2020/02/28 by Fahad Shamshad, Ali Ahmed, Shamshad, Fahad +1 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · Physics and Astronomy · #Advanced Electron Microscopy Techniques and Applications #Advanced Image Processing Techniques #Advanced X-ray Imaging Techniques #Algorithm #Artificial intelligence #Artificial neural network #Blind deconvolution #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolution (computer science) #Deblurring #Deconvolution #Digital Holography and Microscopy #FOS: Computer and information sciences #FOS: Electrical engineering #Fourier transform #Gradient descent #Image (mathematics) #Image and Video Processing (eess.IV) #Image processing #Image restoration #Inverse problem #Kernel (algebra) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mathematics #Motion blur #Noise (video) #Phase retrieval #Prior probability #Range (aeronautics) #Signal Processing (eess.SP) #cs.CV #cs.LG #eess.IV #eess.SP #electronic engineering #information engineering #stat.ML
paper · pdf · doi:10.48550/arxiv.2002.12578
published in arXiv (Cornell University) (Cornell University) · 10 pages
arxiv created 2020/02/28 · openalex publication_date 2020/02/28 · arxiv updated 2020/03/02 · openalex created_date 2022/09/14 · openalex updated_date 2026/07/28
In this paper, we consider the highly ill-posed problem of jointly recovering two real-valued signals from the phaseless measurements of their circular convolution. The problem arises in various imaging modalities such as Fourier ptychography, X-ray crystallography, and in visible light communication. We propose to solve this inverse problem using alternating gradient descent algorithm under two pretrained deep generative networks as priors; one is trained on sharp images and the other on blur kernels. The proposed recovery algorithm strives to find a sharp image and a blur kernel in the range of the respective pre-generators that best explain the forward measurement model. In doing so, we are able to reconstruct quality image estimates. Moreover, the numerics show that the proposed approach performs well on the challenging measurement models that reflect the physically realizable imaging systems and is also robust to noise