BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Imaging Seminar: Diffusion Models for Computational Imaging Proble
 ms
DTSTART:20250130T170000
DTEND:20250130T180000
DTSTAMP:20261025T224146Z
UID:34193fc337f224a9308d64ae8c910e1adbf4abb77219d3e2a9e95409
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Jong Chul Yue\, KAIST\, Korea\nAbstract:\nThe recent eme
 rgence of diffusion models has driven significant advancements in solving 
 inverse problems by leveraging these models as powerful generative priors.
  However\, challenges persist due to the ill-posed nature of such problems
 \, including extending solutions to 3D and temporal domains and addressing
  inherent ambiguities in measurements. In this talk\, we present strategie
 s developed by our lab at KAIST to tackle these challenges. First\, we exp
 lore the manifold geometry of diffusion models\, which has become a founda
 tional concept for designing constrained diffusion models. Building on thi
 s\, we introduce the Diffusion Posterior Sampling (DPS) algorithm\, which 
 enables manifold-constrained measurement guidance during the reverse sampl
 ing process. Additionally\, we present its accelerated implementation\, th
 e Decomposed Diffusion Sampling (DDS) method\, tailored for high-dimension
 al imaging problems in biomedical applications. Finally\, we discuss sever
 al extensions\, including text-driven reconstruction\, CFG++\, and applica
 tions to video and 3D domains.\n\nBio:\nJong Chul Ye is a Professor and th
 e Chung Moon Soul Mirae Chair at the Kim Jaechul Graduate School of Artifi
 cial Intelligence (AI) at the Korea Advanced Institute of Science and Tech
 nology (KAIST)\, Korea. He received his B.Sc. and M.Sc. degrees from Seoul
  National University\, Korea\, and his Ph.D. from Purdue University\, USA.
  Prior to joining KAIST\, he worked at Philips Research and GE Global Rese
 arch in New York. Professor Ye has held several editorial roles\, includin
 g Associate Editor for IEEE Transactions on Image Processing\, IEEE Comput
 ational Imaging\, and IEEE Transactions on Medical Imaging\, as well as Se
 nior Editor for IEEE Signal Processing and editorial board member for Magn
 etic Resonance in Medicine. He is an IEEE Fellow and has served as Chair o
 f the IEEE SPS Computational Imaging Technical Committee and as an IEEE EM
 BS Distinguished Lecturer. He is also a Fellow of the Korean Academy of Sc
 ience and Technology and currently serves as the President of the Korean S
 ociety for Artificial Intelligence in Medicine (2023–2024). Among his nu
 merous accolades are two prestigious awards for mathematicians in Korea: t
 he Choi Suk-Jung Award and the Kum-Kok Award\, as well as the Career Achie
 vement Award from the Korean Society for Magnetic Resonance in Medicine. P
 rofessor Ye’s research interests focus on machine learning for biomedica
 l imaging and computer vision.\n\nThe seminar is followed by an aperitif.
  \n\nRegistration appreciated\nMore info here
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR