Clustered Codebook Quantization for 2D Gaussian-based Image Compression

July 06, 2026 Β· Grace Period Β· πŸ› ACM SIGGRAPH 2026 Poster Track

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Runze Cheng, Yicheng Zhan, Josef Spjut, Kaan Akşit arXiv ID 2607.05667 Category cs.CV: Computer Vision Cross-listed cs.GR Citations 0 Venue ACM SIGGRAPH 2026 Poster Track
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
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago