BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Computational Imaging: Integrating Physical and Learned Models
DTSTART:20221219T173000
DTEND:20221219T183000
DTSTAMP:20260407T041933Z
UID:a2689e08b963eaf5d422fcba3543272140a472780af9654e66be2b63
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Ulugbek Kamilov\, Washington University in St. Louis\n
 Abstract\nComputational imaging is a rapidly growing area that seeks to e
 nhance the capabilities of imaging instruments by viewing imaging as an i
 nverse problem. Plug-and-Play Priors (PnP) is one of the most popular fra
 meworks for solving computational imaging problems through integration of
  physical and learned models. PnP leverages high-fidelity physical sensor
  models and powerful machine learning methods to provide state-of-the-art
  imaging algorithms. PnP models alternate between minimizing a data-fide
 lity term to promote data consistency and imposing a learned image prior 
 in the form of an “image denoising” deep neural network. This talk p
 resents a principled discussion of PnP and recent results on PnP under in
 exact physical and learned models. Inexact models arise naturally in comp
 utational imaging when using approximate physical models for efficiency 
 or when test images are from a different distribution than images used fo
 r training. We present several successful applications of our theoretical
  and algorithmic insights in bio-microscopy\, computerized tomography\, a
 nd magnetic resonance imaging.\n\nBiography\nUlugbek S. Kamilov is the Di
 rector of Computational Imaging Group and an Assistant Professor of Elect
 rical & Systems Engineering and Computer Science & Engineering at Washin
 gton University in St. Louis. He obtained the BSc/MSc degree in Communica
 tion Systems and the PhD degree in Electrical Engineering from EPFL\, Sw
 itzerland\, in 2011 and 2015\, respectively. From 2015 to 2017\, he was a
  Research Scientist at Mitsubishi Electric Research Laboratories\, Cambri
 dge\, MA\, USA. He is a recipient of the NSF CAREER Award and the IEEE S
 ignal Processing Society’s 2017 Best Paper Award. He was among 55 early
 -career researchers in the USA selected as a Fellow for the Scialog init
 iative on “Advancing Bioimaging” in 2021. His PhD thesis was selected
  as a finalist for the EPFL Doctorate Award in 2016. He has served as a 
 Senior Member of the Editorial Board of IEEE Signal Processing Magazine a
 nd as an Associate Editor of IEEE Transactions on Computational Imaging.
  He has served on IEEE Signal Processing Society’s Computational Imagin
 g Technical Committee and Bioimaging and Signal Processing Technical Com
 mittee. He was a plenary speaker at iTWIST 2018 and is a program co-chair
  for the International Biomedical and Astronomical Signal Processing Fro
 ntiers conference for 2023.\n\nRegister here!\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR