Abstract

Fluorescence microscopy typically suffers from aberration induced by system and sample, which could be circumvented by image deconvolution. We proposed a novel, to the best of our knowledge, Richardson–Lucy (RL) model-driven deconvolution framework to improve reconstruction performance and speed. Two kinds of neural networks within this framework were devised, which are partially interpretable compared with previous deep learning methods. We first introduce RL into deep feature space, which has superior generalizability to the convolutional neural networks (CNN). We further accelerate it with an unmatched backprojector, providing a five times faster reconstruction speed than classic RL. Our deconvolution approaches outperform both CNN and traditional methods regarding image quality for blurred images caused by out-of-focus or imaging system aberration.

© 2023 Optica Publishing Group

Richardson–Lucy deconvolution of time histograms for high-resolution non-line-of-sight imaging based on a back-projection method

Chenfei Jin, Jiaheng Xie, Siqi Zhang, ZiJing Zhang, and Yuan Zhao
Opt. Lett. 43(23) 5885-5888 (2018)

End-to-end learned single lens design using improved Wiener deconvolution

Rongshuai Zhang, Fanjiao Tan, Qingyu Hou, Zongling Li, Zaiwu Sun, Changjian Yang, and Xiangyang Gao
Opt. Lett. 48(3) 522-525 (2023)

Sparse deconvolution for background noise suppression with total variation regularization in light field microscopy

Chuhui Wang, Jiachen Wan, Jiaju Chen, Ijaz Gul, Chenyao Jiang, Xiaoyun Zhong, Zhenglin Chen, Zhengyang Lei, Shuyue Ma, Tsz Kwan Lam, Dongmei Yu, and Peiwu Qin
Opt. Lett. 48(7) 1894-1897 (2023)

Blind deconvolution by means of the Richardson–Lucy algorithm

D. A. Fish, A. M. Brinicombe, E. R. Pike, and J. G. Walker
J. Opt. Soc. Am. A 12(1) 58-65 (1995)

Statistical-information-based performance criteria for Richardson–Lucy image deblurring

Sudhakar Prasad
J. Opt. Soc. Am. A 19(7) 1286-1296 (2002)