shriarul5273/CRE-Stereo

CREStereo

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

"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation"

Paper: https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Practical_Stereo_Matching_via_Cascaded_Recurrent_Network_With_Adaptive_Correlation_CVPR_2022_paper.pdf
ArXiv: https://arxiv.org/abs/2203.11483
Venue: CVPR 2022 (Oral)

Authors:
Jiankun Li, Peisen Wang, Pengfei Xiong, Tao Cai, Ziwei Yan, Lei Yang, Jiangyu Liu, Haoqiang Fan, Shuaicheng Liu

Original Repo: https://github.com/megvii-research/CREStereo

PyTorch Repo: https://github.com/ibaiGorordo/CREStereo-Pytorch

@inproceedings{li2022practical,
  title={Practical stereo matching via cascaded recurrent network with adaptive correlation},
  author={Li, Jiankun and Wang, Peisen and Xiong, Pengfei and Cai, Tao and Yan, Ziwei and Yang, Lei and Liu, Jiangyu and Fan, Haoqiang and Liu, Shuaicheng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={16263--16272},
  year={2022}
}