用扩散模型提升单像素成像重建质量，关键在融合物理模型与数据一致性。
Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection
- 将扩散过程拆解为去噪、数据一致性和采样三阶段，统一建模
- 设计混合数据一致性模块，提升测量值匹配度，图像更清晰
- 适合做图像压缩感知重建的研究者或工程师参考
我们研究了插件式（PnP）方法与去噪扩散隐式模型（DDIM）在解决病态逆问题中的联系，聚焦于单像素成像。通过识别PnP与扩散模型在去噪机制和采样流程上的关键差异，我们将扩散过程解耦为三个可解释阶段：去噪、数据一致性约束和采样，构建了一个将学习先验与物理前向模型有机结合的统一框架。基于此，提出一种混合数据一致性模块，线性组合多个PnP风格保真项，直接作用于去噪估计结果，提升测量一致性，同时不破坏扩散采样轨迹。在单像素成像任务上的实验表明，该方法实现了更优的重建质量。
原文摘要 · Abstract (English)
We explore the connection between Plug-and-Play (PnP) methods and Denoising Diffusion Implicit Models (DDIM) for solving ill-posed inverse problems, with a focus on single-pixel imaging. We begin by identifying key distinctions between PnP and diffusion models-particularly in their denoising mechanisms and sampling procedures. By decoupling the diffusion process into three interpretable stages: denoising, data consistency enforcement, and sampling, we provide a unified framework that integrates learned priors with physical forward models in a principled manner. Building upon this insight, we propose a hybrid data-consistency module that linearly combines multiple PnP-style fidelity terms. This hybrid correction is applied directly to the denoised estimate, improving measurement consistency without disrupting the diffusion sampling trajectory. Experimental results on single-pixel imaging tasks demonstrate that our method achieves better reconstruction quality.
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。