TY - JOUR
T1 - Generative Models for Inverse Imaging Problems
T2 - From mathematical foundations to physics-driven applications
AU - Zhao, Zhizhen
AU - Ye, Jong Chul
AU - Bresler, Yoram
N1 - This work was partially supported by NSF Award OAC- 1934757, U.S. Army MURI Award W911NF-15-1-0479, and the Alfred P. Sloan Foundation
PY - 2023/1/1
Y1 - 2023/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85147189656&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147189656&partnerID=8YFLogxK
U2 - 10.1109/MSP.2022.3215282
DO - 10.1109/MSP.2022.3215282
M3 - Article
AN - SCOPUS:85147189656
SN - 1053-5888
VL - 40
SP - 148
EP - 163
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
IS - 1
ER -