End-to-end deep learning for super-oscillatory subtraction imaging
Abstract
Breaking the diffraction limit in optical imaging is crucial for resolving subwavelength details in a wide range of applications, where super-oscillatory imaging and subtraction imaging are two common strategies for surpassing conventional resolution limits. We propose an end-to-end deep learning framework that integrates super-oscillatory focusing and subtraction imaging into a single jointly optimized vectorial Debye integral neural network pipeline, eliminating the traditional two-step acquisition and manual weighting process. With this end-to-end neural network, we further improve the focusing capability of the system to the sub-100-nm regime, enabling deep-subwavelength imaging resolution.
Article Details
Journal Info
Applied Physics Letters
American Institute of Physics
Authors (10)
Zhongwei Jin
College of Optical and Electronic Technology, China Jiliang University 1 , Hangzhou 310018,
Keyi Chen
State Key Laboratory of High-Performance Ceramics and Superfine Microstructure, Shanghai Institute of Ceramics, Chinese Academy of Sciences, 585 He Shuo Road, Shanghai 201899, China
Qiuyu Ren
Zhigang Dai
College of Optical and Electronic Technology, China Jiliang University 1 , Hangzhou 310018,
Ruoping Yao
College of Optical and Electronic Technology, China Jiliang University 1 , Hangzhou 310018,
Zhi Hong
Centre for THz Research, China Jiliang University 2 , Hangzhou 310018,
Bin Fang
Proteomics and Metabolomics Core, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA.
Fangzhou Shu
Centre for THz Research, China Jiliang University 2 , Hangzhou 310018,
Shengtao Mei
College of Optical and Electronic Technology, China Jiliang University 1 , Hangzhou 310018,
Yiping Lu