Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Wenyue Chen¹, Peng Li², Wangguandong Zheng³, Chengfeng Zhao², Mengfei Li², Yaolong Zhu¹, Zhiyang Dou⁴, Ronggang Wang¹, Yuan Liu²

¹ Peking University ² The Hong Kong University of Science and Technology ³ Southeast University ⁴ The University of Hong Kong

Official code of SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

              

Environment Setup

We tested on H800 with CUDA 12.1. Follow the steps below to set up the environment.

1) Create Conda env and install PyTorch (CUDA 12.1)

conda create -n SyncHuman python=3.10
conda activate SyncHuman

# PyTorch 2.1.1 + CUDA 12.1
conda install pytorch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 pytorch-cuda=12.1 -c pytorch -c nvidia

2) Follow trellis to setup the env

3) Install remaining Python packages

pip install accelerate safetensors==0.4.5 diffusers==0.29.1 transformers==4.36.0

Inference

git clone https://github.com/xishuxishu/SyncHuman.git

1) download ckpts

cd SyncHuman
python download.py

The file organization structure is shown below：

SyncHuman
├── ckpts
│   ├── OneStage
│   └── SecondStage
├── SyncHuman
├── examples
├── inference_OneStage.py
├── inference_SecondStage.py
└── download.py

2) run the inference code

python inference_OneStage.py

python inference_SecondStage.py

If you want to change the example image used for inference, please modify the image_path in inference_OneStage.py.

Then you will get the final generated result at outputs/SecondStage/output.glb.

Ack

Our code is based on these wonderful works:

• TRELLIS
• PSHuman

📚 Citation

If you find this work useful, please cite our paper:

@article{chen2025synchuman,
  title={SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction},
  author={Chen, Wenyue and Li, Peng and Zheng, Wangguandong and Zhao, Chengfeng and Li, Mengfei and Zhu, Yaolong and Dou, Zhiyang and Wang, Ronggang and Liu, Yuan},
  journal={arXiv preprint arXiv:2510.07723},
  year={2025}
}