Hybrid-depth

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation (ICCV 2025)

The code is coming soon.

Citation

If you find our idea helpful, please cite our work at

@InProceedings{Zhang_2025_ICCV,
    author    = {Zhang, Wenyao and Liu, Hongsi and Li, Bohan and He, Jiawei and Qi, Zekun and Wang, Yunnan and Zhao, Shengyang and Yu, Xinqiang and Zeng, Wenjun and Jin, Xin},
    title     = {Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {6678-6692}
}