pith. sign in

arxiv: 2508.18242 · v1 · pith:NK4YDVOInew · submitted 2025-08-25 · 💻 cs.CV

GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations

classification 💻 cs.CV
keywords scenefeaturesimagelocalizationgsvislocmatchingvisualadditional
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SG2Loc: Sequential Visual Localization on 3D Scene Graphs

    cs.CV 2026-06 unverdicted novelty 6.0

    A particle-filter sequential localization method that matches per-patch semantic features from images to objects in a compact 3D scene graph via mesh projection and visibility.

  2. LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios

    cs.CV 2026-04 unverdicted novelty 5.0

    LSGS-Loc delivers state-of-the-art accuracy and robustness for 3DGS-based visual localization in large UAV scenes via scale-aware initialization and reliability masking without scene-specific training.