JPEG AI用学习方法提升图像编码效率，兼顾人眼与机器需求。
An Overview of the JPEG AI Learning-Based Image Coding Standard
- 基于学习的单流压缩框架，支持人眼与机器双重用途。
- 相比现有标准，多指标下码率降低显著，如MS-SSIM等。
- 设计兼容性强，适合跨设备部署，2025年初将完成第一版。
JPEG AI 是由联合图像专家组（JPEG）开发的新兴学习型图像编码标准。其目标是构建一个实用的学习型图像编码标准，提供单一数据流、紧凑的压缩域表示，同时满足人类视觉与机器处理需求。计划于2025年初完成首版，重点面向人眼视觉任务，在MS-SSIM、FSIM、VIF、VMAF、PSNR-HVS、IW-SSIM和NLPD等质量指标上表现出显著的BD-rate降低。为确保广泛互操作性，该标准集成多种设计特性，支持在多样设备和应用中的部署。本文综述了JPEG AI标准的技术特征与核心特性。
原文摘要 · Abstract (English)
JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization and machine consumption. Scheduled for completion in early 2025, the first version of JPEG AI focuses on human vision tasks, demonstrating significant BD-rate reductions compared to existing standards, in terms of MS-SSIM, FSIM, VIF, VMAF, PSNR-HVS, IW-SSIM and NLPD quality metrics. Designed to ensure broad interoperability, JPEG AI incorporates various design features to support deployment across diverse devices and applications. This paper provides an overview of the technical features and characteristics of the JPEG AI standard.
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。