IGEV++

IGEV++ is a high-performance stereo matching model introduced in the paper:

"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching"

Paper: https://arxiv.org/pdf/2409.00638 Venue: IEEE TPAMI 2025

Authors:
Gangwei Xu, Xianqi Wang, Zhaoxing Zhang, Junda Cheng, Chunyuan Liao, Xin Yang

Original Repo: https://github.com/gangweiX/IGEV-plusplus

Citation

@article{xu2025igev++,
  title={Igev++: Iterative multi-range geometry encoding volumes for stereo matching},
  author={Xu, Gangwei and Wang, Xianqi and Zhang, Zhaoxing and Cheng, Junda and Liao, Chunyuan and Yang, Xin},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025}
}

@inproceedings{xu2023iterative,
  title={Iterative Geometry Encoding Volume for Stereo Matching},
  author={Xu, Gangwei and Wang, Xianqi and Ding, Xiaohuan and Yang, Xin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={21919--21928},
  year={2023}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for shriarul5273/IGEV-plusplus-Stereo