OpenStereo is a flexible and extensible project for stereo matching.
Distributed Data Parallel (DDP) mode is used during both the training and testing phases.Auto Mixed Precision (AMP) option is available.tensorboard and logging to log everything, which looks pretty.Please see 0.get_started.md. We also provide the following tutorials for your reference:
Results and models are available in the model zoo.
AANet ACVNet CascadeStereo CFNet COEX DenseMatching FADNet++ GwcNet MSNet PSMNet RAFT STTR OpenGait IGEV
@article{OpenStereo,
title={OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline},
author={Guo, Xianda and Zhang, Chenming and Lu, Juntao and Wang, Yiqi and Duan, Yiqun and Yang, Tian and Zhu, Zheng and Chen, Long},
journal={arXiv preprint arXiv:2312.00343},
year={2023}
}
@article{guo2024lightstereo,
title={LightStereo: Channel Boost Is All Your Need for Efficient 2D Cost Aggregation},
author={Guo, Xianda and Zhang, Chenming and Nie, Dujun and Zheng, Wenzhao and Zhang, Youmin and Chen, Long},
journal={arXiv preprint arXiv:2406.19833},
year={2024}
}
@article{guo2024stereoanything,
title={Stereo Anything: Unifying Stereo Matching with Large-Scale Mixed Data},
author={Guo, Xianda and Zhang, Chenming and Zhang, Youmin and Nie, Dujun and Wang, Ruilin and Zheng, Wenzhao and Poggi, Matteo and Chen, Long},
journal={arXiv preprint arXiv:2411.14053},
year={2024}
}Note: This code is only used for academic purposes, people cannot use this code for anything that might be considered commercial use.