CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localization
Mao, Xindong, Li, Hang, Wu, Yuchen, Li, Jiahe, Bai, Xiao, Zheng, Jin
原文摘要
Scene Coordinate Regression (SCR) has emerged as a memory-efficient paradigm for visual localization. While SCR has demonstrated performance comparable to classic feature matching based approaches in small-scale scenes, it has consistently underperformed in large-scale environments. Large-scale localization is hampered by two challenges: sparse co-visibility and local appearance ambiguity. In this work, we propose CoLoR, a novel training framework tailored for large-scale SCR. First, we explicitly and efficiently partition scene points into multi-view and single-view sets and introduce a two-stage bootstrapping paradigm to provide complete and strong supervision for all points. Second, we propose a multi-granularity retrieval feature, which unifies the conventional global and local features as retrieval-oriented representations at the image and pixel levels, respectively, to enforce feature consistency. Our method achieves state-of-the-art performance on multiple challenging large-scale datasets and significantly narrows the accuracy gap with classical feature matching based approaches while retaining a compact map size.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表