1 Paper accepted to CVPR 2022

Accelerating diffusion models with CCDF


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.

Mar 15, 2022 12:00 AM
Hyungjin Chung
Hyungjin Chung
Ph.D. student - Deep Learning & Inverse Problems

My research interests include, but is not restricted to solving inverse problems (MRI, tomography, microscopy, phase retrieval, etc.) via generative models.