GauLoc: 3D Gaussian Splatting-based Camera Relocalization
No Thumbnail Available
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
3D Gaussian Splatting (3DGS) has emerged as a promising representation for scene reconstruction and novel view synthesis for its explicit representation and real-time capabilities. This technique thus holds immense potential for use in mapping applications. Consequently, there is a growing need for an efficient and effective camera relocalization method to complement the advantages of 3DGS. This paper presents a camera relocalization method, namely GauLoc, in a scene represented by 3DGS. Unlike previous methods that rely on pose regression or photometric alignment, our proposed method leverages the differential rendering capability provided by 3DGS. The key insight of our work is the proposed implicit featuremetric alignment, which effectively optimizes the alignment between rendered keyframes and the query frames, and leverages the epipolar geometry to facilitate the convergence of camera poses conditioned explicit 3DGS representation. The proposed method significantly improves the relocalization accuracy even in complex scenarios with large initial camera rotation and translation deviations. Extensive experiments validate the effectiveness of our proposed method, showcasing its potential to be applied in many realworld applications. Source code will be released at https://github.com/xinzhe11/GauLoc.
Description
CCS Concepts: Computing methodologies → Image-based rendering; Computer vision
@article{10.1111:cgf.15256,
journal = {Computer Graphics Forum},
title = {{GauLoc: 3D Gaussian Splatting-based Camera Relocalization}},
author = {Xin, Zhe and Dai, Chengkai and Li, Ying and Wu, Chenming},
year = {2024},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.15256}
}