Multi-prior physics-enhanced neural network enables pixel super-resolution and twin-image-free phase retrieval from single-shot hologram
多先验物理增强神经网络实现了单次拍摄全息图的像素超分辨率和双图像无相位检索
多重アプリオリ物理増強ニューラルネットワークは、単一撮影ホログラムの画素超解像度と2画像の位相なし検索を実現した
다중 선험 물리 증강 신경망은 홀로그램을 한 번에 촬영하는 화소 초해상도와 이중 이미지 무위상 검색을 실현한다
La red neuronal de mejora física multiprevia realiza la súper resolución de píxeles de un holograma de disparo único y la recuperación sin fase de imágenes dobles.
Multi - transcendantal Physical Enhanced Neural Networks permet une super - résolution des pixels et une récupération sans phase des images doubles pour un hologramme à prise unique
Многоаприорное физическое усовершенствование нейронной сети обеспечивает пиксельное сверхразрешение одной голограммы и двухфазный поиск изображений
Xuan Tian ¹ ², Runze Li ¹, Tong Peng ¹, Yuge Xue ¹ ², Junwei Min ¹, Xing Li ¹, Chen Bai ¹ ², Baoli Yao ¹ ²
¹ State Key Laboratory of Transient Optics and Photonics, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, China
中国 西安 中国科学院西安光学精密机械研究所 瞬态光学与光子技术国家重点实验室
² University of Chinese Academy of Sciences, Beijing 100049, China
中国 北京 中国科学院大学
Digital in-line holographic microscopy (DIHM) is a widely used interference technique for real-time reconstruction of living cells’ morphological information with large space-bandwidth product and compact setup. However, the need for a larger pixel size of detector to improve imaging photosensitivity, field-of-view, and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.
Additionally, the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image. The deep learning (DL) approach has emerged as a powerful tool for phase retrieval in DIHM, effectively addressing these challenges. However, most DL-based strategies are data-driven or end-to-end net approaches, suffering from excessive data dependency and limited generalization ability. Herein, a novel multi-prior physics-enhanced neural network with pixel super-resolution (MPPN-PSR) for phase retrieval of DIHM is proposed. It encapsulates the physical model prior, sparsity prior and deep image prior in an untrained deep neural network.
The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods. With the capabilities of pixel super-resolution, twin-image elimination and high-throughput jointly from a single-shot intensity measurement, the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.