Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Murai, Shimon, Lin, Fangzheng, Katto, Jiro
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.18815
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914052230348800
author Murai, Shimon
Lin, Fangzheng
Katto, Jiro
author_facet Murai, Shimon
Lin, Fangzheng
Katto, Jiro
contents High-performance learned image compression codecs require flexible probability models to fit latent representations. Gaussian Mixture Models (GMMs) were proposed to satisfy this demand, but suffer from a significant runtime performance bottleneck due to the large Cumulative Distribution Function (CDF) tables that must be built for rANS coding. This paper introduces a fast coding algorithm that entirely eliminates this bottleneck. By leveraging the CDF's monotonic property, our decoder performs a dynamic binary search to find the correct symbol, eliminating the need for costly table construction and lookup. Aided by SIMD optimizations and numerical approximations, our approach accelerates the GMM entropy coding process by up to approximately 90x without compromising rate-distortion performance, significantly improving the practicality of GMM-based codecs. The implementation will be made publicly available at https://github.com/tokkiwa/FlashGMM.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlashGMM: Fast Gaussian Mixture Entropy Model for Learned Image Compression
Murai, Shimon
Lin, Fangzheng
Katto, Jiro
Image and Video Processing
High-performance learned image compression codecs require flexible probability models to fit latent representations. Gaussian Mixture Models (GMMs) were proposed to satisfy this demand, but suffer from a significant runtime performance bottleneck due to the large Cumulative Distribution Function (CDF) tables that must be built for rANS coding. This paper introduces a fast coding algorithm that entirely eliminates this bottleneck. By leveraging the CDF's monotonic property, our decoder performs a dynamic binary search to find the correct symbol, eliminating the need for costly table construction and lookup. Aided by SIMD optimizations and numerical approximations, our approach accelerates the GMM entropy coding process by up to approximately 90x without compromising rate-distortion performance, significantly improving the practicality of GMM-based codecs. The implementation will be made publicly available at https://github.com/tokkiwa/FlashGMM.
title FlashGMM: Fast Gaussian Mixture Entropy Model for Learned Image Compression
topic Image and Video Processing
url https://arxiv.org/abs/2509.18815