00000) Rank: 43/51 |
0.67346 (±0.00000) Rank: 43/51 |
| MC | 7824.5 | 285.17 | 98.82 Rank: 45/51 |
2397.86 Rank: 47/51 |
4.525 Rank: 39/51 |
0.45362 Rank: 44/51 |
0.43808 (±0.00000) Rank: 42/51 |
0.59360 (±0.00000) Rank: 43/51 |
| MR | 7775.6 | 364.42 | 94.16 Rank: 30/51 |
2968.55 Rank: 46/51 |
4.326 Rank: 34/51 |
0.52263 Rank: 33/51 |
0.39409 (±0.00000) Rank: 36/51 |
0.51072 (±0.00000) Rank: 36/51 |
| PSM | 7785.2 | 150.43 | 84.79 Rank: 39/51 |
2461.42 Rank: 40/51 |
3.118 Rank: 39/51 |
0.69558 Rank: 41/51 |
0.34060 (±0.00000) Rank: 37/51 |
0.40273 (±0.00000) Rank: 39/51 |
| SF | 7839.0 | 305.55 | 93.00 Rank: 45/51 |
3444.20 Rank: 43/51 |
3.990 Rank: 45/51 |
0.36365 Rank: 43/51 |
0.59702 (±0.00000) Rank: 42/51 |
0.68179 (±0.00000) Rank: 41/51 |
| SPC | 7870.8 | 217.90 | 94.68 Rank: 45/51 |
2449.78 Rank: 41/51 |
4.045 Rank: 39/51 |
0.60995 Rank: 41/51 |
0.56758 (±0.00000) Rank: 43/51 |
0.66998 (±0.00000) Rank: 43/51 |
| Avg | 7851.0 | 270.87 | 95.17 Rank: 39/51 |
2616.02 Rank: 43/51 |
4.132 Rank: 40/51 |
0.48199 Rank: 43/51 |
0.52914 (±0.00000) Rank: 42/51 |
0.63232 (±0.00000) Rank: 37/51 |
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 10 images. 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 —
Prague Parks dataset / Stereo track
mAA at 10 degrees: N/A (±N/A over N/A run(s) / ±N/A over 3 scenes)
Rank (per category): (of 50)
No results for this dataset.
Prague Parks dataset / Multiview track
mAA at 10 degrees: N/A (±N/A over N/A run(s) / ±N/A over 3 scenes)
Rank (per category): (of 50)
No results for this dataset.
Google Urban dataset / Stereo track
mAA at 10 degrees: N/A (±N/A over N/A run(s) / ±N/A over 17 scenes)
Rank (per category): (of 50)
No results for this dataset.
Google Urban dataset / Multiview track
mAA at 10 degrees: N/A (±N/A over N/A run(s) / ±N/A over 17 scenes)
Rank (per category): (of 50)
No results for this dataset.