发表机构
Université du Québec à Rimouski; Kingston University London（魁北克大学里穆斯基分校; 伦敦金斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对基于DCT的压缩图像，提出两种基于方差或标准差权重重分配全局MSE以近似局部MSE的方法，实现从MSE估计SSIM，其在多数据集实验中显著优于全局MSE基线，且可自然扩展至视频领域。
AI 中文摘要
高效且具有感知意义的质量评估是图像和视频处理、压缩及流传输系统的基本需求。本文表明，在基于离散余弦变换（DCT）的压缩图像场景中，结构相似性指数（SSIM）可通过仅从参考图像导出的局部统计量，从全局峰值信噪比（PSNR）或均方误差（MSE）近似得到。现有研究假设可获取局部MSE，而我们提出两种方法，通过使用基于方差或标准差的权重重新分配全局MSE来近似局部MSE。在Kodak和Xiph Subset1数据集上针对一系列JPEG质量等级开展的实验表明，两种方法均能提供准确且鲁棒的SSIM近似，显著优于全局MSE基线。所提出的框架被设计为可自然扩展至视频领域，其中从参考图像导出的统计量可在同一内容的多次编码间摊销使用。
英文摘要
Efficient and perceptually meaningful quality assessment is a fundamental requirement for image and video processing, compression, and streaming systems. This article shows that, in the context of Discrete Cosine Transform ( DCT)-based compressed images, Structural Similarity Index ( SSIM ) can be approximated from global Peak Signal to Noise Ratio (PSNR) or Mean Square Error ( MSE) using local statistics derived only from the reference image. While prior work assumes access to local MSE, we propose two approaches to approximate local MSE by redistributing the global MSE using variance or standard-deviation-based weighting. Experiments on the Kodak and Xiph Subset1 datasets across a range of JPEG quality levels demonstrate that both approaches provide accurate and robust SSIM approximations, substantially outperforming the global MSE baseline. The proposed framework is designed to extend naturally to video, where reference-derived statistics can be amortized across multiple encodes of the same content.
Journal ref2026 18th International Conference on Quality of Multimedia Experience (QoMEX)
DOI：10.1109/QoMEX69967.2026.11618343
