What's in a Prior? Learned Proximal Networks for Inverse Problems

arXiv:2310.14344v2 Announce Type: replace-cross
Abstract: Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep learning models have been brought to bear for these tasks too, as in the framework of plug-and-play or deep unrolling, where they loosely resemble proximal operators. Yet, something essential is lost in employing these purely data-driven approaches: there is no guarantee that a general deep network represents the proximal operator of any …

abstract arxiv cs.cv cs.lg deep learning framework modern networks operators part prior strategies tasks type