Welcome to my personal homepage. I am an ongoing Ph.D. student @KAIST. The motivation of my research is “Making invisible, visible”. Mostly, I work on solving inverse problems arising in computational imaging, and I focus on using deep learning, especially unsupervised learning methods to accomplish it. Unlike many works in literature that simply adopt published methods off-the-shelf, I also try to delve on theoretical links of machine learning and signal processing.
Second year Ph.D. student @KAIST bio-imaging signal processing & learning lab (BISPL). Prior research intern at the Los Alamos National Laboratory (LANL) applied math and plasma physics group (T-5). His research interests include, but is not restricted to solving inverse problems via generative modeling, and especially diffusion models. He has published papers and ongoing projects in a wide variety of fields including compressed sensing MRI (CS-MRI), tomographic reconstruction, microscopy, and phase retrieval.
Download my CV.
MS in Bio & Brain Engineering, 2021
Korea Advanced Institute of Science & Technology (KAIST)
BS in Biomedical Engineering, 2019
Interview at BRIC for the publication of “Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data” in Medical Image Analysis, 2021.
We propose a method to perform posterior sampling with diffusion models on blind inverse problems.
We propose a method that can solve 3D inverse problems in the medical imaging domain using only the pre-trained 2D diffusion model augmented with the conventional model-based prior.
Diffusion posterior sampling enables solving arbitrary noisy (e.g. Gaussian, Poisson) inverse problems that are both linear or non-linear.
Manifold constraint dramatically improves the performance of unsupervised inverse problem solving using diffusion models.
Come-close to diffuse-fast when solving inverse problems with diffusion models. We establish state-of-the-art results with only 20 diffusion steps across various tasks including SR, inpainting, and CS-MRI
Score-based diffusion models beat supervised learning methods on MRI reconstruction.