Lensless computational imaging through deep learning

作者：Ayan Sinha, Justin Lee, Shuai Li, George Barbastathis · 发表于：Optica · 年份：2017 · DOI：10.1364/optica.4.001117 · 被引用次数：719 · 研究领域：Digital Holography and Microscopy、Random lasers and scattering media、Image Processing Techniques and Applications

Deep learning has been proven to yield reliably generalizable solutions 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 end-to-end inverse problems in computational imaging. We experimentally built and tested a lensless imaging system where a DNN was trained to recover phase objects given their propagated intensity diffraction patterns.