Iterative Geometry Encoding Volume for Stereo Matching
Paper • 2303.06615 • Published
IGEV-Stereo is a high-performance stereo matching model introduced in the paper:
"Iterative Geometry Encoding Volume for Stereo Matching"
Paper: https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Iterative_Geometry_Encoding_Volume_for_Stereo_Matching_CVPR_2023_paper.pdf
ArXiv: https://arxiv.org/abs/2303.06615
Venue: CVPR 2023
Authors:
Gangwei Xu, Xianqi Wang, Xiaohuan Ding, Xin Yang
Original Repo: https://github.com/gangweiX/IGEV
Extension (IGEV++): https://github.com/gangweiX/IGEV-plusplus
@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}
}
@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}
}