Lensless computational imaging through deep learning

2017/02/22 by Ayan Sinha, Sinha, Ayan, Justin Lee +5 · 10 citations
Computer Science · Physics and Astronomy · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Optics (physics.optics) #cs.CV #physics.optics

paper · pdf · doi:10.48550/arxiv.1702.08516

8 pages, 13 figures

arxiv created 2017/06/26 · arxiv updated 2017/06/27

Abstract

Deep learning has been proven to yield reliably generalizable answers to numerous classification and decision tasks. Here, we demonstrate for the first time, to our knowledge, that deep neural networks (DNNs) can be trained to solve inverse problems in computational imaging. We experimentally demonstrate a lens-less imaging system where a DNN was trained to recover a phase object given a raw intensity image recorded some distance away.

Cited by

• Deep Learning-Driven Quantitative Spectroscopic Photoacoustic Imaging for Segmentation and Oxygen Saturation Estimation
• Poisson wavefront imaging in photon-starved scenarios
• Constraint-Free Coherent Diffraction Imaging via Physics-Guided Neural Fields
• Lithium Niobate Vertical Cavity Electro-Optic Modulator
• Focal-plane wavefront sensing with moderately broadband light using a short multi-mode fiber
• Towards generalizable deep ptychography neural networks
• Resolving Complex Subwavelength Grating Structures Using Topologically Structured Light
• Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizers
• Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram
• Multi-layer 5D Optical Data Storage: Mathematical Modeling and Deep Learning-Based Reconstruction of Birefringent Parameters

Related

• Deep Learning Techniques for Inverse Problems in Imaging
• Towards Lensless Image Deblurring with Prior-Embedded Implicit Neural Representations in the Low-Data Regime
• Deep Decomposition Learning for Inverse Imaging Problems
• Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems
• One Network to Solve Them All --- Solving Linear Inverse Problems using\n Deep Projection Models