Clustered Codebook Quantization for 2D Gaussian-based Image Compression
Abstract
Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality
Cite
@article{arxiv.2607.05667,
title = {Clustered Codebook Quantization for 2D Gaussian-based Image Compression},
author = {Runze Cheng and Yicheng Zhan and Josef Spjut and Kaan Akşit},
journal= {arXiv preprint arXiv:2607.05667},
year = {2026}
}
Comments
3 pages. Accepted to ACM SIGGRAPH 2026 Poster Track. Code available at https://github.com/complight/Cluster_Guided_Vector_Quantization