Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Chongjie Ye^1,2*, Yushuang Wu^2*, Ziteng Lu¹, Jiahao Chang¹, Xiaoyang Guo², Jiaqing Zhou², Hao Zhao³, Xiaoguang Han^1#

ICCV 2025

¹The Chinese University of Hong Kong, Shenzhen,   ²ByteDance,   ³AIR, Tsinghua University

Hi3DGen target at generating high-fidelity 3D geometry from images using normal maps as an intermediate representation. The framework addresses limitations in existing methods that struggle to reproduce fine-grained geometric details from 2D inputs.

Installation

Clone the repo:

git clone --recursive https://github.com/ByteDance/Hi3DGen.git
cd Hi3DGen

Create a conda environment (optional):

conda create -n stablex python=3.10
conda activate stablex

Install dependencies:

# pytorch (select correct CUDA version)
pip install torch==2.4.0 torchvision==0.19.0 --index-url https://download.pytorch.org/whl/{your-cuda-version}
pip install spconv-cu{your-cuda-version}==2.3.6 xformers==0.0.27.post2
# other dependencies
pip install -r requirements.txt

Local Demo 🤗

Run by:

python app.py

Citation

If you find this work helpful, please consider citing our paper:

@article{ye2025hi3dgen,
  title={Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging},
  author={Ye, Chongjie and Wu, Yushuang and Lu, Ziteng and Chang, Jiahao and Guo, Xiaoyang and Zhou, Jiaqing and Zhao, Hao and Han, Xiaoguang},
  journal={arXiv preprint arXiv:2503.22236}, 
  year={2025}
}