用动态二分查找加速高斯混合熵编码，速度提升90倍
FlashGMM: Fast Gaussian Mixture Entropy Model for Learned Image Compression
- 通过动态二分查找替代传统CDF查表，消除编码瓶颈
- 在不损失率失真性能前提下，编码速度最高提升90倍
- 适合需要高速图像压缩的实时应用开发人员
高性能学习型图像压缩编码器需要灵活的概率模型来拟合潜在表示。高斯混合模型（GMM）被提出以满足这一需求，但其在使用rANS编码时因需构建庞大的累积分布函数（CDF）表而存在显著运行时性能瓶颈。本文提出一种快速编码算法，完全消除该瓶颈：利用CDF的单调性，解码器采用动态二分查找定位符号，无需昂贵的表构建与查表操作。结合SIMD优化与数值近似，本方法使GMM熵编码速度最高提升约90倍，且未牺牲率失真性能，显著提升了基于GMM的编码器实用性。代码将公开于https://github.com/tokkiwa/FlashGMM。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。