Abstract

This Letter introduces the idea of unsupervised learning into object-independent wavefront sensing for the first time, to the best of our knowledge, which can achieve fast phase recovery of arbitrary objects without labels. First, a fine feature extraction method which only depends on the wavefront aberrations is proposed. Then, a lightweight neural network and an optical feature system are combined to form an unsupervised learning model, and the neural network is promoted to be well trained by reversely outputting fine features. Simulation results prove that the proposed method can effectively overcome the aberrations (static or variable) existing in the optical system and achieve wavefront sensing of different objects with high precision and efficiency.

© 2023 Optica Publishing Group

Unsupervised learning-based wavefront sensing method for Hartmanns with insufficient sub-apertures

Yu Ning, Yulong He, Jun Li, Quan Sun, Fengjie Xi, Ang Su, Yang Yi, and Xiaojun Xu
Opt. Continuum 3(2) 122-134 (2024)

Object-independent image-based wavefront sensing approach using phase diversity images and deep learning

Qi Xin, Guohao Ju, Chunyue Zhang, and Shuyan Xu
Opt. Express 27(18) 26102-26119 (2019)

Machine learning for improved image-based wavefront sensing

Scott W. Paine and James R. Fienup
Opt. Lett. 43(6) 1235-1238 (2018)

RepE: unsupervised representation learning for image enhancement in nonlinear optical microscopy

Yun-Jie Jhang, Xin Lin, Shih-Hsuan Chia, Wei-Chung Chen, I-Chen Wu, Ming-Tsang Wu, Guan-Yu Zhuo, Tsung-Ming Tai, and Hung-Wen Chen
Opt. Lett. 48(16) 4245-4248 (2023)

Experimental demonstration of wavefront reconstruction and correction techniques for variable targets based on distorted grating and deep learning

Xinlan Ge, Licheng Zhu, Zeyu Gao, Ning Wang, Ping Yang, Shuai Wang, and Hongwei Ye
Opt. Express 32(10) 17775-17792 (2024)