Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization
It addresses the challenge of accurate and generalizable visual localization for applications like robotics and AR, with incremental improvements over existing regression methods.
The paper tackles the problem of visual localization by introducing Reloc3r, a framework that achieves high-quality camera pose estimates in real time and generalizes to novel scenes, as demonstrated on six public datasets.
Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera poses have gained popularity due to their fast inference capabilities. However, existing methods struggle to either generalize well to new scenes or provide accurate camera pose estimates. To address these issues, we present Reloc3r, a simple yet effective visual localization framework. It consists of an elegantly designed relative pose regression network, and a minimalist motion averaging module for absolute pose estimation. Trained on approximately eight million posed image pairs, Reloc3r achieves surprisingly good performance and generalization ability. We conduct extensive experiments on six public datasets, consistently demonstrating the effectiveness and efficiency of the proposed method. It provides high-quality camera pose estimates in real time and generalizes to novel scenes. Code: https://github.com/ffrivera0/reloc3r.