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 will be available at: https://github.com/cvg/scrstudio .
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
The work introduces a method using a covisibility graph and depth-adjusted reprojection loss to enhance learning-based visual localization, achieving superior accuracy on large-scale datasets with smaller map sizes compared to SCR methods.
- Year
- 2025
- Venue
- CVPR 2025 1
- Authors
- 5
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2501.01421ARXIV-DEFAULT
- TL;DR
- Semantic Scholar