JPEG AI首次实现移动端学习型图像压缩，支持可变码率与区域优先编码。
Overview of Variable Rate Coding in JPEG AI
- 引入三维质量图、快速码率匹配算法与训练策略实现连续可调码率。
- 低复杂度主档比VVC内插编码高13.1%的BD-rate性能，高复杂度档达19.2%。
- 适合移动设备部署，支持重点区域质量提升，适用于对画质敏感场景。
实证表明，基于学习的图像压缩可超越传统框架。这推动了基于学习的图像编解码器的标准化进程，即联合图像专家组（JPEG AI）。JPEG AI的目标是提升压缩效率，并提供软硬件友好的解决方案。据研究，JPEG AI是首个可在移动设备上实现学习型图像编码的标准。本文综述了JPEG AI中的可变码率编码功能，包含三项可变码率适配：三维质量图、快速码率匹配算法和训练策略。这些适配实现了最高2.0 bpp的连续码率函数，具备高性能、灵活的色彩分量比特分配能力以及针对特定应用场景的感兴趣区域功能。性能评估涵盖客观与主观结果。在客观码率匹配方面，低复杂度主档相比VVC内插编码获得13.1%的BD-rate增益，高复杂度档达19.2%。该BD-rate为七种感知度量在JPEG AI通用测试条件下的均值。主观结果展示了对感兴趣区域质量提升的实例。
原文摘要 · Abstract (English)
Empirical evidence has demonstrated that learning-based image compression can outperform classical compression frameworks. This has led to the ongoing standardization of learned-based image codecs, namely Joint Photographic Experts Group (JPEG) AI. The objective of JPEG AI is to enhance compression efficiency and provide a software and hardwarefriendly solution. Based on our research, JPEG AI represents the first standardization that can facilitate the implementation of a learned image codec on a mobile device. This article presents an overview of the variable rate coding functionality in JPEG AI, which includes three variable rate adaptations: a threedimensional quality map, a fast bit rate matching algorithm, and a training strategy. The variable rate adaptations offer a continuous rate function up to 2.0 bpp, exhibiting a high level of performance, a flexible bit allocation between different color components, and a region of interest function for the specified use case. The evaluation of performance encompasses both objective and subjective results. With regard to the objective bit rate matching, the main profile with low complexity yielded a 13.1% BD-rate gain over VVC intra, while the high profile with high complexity achieved a 19.2% BD-rate gain over VVC intra. The BD-rate result is calculated as the mean of the seven perceptual metrics defined in the JPEG AI common test conditions. With respect to subjective results, the example of improving the quality of the region of interest is illustrated.
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。