jingheya

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction This model belongs to the family of official Lotus models. [](https://lotus3d.github.io/) [](https://arxiv.org/abs/2409.18124) [](https://huggingface.co/spaces/haodongli/Lotus) [](https://github.com/EnVision-Research/Lotus) Developed by: Jing He ✱ , Haodong Li ✱ , Wei Yin, Yixun Liang, Leheng Li, [Kaiqiang Zhou](), [Hongbo Zhang](), Bingbing Liu, Ying-Cong Chen✉

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction - This model belongs to the family of official Lotus models. - Compared to the previous version (jingheya/lotus-depth-g-v2-0-disparity), this model was trained with random flip augmentation and achieves better results. [](https://lotus3d.github.io/) [](https://arxiv.org/abs/2409.18124) [](https://huggingface.co/spaces/haodongli/Lotus) [](https://github.com/EnVision-Research/Lotus) Developed by: Jing He ✱ , Haodong Li ✱ , Wei Yin, Yixun Liang, Leheng Li, [Kaiqiang Zhou](), [Hongbo Zhang](), Bingbing Liu, Ying-Cong Chen✉