无需熵编码的高效图像压缩，速度提升5倍以上
Efficient Learned Image Compression without Entropy Coding
- 用无约束向量量化消除统计冗余，索引分布趋近最大熵
- 通过上下文自回归变换降低特征相关性，理论可等效熵编码效果
- 比传统方法快3倍编码、5倍解码，比特率降低67.86%
熵编码广泛用于典型学习型图像压缩（LIC）中，将潜在表示转换为紧凑比特流。然而，熵编码通常具有串行特性，成为编码延迟的主要瓶颈。为克服该问题，本文提出无熵编码学习型图像压缩（EF-LIC），一种多速率框架，通过去除统计与相关冗余，在低编码延迟下生成紧凑表示。首先，引入无约束向量量化，并证明其索引分布趋近最大熵边界，实现最小统计冗余。其次，提出一种上下文条件自回归变换，直接重参数化潜在变量以减少内部依赖。理论分析表明，EF-LIC在消除相关冗余方面可等效于含熵编码的典型LIC，从而达到相当的压缩性能。实验显示，EF-LIC在Kodak数据集上相较MS-ILLM的比特率降低达67.86%（以LPIPS衡量）。消融实验进一步表明，其压缩性能与基于熵编码的变体相当，同时编码速度提升超3倍，解码速度提升超5倍。
原文摘要 · Abstract (English)
Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we introduce unconstrained vector quantization and prove that its index distribution approaches the maximum-entropy bound, yielding minimal statistical redundancy. Second, we propose a context-conditioned autoregressive transform that directly reparameterizes the latents to reduce inter-dependency. Theoretical analysis shows that EF-LIC can remove correlation redundancy as effectively as typical LIC with entropy coding, leading to comparable compression performance. Experiments show EF-LIC achieves up to 67.86% bitrate reduction over MS-ILLM on Kodak with LPIPS. Ablation studies further show EF-LIC matches the compression performance of its entropy-coding based variant while achieving over $3\times$ faster encoding and $5\times$ faster decoding.
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。