GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
This addresses camera pose estimation for 3DGS representations, offering a generalizable solution without retraining, though it is incremental as it builds on existing 3DGS frameworks.
The paper tackles visual localization for 3D Gaussian Splatting scenes by matching scene and image features, achieving competitive performance on benchmarks and outperforming existing 3DGS-based methods.
We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We accomplish this by robustly matching scene features to image features. Scene features are produced by downsampling and encoding the 3D Gaussians while image features are obtained by encoding image patches. Our algorithm proceeds in three steps, starting with coarse matching, then fine matching, and finally by applying pose refinement for an accurate final estimate. Importantly, our method leverages the explicit 3DGS scene representation for visual localization without requiring modifications, retraining, or additional reference images. We evaluate GSVisLoc on both indoor and outdoor scenes, demonstrating competitive localization performance on standard benchmarks while outperforming existing 3DGS-based baselines. Moreover, our approach generalizes effectively to novel scenes without additional training.