English

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

Image and Video Processing 2024-07-10 v5 Artificial Intelligence Computer Vision and Pattern Recognition Multimedia

Abstract

Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this requirement often hinders their use on low-end devices with limited memory. In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage. We first introduce 2D Gaussian to represent the image, where each Gaussian has 8 parameters including position, covariance and color. Subsequently, we unveil a novel rendering algorithm based on accumulated summation. Remarkably, our method with a minimum of 3×\times lower GPU memory usage and 5×\times faster fitting time not only rivals INRs (e.g., WIRE, I-NGP) in representation performance, but also delivers a faster rendering speed of 1500-2000 FPS regardless of parameter size. Furthermore, we integrate existing vector quantization technique to build an image codec. Experimental results demonstrate that our codec attains rate-distortion performance comparable to compression-based INRs such as COIN and COIN++, while facilitating decoding speeds of approximately 2000 FPS. Additionally, preliminary proof of concept shows that our codec surpasses COIN and COIN++ in performance when using partial bits-back coding. Code is available at https://github.com/Xinjie-Q/GaussianImage.

Keywords

Cite

@article{arxiv.2403.08551,
  title  = {GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting},
  author = {Xinjie Zhang and Xingtong Ge and Tongda Xu and Dailan He and Yan Wang and Hongwei Qin and Guo Lu and Jing Geng and Jun Zhang},
  journal= {arXiv preprint arXiv:2403.08551},
  year   = {2024}
}

Comments

Accepted by ECCV 2024. Project Page:https://xingtongge.github.io/GaussianImage-page/ Code: https://github.com/Xinjie-Q/GaussianImage

R2 v1 2026-06-28T15:18:45.937Z