3.9 Article

Research Progress and Prospect of Adaptive Optics Based on Deep Learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Optics

Deep learning assisted plenoptic wavefront sensor for direct wavefront detection

Hao Chen et al.

Summary: This paper proposes a deep learning model to directly restore phase maps from slope measurements of PWFS, solving the poor wavefront detection performance issue of traditional PWFS. Numerical simulations demonstrate that our method has a statistical residual wavefront RMSE of 0.0810 +/- 0.0258, which is much better than the modal algorithm (0.2511 +/- 0.0587) and zonal approach (0.3584 +/- 0.0487). The driving force of PWFS-ResUnet is investigated, with the slope response differences between sub-apertures and directions playing a likely key role in accurately restoring the phase map. The robustness of our model to turbulence strength and SNR level is also tested. This method offers a new direction in solving the nonlinear problem of traditional PWFS.

OPTICS EXPRESS (2023)

Article Optics

Real-time wavefront correction using diffractive optical networks

Xiushan Pan et al.

Summary: We present an all-optical system using deep learning to achieve real-time wavefront correction for unknown, random, and distorted wavefronts, with high-quality imaging results. The system, consisting of multiple transmissive diffractive layers, is physically placed between the imaging lens and the image plane for all-optical correction of unknown wavefronts within the training range. Simulated experiments showed significant improvements in imaging Strehl ratio and resolvable probability of binary stars. The solution of real-time wavefront correction has potential applications in astronomy, laser communication, etc.

OPTICS EXPRESS (2023)

Article Optics

Extended scene deep learning wavefront sensing

Bas de Bruijne et al.

Summary: In this study, a combination of blind deconvolution and deep learning was applied to process Shack-Hartmann images. By utilizing the intensity information from spot positions and the fine structure of the individual images generated by lenslets, the sensitivity and resolution of the sensor were improved beyond the limitations of traditional spot displacement processing. The applicability of this method to wavefront sensing using extended objects as a reference was also demonstrated.

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION (2022)

Article Multidisciplinary Sciences

Direct retrieval of Zernike-based pupil functions using integrated diffractive deep neural networks

Elena Goi et al.

Summary: This article presents a compact optical-electronic module based on multi-layered diffractive neural networks that can directly retrieve pupil phase information from an imaging sensor. Compared to current phase retrieval schemes, this module has a smaller size and higher practical value.

NATURE COMMUNICATIONS (2022)

Article Optics

Mitigating the ambiguity problem in the CNN-based wavefront correction

Chenda Lu et al.

Summary: In this work, an attention-based adaptive optics method is proposed, which integrates phase diversity with a convolutional neural network (CNN) using a non-local block. Simulation results demonstrate the effectiveness of the proposed method in mitigating the ambiguity problem of phase retrieval and its superior performance compared to traditional CNN-based wavefront correction.

OPTICS LETTERS (2022)

Article Optics

Single-shot wavefront sensing with deep neural networks for free-space optical communications

Minghao Wang et al.

Summary: In this paper, the authors demonstrate the high accuracy of retrieving wavefront by exploiting a single image of the pupil plane intensity pattern. EfficientNet outperformed ResNet-50 and Inception-V3 in regressing Zernike polynomial coefficients from intensity frames, providing a more effective method in image-based wavefront sensing.

OPTICS EXPRESS (2021)

Article Optics

Fast demodulation of single-shot interferogram via convolutional neural network

Xin Liu et al.

Summary: The study proposed a method based on deep learning to demodulate single-shot interferograms, achieving millisecond-level speed and high accuracy, with lower cost and superior performance.

OPTICS COMMUNICATIONS (2021)

Article Computer Science, Information Systems

Deep learning based wavefront sensor for complex wavefront detection in adaptive optical microscopes

Shuwen Hu et al.

Summary: This study proposes a new deep learning-based wavefront detection method, which can offer low root mean square wavefront errors and high detection accuracy in adaptive optical microscopes.

FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING (2021)

Article Optics

Random two-frame interferometry based on deep learning

Ziqiang Li et al.

OPTICS EXPRESS (2020)

Article Chemistry, Analytical

Sub-Millisecond Phase Retrieval for Phase-Diversity Wavefront Sensor

Yu Wu et al.

SENSORS (2020)

Article Optics

Neural networks for image-based wavefront sensing for astronomy

Torben Andersen et al.

OPTICS LETTERS (2019)

Article Optics

Deep learning wavefront sensing

Yohei Nishizaki et al.

OPTICS EXPRESS (2019)

Article Geochemistry & Geophysics

Road Extraction by Deep Residual U-Net

Zhengxin Zhang et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2018)

Article Optics

Machine learning for improved image-based wavefront sensing

Scott W. Paine et al.

OPTICS LETTERS (2018)

Article Multidisciplinary Sciences

All-optical machine learning using diffractive deep neural networks

Xing Lin et al.

SCIENCE (2018)

Article Multidisciplinary Sciences

Mastering the game of Go without human knowledge

David Silver et al.

NATURE (2017)

Article Computer Science, Artificial Intelligence

LSTM: A Search Space Odyssey

Klaus Greff et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2017)

Article Engineering, Electrical & Electronic

Gerchberg-Saxton algorithm based phase correction in optical wireless communication

Ming Li et al.

PHYSICAL COMMUNICATION (2017)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Article Multidisciplinary Sciences

Mastering the game of Go with deep neural networks and tree search

David Silver et al.

NATURE (2016)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Optics

Wavefront reconstruction with artificial neural networks

Hong Guo et al.

OPTICS EXPRESS (2006)

Article Optics

Simulated annealing in ocular adaptive optics

S Zommer et al.

OPTICS LETTERS (2006)

Article Optics

Wave-front sensing from subdivision of the focal plane with a lenslet array

RM Clare et al.

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION (2005)

Article Computer Science, Artificial Intelligence

Image analysis by Tchebichef moments

R Mukundan et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2001)

Article Computer Science, Artificial Intelligence

Learning to forget: Continual prediction with LSTM

FA Gers et al.

NEURAL COMPUTATION (2000)

Article Optics

Adaptive optics based on analog parallel stochastic optimization: analysis and experimental demonstration

MA Vorontsov et al.

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION (2000)