# Learning to Localize in New Environments from Synthetic Training Data

arXiv: https://arxiv.org/abs/2011.04539 · HTML: https://mlsanity.com/paper/2011.04539/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 21 of 21)

- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses](https://mlsanity.com/paper/2305.14059/) (2023)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [GLACE: Global Local Accelerated Coordinate Encoding](https://mlsanity.com/paper/2406.04340/) (2024)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes](https://mlsanity.com/paper/2109.09690/) (2021)
- [Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression](https://mlsanity.com/paper/2211.14950/) (2022)
- [Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments](https://mlsanity.com/paper/2304.07250/) (2023)
- [SRPose: Two-view Relative Pose Estimation with Sparse Keypoints](https://mlsanity.com/paper/2407.08199/) (2024)
- [A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features](https://mlsanity.com/paper/2510.00978/) (2025)
- [Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer](https://mlsanity.com/paper/2512.21883/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset](https://mlsanity.com/paper/2303.02610/) (2023)
- [GRLoc: Geometric Representation Regression for Visual Localization](https://mlsanity.com/paper/2511.13864/) (2025)
- [ImLoc: Revisiting Visual Localization with Image-based Representation](https://mlsanity.com/paper/2601.04185/) (2026)
- [VVLoc: Prior-free 3-DoF Vehicle Visual Localization](https://mlsanity.com/paper/2602.00810/) (2026)
- [MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization](https://mlsanity.com/paper/2603.27170/) (2026)
- [NaCR: Visual Localization via NeRF-aided Camera Ray Regression](https://mlsanity.com/paper/2609.25907/) (2026)
- [Agentic Relative Camera Pose Estimation via Learned Ranking and Verification](https://mlsanity.com/paper/2609.38755/) (2026)

## Abstract (arXiv)

Most existing approaches for visual localization either need a detailed 3D model of the environment or, in the case of learning-based methods, must be retrained for each new scene. This can either be very expensive or simply impossible for large, unknown environments, for example in search-and-rescue scenarios. Although there are learning-based approaches that operate scene-agnostically, the generalization capability of these methods is still outperformed by classical approaches. In this paper, we present an approach that can generalize to new scenes by applying specific changes to the model architecture, including an extended regression part, the use of hierarchical correlation layers, and the exploitation of scale and uncertainty information. Our approach outperforms the 5-point algorithm using SIFT features on equally big images and additionally surpasses all previous learning-based approaches that were trained on different data. It is also superior to most of the approaches that were specifically trained on the respective scenes. We also evaluate our approach in a scenario where only very few reference images are available, showing that under such more realistic conditions our learning-based approach considerably exceeds both existing learning-based and classical methods.