# GRLoc: Geometric Representation Regression for Visual Localization

arXiv: https://arxiv.org/abs/2511.13864 · HTML: https://mlsanity.com/paper/2511.13864/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 64 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 30 of 47)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [LENS: Localization enhanced by NeRF synthesis](https://mlsanity.com/paper/2110.06558/) (2021)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Learning Multi-Scene Absolute Pose Regression with Transformers](https://mlsanity.com/paper/2103.11468/) (2021)
- [Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses](https://mlsanity.com/paper/2305.14059/) (2023)
- [DFNet: Enhance Absolute Pose Regression with Direct Feature Matching](https://mlsanity.com/paper/2204.00559/) (2022)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [Robust Image Retrieval-based Visual Localization using Kapture](https://mlsanity.com/paper/2007.13867/) (2020)
- [On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation](https://mlsanity.com/paper/2109.00524/) (2021)
- [Direct-PoseNet: Absolute Pose Regression with Photometric Consistency](https://mlsanity.com/paper/2104.04073/) (2021)
- [GLACE: Global Local Accelerated Coordinate Encoding](https://mlsanity.com/paper/2406.04340/) (2024)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [Neural Refinement for Absolute Pose Regression with Feature Synthesis](https://mlsanity.com/paper/2303.10087/) (2023)

## Built on by (most cited first, 1 of 1)

- [NaCR: Visual Localization via NeRF-aided Camera Ray Regression](https://mlsanity.com/paper/2609.25907/) (2026)

## Abstract (arXiv)

Absolute Pose Regression (APR) has emerged as a compelling paradigm for visual localization. However, APR models typically operate as black boxes, directly regressing a 6-DoF pose from a query image, which can lead to memorizing training views rather than understanding 3D scene geometry. In this work, we propose a geometrically-grounded alternative. Inspired by novel view synthesis, which renders images from intermediate geometric representations, we reformulate APR as its inverse that regresses the underlying 3D representations directly from the image, and we name this paradigm Geometric Representation Regression (GRR). Our model explicitly predicts two disentangled geometric representations in the world coordinate system: (1) a raymap's directions to estimate camera rotation, and (2) a corresponding pointmap to estimate camera translation. The final camera pose is then recovered from these geometric components using a differentiable deterministic solver. This disentangled approach, which separates the learned visual-to-geometry mapping from the final pose calculation, introduces a strong geometric prior into the network. We find that the explicit decoupling of rotation and translation predictions measurably boosts performance. We demonstrate state-of-the-art performance on 7-Scenes and Cambridge Landmarks datasets, validating that modeling the inverse rendering process is a more robust path toward generalizable absolute pose estimation.