MultiLoc: Multi-view Guided Relative Pose Regression for Fast and Robust Visual Re-Localization

TL;DR

MultiLoc introduces a multi-view guided relative pose regression model that fuses multiple reference views for fast, accurate, and robust visual re-localization across diverse environments, outperforming existing methods.

Contribution

The paper presents a novel multi-view guided RPR model with a co-visibility retrieval strategy, achieving state-of-the-art results in visual re-localization and relative pose estimation.

Findings

Outperforms SOTA RPR methods on multiple datasets.

Achieves real-time, zero-shot pose estimation.

Demonstrates robust generalization across indoor and outdoor environments.

Abstract

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. To reliably supply informative context, we further propose a co-visibility-driven retrieval strategy for geometrically relevant reference view selection. MultiLoc establishes a new benchmark in visual re-localization, consistently outperforming existing state-of-the-art (SOTA) relative pose regression (RPR) methods across diverse datasets, including WaySpots, Cambridge Landmarks, and Indoor6. Furthermore, MultiLoc's pose regressor exhibits SOTA performance in relative pose estimation, surpassing RPR, feature matching and non-regression-based techniques on the MegaDepth-1500, ScanNet-1500, and ACID benchmarks. These results demonstrate robust domain generalization of MultiLoc across indoor, outdoor and natural environments. Code will be made publicly available.