We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the robustness of our model in challenging outdoor environments, we incorporate an exposure-adaptive module within the 3DGS framework. Consequently, GS-CPR enables efficient one-shot pose refinement given a single RGB query and a coarse initial pose estimation. Our proposed approach surpasses leading NeRF-based optimization methods in both accuracy and runtime across indoor and outdoor visual localization benchmarks, achieving new state-of-the-art accuracy on two indoor datasets. The project page is available atthis https URL.
View on arXiv@article{liu2025_2408.11085,
title={ GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting },
author={ Changkun Liu and Shuai Chen and Yash Bhalgat and Siyan Hu and Ming Cheng and Zirui Wang and Victor Adrian Prisacariu and Tristan Braud },
journal={arXiv preprint arXiv:2408.11085},
year={ 2025 }
}