用物理引导的扩散模型，仅需20%重叠就能高保真重建相衬图像
Ptychographic Image Reconstruction from Limited Data via Score-Based Diffusion Models with Physics-Guidance
- 用扩散模型学习物体先验，结合物理约束优化反向生成过程
- 20%重叠即可达到与62%重叠相当的重建精度
- 适用于低数据量、快速成像场景，适合微纳结构成像研究者
波前扫描技术是一种依赖大量数据的计算成像方法，可在大视场下实现高空间分辨率。该技术通过相干光束扫描重叠区域并记录衍射图样，传统算法需大量重叠以保证重建质量，导致实验数据量达皮字节级别，采集时间长达数周至数月。为此，我们提出一种基于物理引导的分数驱动扩散模型重建方法。训练阶段在代表性物体图像上学习对象分布先验；重建时，通过修改逆向扩散过程以满足数据一致性，引导生成符合物理规律的解。该方法仅需一次预训练，可泛化至不同扫描重叠率和位置。结果表明，本方法在仅20%重叠条件下即可实现高保真重建，而广泛使用的rPIE方法需62%重叠才能达到相近精度，显著降低数据需求，为传统方法提供替代方案。
原文摘要 · Abstract (English)
Ptychography is a data-intensive computational imaging technique that achieves high spatial resolution over large fields of view. The technique involves scanning a coherent beam across overlapping regions and recording diffraction patterns. Conventional reconstruction algorithms require substantial overlap, increasing data volume and experimental time, reaching PiB-scale experimental data and weeks to month-long data acquisition times. To address this, we propose a reconstruction method employing a physics-guided score-based diffusion model. Our approach trains a diffusion model on representative object images to learn an object distribution prior. During reconstruction, we modify the reverse diffusion process to enforce data consistency, guiding reverse diffusion toward a physically plausible solution. This method requires a single pretraining phase, allowing it to generalize across varying scan overlap ratios and positions. Our results demonstrate that the proposed method achieves high-fidelity reconstructions with only a 20% overlap, while the widely employed rPIE method requires a 62% overlap to achieve similar accuracy. This represents a significant reduction in data requirements, offering an alternative to conventional techniques.
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。