R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910908753641472 |
|---|---|
| author | Jiang, Xudong Wang, Fangjinhua Galliani, Silvano Vogel, Christoph Pollefeys, Marc |
| author_facet | Jiang, Xudong Wang, Fangjinhua Galliani, Silvano Vogel, Christoph Pollefeys, Marc |
| contents | Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination changes or image-level ambiguities, it remains a less robust alternative to feature matching methods. This work aims to close the gap. We introduce a covisibility graph-based global encoding learning and data augmentation strategy, along with a depth-adjusted reprojection loss to facilitate implicit triangulation. Additionally, we revisit the network architecture and local feature extraction module. Our method achieves state-of-the-art on challenging large-scale datasets without relying on network ensembles or 3D supervision. On Aachen Day-Night, we are 10$\times$ more accurate than previous SCR methods with similar map sizes and require at least 5$\times$ smaller map sizes than any other SCR method while still delivering superior accuracy. Code is available at: https://github.com/cvg/scrstudio . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization Jiang, Xudong Wang, Fangjinhua Galliani, Silvano Vogel, Christoph Pollefeys, Marc Computer Vision and Pattern Recognition Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination changes or image-level ambiguities, it remains a less robust alternative to feature matching methods. This work aims to close the gap. We introduce a covisibility graph-based global encoding learning and data augmentation strategy, along with a depth-adjusted reprojection loss to facilitate implicit triangulation. Additionally, we revisit the network architecture and local feature extraction module. Our method achieves state-of-the-art on challenging large-scale datasets without relying on network ensembles or 3D supervision. On Aachen Day-Night, we are 10$\times$ more accurate than previous SCR methods with similar map sizes and require at least 5$\times$ smaller map sizes than any other SCR method while still delivering superior accuracy. Code is available at: https://github.com/cvg/scrstudio . |
| title | R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01421 |