用参考图像统计信息，从MSE估算压缩图像的SSIM。
Estimating SSIM from MSE for DCT-Based Compressed Images via Modeling Local Error Statistics
- 基于参考图局部误差统计重构局部MSE
- 在Kodak和Xiph数据集上逼近效果优于全局MSE
- 适合视频质量评估，可复用参考统计
高效且符合人眼感知的图像质量评估是图像、视频处理、压缩与流媒体系统的基本需求。本文表明，在基于离散余弦变换（DCT）的压缩图像中，可通过仅依赖参考图像的局部统计信息，从全局峰值信噪比（PSNR）或均方误差（MSE）近似结构相似性指数（SSIM）。以往工作假设可获取局部MSE，本文提出两种方法：通过方差或标准差加权，将全局MSE重新分配以近似局部MSE。在Kodak和Xiph Subset1数据集上，不同JPEG质量级别下的实验表明，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。该框架可自然扩展至视频场景，其中参考图像导出的统计量可在同一内容的多次编码中复用。
原文摘要 · Abstract (English)
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.
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。