Lotus-2 / README.md
jingheya's picture
Update README.md
ea34cdb verified
---
license: apache-2.0
pipeline_tag: depth-estimation
---
# Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
This repository contains the official model weights of Lotus-2 (including the <b>core predictor</b>, <b>detail sharpener</b> and <b>local continuity module</b> for both <u>depth</u> and <u>normal</u> estimation).
[![Page](https://img.shields.io/badge/Project-Website-pink?logo=googlechrome&logoColor=white)](https://lotus-2.github.io/)
[![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=white)](https://huggingface.co/papers/2512.01030)
[![HuggingFace Demo (Depth)](https://img.shields.io/badge/🤗%20HuggingFace-Demo-yellow)](https://huggingface.co/spaces/haodongli/Lotus-2_Depth)
[![HuggingFace Demo (Normal)](https://img.shields.io/badge/🤗%20HuggingFace-Demo-yellow)](https://huggingface.co/spaces/haodongli/Lotus-2_Normal)
[![GitHub](https://img.shields.io/github/stars/EnVision-Research/Lotus-2?style=default&label=GitHub%20%E2%98%85&logo=github)](https://github.com/EnVision-Research/Lotus-2)
Devoloped by:
[Jing He](https://scholar.google.com/citations?hl=en&user=RsLS11MAAAAJ)<sup>1</sup>,
[Haodong Li](https://haodong-li.com/)<sup>12<span>&#10033;</span></sup>,
[Mingzhi Sheng]()<sup>1<span>&#10033;</span></sup>,
[Ying-Cong Chen](https://www.yingcong.me/)<sup>13&#9993;</sup>
![teaser](assets/teaser-1.jpg)
## Usage
Please refer to this [page](https://github.com/EnVision-Research/Lotus-2).