Optimal Physical Preprocessing for Example-Based Super-Resolution

Abstract

In example-based super-resolution, the function relating low-resolution images to their high-resolution counterparts is learned from a given dataset. This data-driven approach to solving the inverse problem of increasing image resolution has been implemented with deep learning algorithms. In this work, we explore modifying the imaging hardware in order to collect more informative low-resolution images for better ultimate high-resolution image reconstruction. We show that this "physical preprocessing" allows for improved image reconstruction with deep learning in Fourier ptychographic microscopy. Fourier ptychographic microscopy is a technique allowing for both high resolution and high field-of-view at the cost of temporal resolution. In Fourier ptychographic microscopy, variable illumination patterns are used to collect multiple low-resolution images. These low-resolution images are then computationally combined to create an image with resolution exceeding that of any single image from the microscope. We use deep learning to jointly optimize the illumination pattern with the post-processing reconstruction algorithm for a given sample type, allowing for single-shot imaging with both high resolution and high field-of-view. We demonstrate, with simulated data, that the joint optimization yields improved image reconstruction as compared with sole optimization of the post-processing reconstruction algorithm.

References in corpus (29)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Generative Adversarial Networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• Wide-field, high-resolution Fourier ptychographic microscopy
• Learning-Based View Synthesis for Light Field Cameras
• Deep Learning Microscopy
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Deep multi-scale video prediction beyond mean square error
• Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Experimental robustness of Fourier Ptychography phase retrieval algorithms
• Computational illumination for high-speed in vitro Fourier ptychographic microscopy
• Low Photon Count Phase Retrieval Using Deep Learning
• Deep learning enhanced mobile-phone microscopy
• Computational ghost imaging using deep learning
• Efficient and accurate inversion of multiple scattering with deep learning
• Super-Resolution via Deep Learning
• Compressed Learning: A Deep Neural Network Approach
• Deeply-Recursive Convolutional Network for Image Super-Resolution
• Convolutional neural networks that teach microscopes how to image
• Learning Sensor Multiplexing Design through Back-propagation
• Imaging through glass diffusers using densely connected convolutional networks
• An Introduction to Deep Learning for the Physical Layer
• Toward a Thinking Microscope: Deep Learning in Optical Microscopy and Image Reconstruction
• RAISR: Rapid and Accurate Image Super Resolution

Cited by in corpus (7)

• Reliable deep-learning-based phase imaging with uncertainty quantification
• Intelligent Meta-Imagers: From Compressed to Learned Sensing
• Illumination Pattern Design with Deep Learning for Single-Shot Fourier Ptychographic Microscopy
• HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
• Data-Driven Design for Fourier Ptychographic Microscopy
• Deep Learned Optical Multiplexing for Multi-Focal Plane Microscopy
• Physics-based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging