Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks

Wavefront sensing is an essential technique in optical imaging, adaptive optics, and atmospheric turbulence correction. Traditional wavefront reconstruction methods, including the Gerchberg–Saxton (GS) algorithm and phase diversity (PD) techniques, are often limited by issues such as low inversion a...

Full description

Saved in:
Bibliographic Details
Main Authors: Hangning Kou, Jingliang Gu, Jiang You, Min Wan, Zixun Ye, Zhengjiao Xiang, Xian Yue
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Optics
Subjects:
Online Access:https://www.mdpi.com/2673-3269/6/1/11
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279628020645888
author Hangning Kou
Jingliang Gu
Jiang You
Min Wan
Zixun Ye
Zhengjiao Xiang
Xian Yue
author_facet Hangning Kou
Jingliang Gu
Jiang You
Min Wan
Zixun Ye
Zhengjiao Xiang
Xian Yue
author_sort Hangning Kou
collection DOAJ
description Wavefront sensing is an essential technique in optical imaging, adaptive optics, and atmospheric turbulence correction. Traditional wavefront reconstruction methods, including the Gerchberg–Saxton (GS) algorithm and phase diversity (PD) techniques, are often limited by issues such as low inversion accuracy, slow convergence, and the presence of multiple possible solutions. Recent developments in deep learning have led to new methods, although conventional CNN-based models still face challenges in effectively capturing global context. To overcome these limitations, we propose a Transformer-based single-shot wavefront sensing method, which directly reconstructs wavefront aberrations from focal plane intensity images. Our model integrates a Normalization-based Attention Module (NAM) into the CoAtNet architecture, which strengthens feature extraction and leads to more accurate wavefront characterization. Experimental results in both simulated and real-world conditions indicate that our method achieves a 4.5% reduction in normalized wavefront error (NWE) compared to ResNet34, suggesting improved performance over conventional deep learning models. Additionally, by leveraging Walsh function modulation, our approach resolves the multiple-solution problem inherent in phase retrieval techniques. The proposed model achieves high accuracy, fast convergence, and simplicity in implementation, making it a promising solution for wavefront sensing applications.
format Article
id doaj-art-2a09dff0bd7f48209d40f214cee50161
institution OA Journals
issn 2673-3269
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Optics
spelling doaj-art-2a09dff0bd7f48209d40f214cee501612025-08-20T01:49:01ZengMDPI AGOptics2673-32692025-03-01611110.3390/opt6010011Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer NetworksHangning Kou0Jingliang Gu1Jiang You2Min Wan3Zixun Ye4Zhengjiao Xiang5Xian Yue6Graduate School of China Academy of Engineering Physics, Beijing 100088, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaInstitute of Applied Electronics, China Academy of Engineering Physics, Mianyang 621900, ChinaWavefront sensing is an essential technique in optical imaging, adaptive optics, and atmospheric turbulence correction. Traditional wavefront reconstruction methods, including the Gerchberg–Saxton (GS) algorithm and phase diversity (PD) techniques, are often limited by issues such as low inversion accuracy, slow convergence, and the presence of multiple possible solutions. Recent developments in deep learning have led to new methods, although conventional CNN-based models still face challenges in effectively capturing global context. To overcome these limitations, we propose a Transformer-based single-shot wavefront sensing method, which directly reconstructs wavefront aberrations from focal plane intensity images. Our model integrates a Normalization-based Attention Module (NAM) into the CoAtNet architecture, which strengthens feature extraction and leads to more accurate wavefront characterization. Experimental results in both simulated and real-world conditions indicate that our method achieves a 4.5% reduction in normalized wavefront error (NWE) compared to ResNet34, suggesting improved performance over conventional deep learning models. Additionally, by leveraging Walsh function modulation, our approach resolves the multiple-solution problem inherent in phase retrieval techniques. The proposed model achieves high accuracy, fast convergence, and simplicity in implementation, making it a promising solution for wavefront sensing applications.https://www.mdpi.com/2673-3269/6/1/11wavefront sensingtransformersingle-shot wavefront reconstructionWalsh function modulationfocal plane imaging
spellingShingle Hangning Kou
Jingliang Gu
Jiang You
Min Wan
Zixun Ye
Zhengjiao Xiang
Xian Yue
Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
Optics
wavefront sensing
transformer
single-shot wavefront reconstruction
Walsh function modulation
focal plane imaging
title Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
title_full Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
title_fullStr Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
title_full_unstemmed Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
title_short Single-Shot Wavefront Sensing in Focal Plane Imaging Using Transformer Networks
title_sort single shot wavefront sensing in focal plane imaging using transformer networks
topic wavefront sensing
transformer
single-shot wavefront reconstruction
Walsh function modulation
focal plane imaging
url https://www.mdpi.com/2673-3269/6/1/11
work_keys_str_mv AT hangningkou singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT jinglianggu singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT jiangyou singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT minwan singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT zixunye singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT zhengjiaoxiang singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks
AT xianyue singleshotwavefrontsensinginfocalplaneimagingusingtransformernetworks