Xuangeng Chu¹  Tatsuya Harada^1,2
1The University of Tokyo, ²RIKEN AIP

🤩 NeurIPS 2024 🤩

GAGAvatar reconstructs controllable 3D head avatars from single images.
GAGAvatar achieves one-shot 3DGS-based head reconstruction and ⚡️real-time⚡️ reenactment.
🔥 More results can be found in our Project Page. 🔥

Installation

Build environment

conda env create -f environment.yml
conda activate GAGAvatar

Install the 3DGS renderer

What’s the difference between this version and the original 3DGS?

• We changed the number of channels so that 3D Gaussians carry 32-dim features.
• We changed the package name to avoid conflict with the original Gaussian splash.

git clone --recurse-submodules [email protected]:xg-chu/diff-gaussian-rasterization.git
pip install ./diff-gaussian-rasterization
rm -rf ./diff-gaussian-rasterization

Prepare resources

Prepare resources with bash ./build_resources.sh.

Quick Start Guide

Driven by another image:

python inference.py -d ./demos/examples/2.jpg -i ./demos/examples/1.jpg

Driven by a tracked video:

python inference.py -d ./demos/drivers/obama -i ./demos/examples/1.jpg

Driven by a tracked image_lmdb:

python inference.py -d ./demos/drivers/vfhq_demo -i ./demos/examples/1.jpg

To test the inference speed, refer to the speed_test() function in inference.py.

To test your own images online, refer to lines 52-55 in inference.py.

Citation

If you find our work useful in your research, please consider citing:

@inproceedings{
    chu2024gagavatar,
    title={Generalizable and Animatable Gaussian Head Avatar},
    author={Xuangeng Chu and Tatsuya Harada},
    booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
    year={2024},
    url={https://openreview.net/forum?id=gVM2AZ5xA6}
}

Acknowledgements

Some part of our work is built based on FLAME, StyleMatte, EMICA and VGGHead. The GAGAvatar Logo is designed by Caihong Ning. We also thank the following projects for sharing their great work.

• FLAME: https://flame.is.tue.mpg.de
• StyleMatte: https://github.com/chroneus/stylematte
• EMICA: https://github.com/radekd91/inferno
• VGGHead: https://github.com/KupynOrest/head_detector