2 Papers accepted to NeurIPS 2022 / NeurIPS 2022 SBM Workshop

Abstract

Paper titled “Improving Diffusion Models for Inverse Problems using Manifold Constraints” is accepted to NeurIPS 2022. We propose a geometric view of diffusion models, and use this view to dramatically improve the performance of diffusion models in linear inverse problem solving. Paper titled “Progressive deblurring of diffusion models for coarse-to-fine image synthesis” is accepted to NeurIPS 2022 SBM workshop.

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.