APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 6

2D Gaussian Splatting for Image Compression

Pingping Zhang, City University of Hong Kong, China, Xiangrui Liu, City University of Hong Kong, China, Meng Wang, City University of Hong Kong, China, Shiqi Wang, City University of Hong Kong, China, shiqwang@cityu.edu.hk , Sam Kwong, Lingnan University, China, samkwong@ln.edu.hk
 
Suggested Citation
Pingping Zhang, Xiangrui Liu, Meng Wang, Shiqi Wang and Sam Kwong (2024), "2D Gaussian Splatting for Image Compression", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 6, e501. http://dx.doi.org/10.1561/116.20240025

Publication Date: 30 Oct 2024
© 2024 P. Zhang, X. Liu, M. Wang, S. Wang and S. Kwong
 
Subjects
Speech and image compression,  Data compression,  Quantization,  Coding and compression,  Image and video processing
 
Keywords
Gaussian splattingimage compressionvector quantization
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 281 times

In this article:
Introduction 
Related Work 
Approach 
Experiments 
Conclusions 
References 

Abstract

The implicit neural representation (INR) employed in image compression shows high decoding efficiency, yet it requires long encoding times due to the need for the model training tailored to the specific image being coded. Thus, we propose a new image compression scheme leveraging the 2D Gaussian splatting technique to accelerate encoding speed and maintain decoding efficiency. Specifically, we parameterize these Gaussians with key attributes including position, anisotropic covariance, color, and opacity coefficients, totaling 9 parameters per Gaussian. We initialize these Gaussians by sampling points from the image, followed by employing an α- blending mechanism to determine the color values of each pixel. For compact attribute representation, we adopt a K-means based vector quantization approach for anisotropic covariance, color and opacity coefficients. Additionally, we introduce an adaptive dense control methodology to dynamically adjust Gaussian numbers, facilitating automatic point reduction or augmentation. Finally, the position, codebooks and indexes of other attributes are quantized and compressed by the lossless entropy coding. Our experimental evaluation demonstrates that our method achieves faster encoding speeds compared to other INR techniques while exhibiting comparable decoding speeds.

The source code is available via the following link: https://github.com/ppingzhang/2DGS_ImageCompression.

DOI:10.1561/116.20240025

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Deep Learning-Based Data Compression
See the other articles that are part of this special issue.