Photon-Limited Deblurring using Algorithm Unrolling

Yash Sanghvi, Abhiram Gnanasambandam, Stanley Chan

Keywords: Poisson deconvolution, photon-limited, algorithm unrolling, plug-and-play

TL;DR: A fixed iteration unrolled method for Poisson deblurring is provided using the Plug-and-Play framework and method is demonstrated on real data.

Abstract: Image deblurring in a photon-limited condition is ubiquitous in a variety of low-light applications such as photography, microscopy and astronomy. However, presence of photon shot noise due to low-illumination and/or short exposure time makes the deblurring task substantially more challenging . This paper presents an algorithm unrolling approach for the photon-limited deblurring problem that unrolls a Plug-and-Play algorithm using a fixed-iteration network. By modifying the typical two-variable splitting to a three-variable splitting, our unrolled network is differentiable and can be trained end-to-end. We demonstrate the usage of our algorithm on real photon-limited image data.