DDIP receives 30th Samsung Humantech Paper Award (1st in Signal Processing)
Abstract
Deep Diffusion Image Prior (DDIP) is a paper that combines the merits of decomposed diffusion sampler (DDS) and steerable conditional diffusion (SCD) for solving out-of-distribution inverse rpoblems.
Date
Jan 16, 2024 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.