Abstract
Paper titled “Come-Closer-Diffuse-Faster Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction” is accepted to CVPR 2022. We study the stochastically contracting property of reverse diffusion, and leverage this property to significantly accelerate diffusion model based linear inverse problem solvers.
Date
Mar 15, 2022 12:00 AM
Hyungjin Chung
Ph.D. student - Generative Models & Inverse Problems
My research interests include, but is not restricted to developing efficient, modular deep generative models (diffusion models), and solving real-world inverse problems (MRI, tomography, microscopy, phase retrieval, etc.) with deep generative priors.