# 用随机 Hessian 估计实现全参考图像质量指标的率失真优化

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-24 08:00
- AIHOT 分数：36
- AIHOT 链接：https://aihot.news/items/cmugc3elz0n0urogvh37ecpyu
- 原文链接：https://arxiv.org/abs/2609.30077

## AI 摘要

研究者提出 IDQD-RDO，用输入相关的二次失真近似 MS-SSIM、LPIPS 等全参考图像质量指标，通过自动微分得到的 Hessian 矩阵-向量积估计其块对角或纯对角形式，使这类指标可逐块计算并用于 VVC 编码的率失真优化。在 Kodak 和 CLIC 上的五种指标测试中，该方法取得 14.2-36.7% 的 BD-rate 节省，无需改动解码器，编码复杂度仅增加 10-30%。

## 正文

Block-based video codecs select coding parameters based on the input by optimizing a rate-distortion trade-off. The conventional distortion choice, the sum of squared errors (SSE), simplifies parameter selection: the SSE is the sum of block-wise SSEs, so rate-distortion optimization (RDO) can treat blocks independently. Alternatively, full-reference image quality assessment (FR-IQA) metrics such as MS-SSIM or LPIPS often align better with the human visual system than SSE, but they cannot be used in-loop: they do not decompose block-wise and typically require the fully decoded image as input.

Building on existing results in metric quadratization, we approximate a broad class of FR-IQA metrics by an input-dependent quadratic distortion (IDQD), whose quadratic form matrix is derived from the Hessian of the metric evaluated at the source video. To make the distortion computable block-wise, we propose two approximations of the Hessian matrix: 1) keeping the block-diagonal, and 2) keeping only its diagonal. We propose estimators for both that require only matrix-vector products with the Hessian obtained by automatic differentiation. Across five metrics for Kodak and CLIC in VVC, IDQD-RDO achieves 14.2-36.7 % BD-rate savings under the target metric with no decoder changes and incurs 10-30 % encoding complexity overhead.