Abstract
Iterative phase retrieval algorithms are time-consuming. To accelerate reconstructions for Randomized Probe Imaging (RPI), we propose deep k-learning, a neural network with attention to frequency. The associated computational speedup may enable fast dynamical imaging.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Xin Yuan
IW4A.1 Imaging Systems and Applications (IS) 2021
Ruibo Shang, Kevin Hoffer-Hawlik, Fei Wang, Guohai Situ, and Geoffrey P. Luke
CM6B.5 Computational Optical Sensing and Imaging (COSI) 2021
Silvio Montresor, Marie Tahon, and Pascal Picart
DTh1D.1 Digital Holography and Three-Dimensional Imaging (DH) 2021