R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
This work addresses the robustness gap in visual localization for applications like robotics and AR, offering a more efficient and accurate alternative to existing methods, though it is incremental in improving SCR techniques.
The paper tackles the robustness problem of scene coordinate regression (SCR) methods in visual localization under complex illumination changes and image-level ambiguities, achieving state-of-the-art accuracy on large-scale datasets with 10x higher accuracy than previous SCR methods and at least 5x smaller map sizes.
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 .