Paper accepted to NeurIPS 2023

Abstract

Paper titled “Direct Diffusion Bridges using Data Consistency for Inverse Problems” is accepted to NeurIPS 2023. We unify the seemingly different frameworks into one, under the name direct diffusion bridges. We further move on to propose data consistent direct diffusion bridge, which can push the pareto-frontier forward by imposing data consistency.

Hyungjin Chung, Ph.D.

Research Scientist

Generative models, Inverse problems, Multimodality, Motion, and more.