We present GSplatLoc, a camera localization method that leverages the differentiable rendering capabilities of 3D Gaussian splatting for ultra-precise pose estimation. By formulating pose estimation as a gradient-based optimization problem that minimizes discrepancies between rendered depth maps from a pre-existing 3D Gaussian scene and observed depth images, GSplatLoc achieves translational errors within 0.01 cm and near-zero rotational errors on the Replica dataset - significantly outperforming existing methods. Evaluations on the Replica and TUM RGB-D datasets demonstrate the method's robustness in challenging indoor environments with complex camera motions. GSplatLoc sets a new benchmark for localization in dense mapping, with important implications for applications requiring accurate real-time localization, such as robotics and augmented reality.
@article{arxiv.2412.20056,
title = {GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting},
author = {Atticus J. Zeller and Haijuan Wu},
journal= {arXiv preprint arXiv:2412.20056},
year = {2025}
}
Comments
11 pages, 2 figures. Code available at https://github.com/AtticusZeller/GsplatLoc