activity
20202024
most citedA Survey on Diffusion Models for Inverse Problems

10 citations · 19 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CV20223 cited

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Hyungjin Chung, Jeongsol Kim, Sehui Kim +1

Diffusion model-based inverse problem solvers have demonstrated state-of-the-art performance in cases where the forward operator is known (i.e. non-blind). However, the applicabili…

eess.IV20226 cited

MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion

Hyungjin Chung, Eun Sun Lee, Jong Chul Ye

Patient scans from MRI often suffer from noise, which hampers the diagnostic capability of such images. As a method to mitigate such artifact, denoising is largely studied both wit…

eess.IV2021

Simultaneous super-resolution and motion artifact removal in diffusion-weighted MRI using unsupervised deep learning

Hyungjin Chung, Jaehyun Kim, Jeong Hee Yoon +2

Diffusion-weighted MRI is nowadays performed routinely due to its prognostic ability, yet the quality of the scans are often unsatisfactory which can subsequently hamper the clinic…

cs.CV2021

Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN

Hyungjin Chung, Jong Chul Ye

Deep generative models are known to be able to model arbitrary probability distributions. Among these, a recent deep generative model, dubbed sliceGAN, proposed a new way of using…

eess.IV2021

Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain

Hyungjin Chung, Jaeyoung Huh, Geon Kim +2

Optical diffraction tomography (ODT) produces three dimensional distribution of refractive index (RI) by measuring scattering fields at various angles. Although the distribution of…

eess.IV2020

Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN

Gyutaek Oh, Byeongsu Sim, Hyungjin Chung +2

Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced runtime compl…