This is the gsplat module for the paper titled "GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting ".
[code][paper][project page]
pip install -e .[dev]For more detail development instructions, please refer to ./docs/DEV.md.
Our code was developed based on gsplat. This is a concise and easily extensible Gaussian splatting library.
If you find our GaussianImage paradigm useful or relevant to your research, please kindly cite our paper:
@inproceedings{zhang2024gaussianimage,
title={GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting},
author={Zhang, Xinjie and Ge, Xingtong and Xu, Tongda and He, Dailan and Wang, Yan and Qin, Hongwei and Lu, Guo and Geng, Jing and Zhang, Jun},
booktitle={European Conference on Computer Vision},
year={2024}
}