English | 简体中文

XRSfM is an open-source SfM codebase. It is a part of the OpenXRLab project. A detailed introduction can be found in introduction.md.

If you find this project useful in your research, please consider cite:

@misc{xrsfm,
    title={OpenXRLab Structure-from-Motion Toolbox and Benchmark},
    author={XRSfM Contributors},
    howpublished = {\url{https://github.com/openxrlab/xrsfm}},
    year={2022}
}

If you use the covisibility-based matching method for your research, please cite:

@inproceedings{ye2020efficient,
  title={Efficient Covisibility-based Image Matching for Large-Scale SfM},
  author={Ye, Zhichao and Zhang, Guofeng and Bao, Hujun},
  booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
  year={2020}
}

@misc{ye2023ecsfm,
  title = {EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Images},
  author = {Ye, Zhichao and Bao, Chong and Zhou, Xin and Liu, Haomin and Bao, Hujun and Zhang, Guofeng},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2023},
  publisher={IEEE}
}

1.Build the library manually as described in installation.md.

2.Download the provided test data or prepare data with your own images.

3.Run the following script to automatically reconstruction:

python3 ./scripts/run_test_data.py --workspace_path ${workspace_path}$

Refer to tutorial.md for more details.

In addition to the reconstruction function, OpenXRLab project also provides localization function. Users can build a simple cloud-end combined ARDemo. For more information, please refer to ARDemo.

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.

XRSfM 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.

• 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.