Generative Models for Inverse Imaging Problems: From mathematical foundations to physics-driven applications

Research output: Contribution to journalArticlepeer-review

Abstract

Physics-informed generative modeling for inverse problems in computational imaging is a fast-growing field encompassing a variety of methods and applications. Here, we review a few generative modeling techniques, such as variational autoencoders (VAEs) and generative adversarial networks (GANs), as well as more recent developments in score-based generative models. Through different imaging applications, we review how the generative modeling techniques are effectively combined with the physics of the imaging problem, e.g., the measurement forward model and physical properties of the target objects, to solve the inverse problems.

Original languageEnglish (US)
Pages (from-to)148-163
Number of pages16
JournalIEEE Signal Processing Magazine
Volume40
Issue number1
DOIs
StatePublished - Jan 1 2023

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Generative Models for Inverse Imaging Problems: From mathematical foundations to physics-driven applications'. Together they form a unique fingerprint.

Cite this