English | 简体中文

XRLocalization is an open source visual localization toolbox based on Python. It is a part of the OpenXRLab project.

• Robust and efficient large-scale feature-based visual localization
• Both offline and online visual localization are supported
• A hierarchical framework that can easily integrate new features and matching methods

• Installation
• Quick Start
• Benchmark Evaluation
• Customizing New Feature
• Customizing Your Map
• Building AR Application

Please refer to benchmark.

Please refer to here for building your own AR application. Here is an AR demo based on XRLocalization.

The license of our codebase is Apache-2.0. Note that this license only applies to code in our library, the dependencies of which are separate and individually licensed. We would like to pay tribute to open-source implementations to which we rely on. Please be aware that using the content of dependencies may affect the license of our codebase. Some supported methods may carry additional licenses.

Please refer to FAQ for frequently asked questions.

If you use this toolbox or benchmark in your research, please cite this project.

@misc{xrlocalization,
    title={OpenXRLab Visual Localization Toolbox and Server},
    author={XRLocalization Contributors},
    howpublished = {\url{https://github.com/openxrlab/xrlocalization}},
    year={2022}
}

If you use Geometry-Aided Matching in your research, please cite:

@misc{https://doi.org/10.48550/arxiv.2211.08712,
  url = {https://arxiv.org/abs/2211.08712},
  author = {Yu, Hailin and Feng, Youji and Ye, Weicai and Jiang, Mingxuan and Bao, Hujun and Zhang, Guofeng},
  title = {Improving Feature-based Visual Localization by Geometry-Aided Matching},
  publisher = {arXiv},
  year = {2022},
}

and

@inproceedings{yu2020learning,
  title={Learning bipartite graph matching for robust visual localization},
  author={Yu, Hailin and Ye, Weicai and Feng, Youji and Bao, Hujun and Zhang, Guofeng},
  booktitle={2020 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)},
  pages={146--155},
  year={2020},
  organization={IEEE}
}

We appreciate all contributions to improve XRLocalization. Please refer to CONTRIBUTING.md for the contributing guideline.

XRLocalization is an open source project that is contributed by researchers and engineers from both the academia and the industry. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new models.

• XRPrimer: OpenXRLab foundational library for XR-related algorithms.
• XRSLAM: OpenXRLab Visual-inertial SLAM Toolbox and Benchmark.
• XRSfM: OpenXRLab Structure-from-Motion Toolbox and Benchmark.
• XRLocalization: OpenXRLab Visual Localization Toolbox and Server.
• XRMoCap: OpenXRLab Multi-view Motion Capture Toolbox and Benchmark.
• XRMoGen: OpenXRLab Human Motion Generation Toolbox and Benchmark.
• XRNeRF: OpenXRLab Neural Radiance Field (NeRF) Toolbox and Benchmark.