Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.09365 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909781837479936 |
|---|---|
| author | Wang, Xiaodong Wang, Ping Li, Zhangyuan Yuan, Xin |
| author_facet | Wang, Xiaodong Wang, Ping Li, Zhangyuan Yuan, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09365 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection Wang, Xiaodong Wang, Ping Li, Zhangyuan Yuan, Xin Computer Vision and Pattern Recognition 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. |
| title | Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.09365 |