Awesome
Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors (ICCV 2023)
<a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"></a>
Project Page | Paper | Code | Data
This is the official PyTorch implementation of Get3DHuman.
TODO:
- Synthetic data (with latent code)
- Inference code
- Pretrained weights
- Training Code
Requirements:
- Python 3
- PyTorch tested on 1.8.0+cu111
Inference:
- Download pretrained models from the following link and copy them into a same file.
S&T pretrained model or S&T pretrained model_v2.
- Enter the code path and run:
cd GET3DHUMAN_CODE_PATH
pip install -r requirements.txt
python inference.py --model_path PRETRAINED_MODELS_PATH --sample_num 1
The results will be saved in "./results". Like sample
Note: A GTX 3090 is recommended to run Get3DHuman, make sure enough GPU memory if using other cards.
Overview of our framework <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/pipeline.png" width="800"> <br /> </div>Multi-view images rendered by Blender. <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/sup_multi_view.jpg" width="600"> <br /> </div>Applications
Interpolation <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/sup_inter_0.jpg" width="600"> <br /> </div>Re-texturing <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/sup_recolor_all.jpg" width="600"> <br /> </div>Inversion <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/inversion.png" width="800"> <br /> </div>Rendering methods <br />
<div align="center"> <img src="https://github.com/X-zhangyang/Get3DHuman/blob/main/paper_figures/render_method.png" width="800"> <br /> </div>Citation
If you use Get3DHuman in your research, please consider the following BibTeX entry and give a star🌟!
@inproceedings{xiong2023Get3DHuman,
author = {Xiong, Zhangyang and Kang, Di and Jin, Derong and Chen, Weikai and Bao, Linchao and Cui, Shuguang and Han, Xiaoguang},
title = {Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model Using Pixel-Aligned Reconstruction Priors},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2023},
pages = {9287-9297}
}
Acknowledgements
Here are some great resources we benefit or utilize from: