AI RESEARCH
MultiLoc: Multi-view Guided Relative Pose Regression for Fast and Robust Visual Re-Localization
arXiv CS.CV
•
ArXi:2603.27170v1 Announce Type: new Relative Pose Regression (RPR) generalizes well to unseen environments, but its performance is often limited due to pairwise and local spatial views. To this end, we propose MultiLoc, a novel multi-view guided RPR model trained at scale, equipping relative pose regression with globally consistent spatial and geometric understanding. Specifically, our method jointly fuses multiple reference views and their associated camera poses in a single forward pass, enabling accurate zero-shot pose estimation with real-time efficiency.