用得分模型提升压缩图像恢复精度与速度
Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery
- 将得分模型的最优去噪器融入消息传递框架
- 在FFHQ数据集上仅需20次内神经函数评估即收敛
- 适合需要高精度、低计算开销的图像重建场景
消息传递算法通过接入现成的图像去噪器被用于压缩成像。这些现成去噪器大多依赖通用或手工设计的先验，难以准确捕捉真实图像分布，在高度欠定情况下表现不佳。相反，基于得分的生成建模能更精确地刻画复杂图像分布。本文利用得分建模与经验贝叶斯最优去噪之间的紧密关系，提出一种集成得分模型最小均方误差（MMSE）去噪器的消息传递框架，用于压缩图像恢复。在FFHQ数据集上的实验表明，该方法显著优于传统消息传递、正则化线性回归及基于得分的后验采样基线，尤其在性能-复杂度权衡上表现突出。值得注意的是，该方法通常在少于20次神经函数评估（NFEs）内即可收敛。
原文摘要 · Abstract (English)
Message passing algorithms have been tailored for compressive imaging applications by plugging in different types of off-the-shelf image denoisers. These off-the-shelf denoisers mostly rely on some generic or hand-crafted priors for denoising. Due to their insufficient accuracy in capturing the true image prior, these methods often fail to produce satisfactory results, especially in highly underdetermined scenarios. On the other hand, score-based generative modeling offers a promising way to accurately characterize the sophisticated image distribution. In this paper, by exploiting the close relation between score-based modeling and empirical Bayes-optimal denoising, we devise a message passing framework that integrates a score-based minimum mean squared error (MMSE) denoiser for compressive image recovery. Experiments on the FFHQ dataset demonstrate that our method strikes a significantly better performance-complexity tradeoff than conventional message passing, regularized linear regression, and score-based posterior sampling baselines. Remarkably, our method typically converges in fewer than 20 neural function evaluations (NFEs).
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。