Dual-domain mean-reverting diffusion model-enhanced temporal compressive coherent diffraction imaging

• DOI: 10.1364/oe.517567
• Publication Date: 2024-03-26T10:00:12Z
• Authors: Hao Li; Jinwei Xu; Xinyi Wu; Cong Wan; Weisheng Xu; Jianghao Xiong; Wenbo Wan; Qiegen Liu
• Keywords: Spatial frequency; Coherent diffraction imaging

Temporal compressive coherent diffraction imaging is a lensless technique with the capability to capture fast-moving small objects. However, accuracy of reconstruction often hindered by loss frequency domain information, critical factor limiting quality reconstructed images. To improve these images, method dual-domain mean-reverting diffusion model-enhanced temporal (DMDTC) has been introduced. DMDTC leverages model acquire prior information in both and spatial through sample learning. The employed recover missing while hybrid input-output algorithm carried out reconstruct image. utilized for denoising image restoration. demonstrated significant enhancement results indicate that structural similarity peak signal-to-noise ratio images surpass those obtained conventional methods. enables high frame rates resolution imaging.