# GSFeatLoc: Visual Localization Using Feature Correspondence on 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2504.20379 · HTML: https://mlsanity.com/paper/2504.20379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation](https://mlsanity.com/paper/2210.10108/) (2022)
- [3D Gaussian Splatting in Robotics: A Survey](https://mlsanity.com/paper/2410.12262/) (2024)
- [6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model](https://mlsanity.com/paper/2407.15484/) (2024)
- [NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods](https://mlsanity.com/paper/2406.17345/) (2024)
- [3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization](https://mlsanity.com/paper/2403.11367/) (2024)
- [GSLoc: Visual Localization with 3D Gaussian Splatting](https://mlsanity.com/paper/2410.06165/) (2024)
- [A Survey on Monocular Re-Localization: From the Perspective of Scene Map Representation](https://mlsanity.com/paper/2311.15643/) (2023)
- [Marrying NeRF with Feature Matching for One-step Pose Estimation](https://mlsanity.com/paper/2404.00891/) (2024)

## Abstract (arXiv)

In this paper, we present a method for localizing a query image with respect to a precomputed 3D Gaussian Splatting (3DGS) scene representation. First, the method uses 3DGS to render a synthetic RGBD image at some initial pose estimate. Second, it establishes 2D-2D correspondences between the query image and this synthetic image. Third, it uses the depth map to lift the 2D-2D correspondences to 2D-3D correspondences and solves a perspective-n-point (PnP) problem to produce a final pose estimate. Results from evaluation across three existing datasets with 38 scenes and over 2,700 test images show that our method significantly reduces both inference time (by over two orders of magnitude, from more than 10 seconds to as fast as 0.1 seconds) and estimation error compared to baseline methods that use photometric loss minimization. Results also show that our method tolerates large errors in the initial pose estimate of up to 55deg in rotation and 1.1 units in translation (normalized by scene scale), achieving final pose errors of less than 5deg in rotation and 0.05 units in translation on 90% of images from the Synthetic NeRF and Mip-NeRF360 datasets and on 42% of images from the more challenging Tanks and Temples dataset.