BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CIS - "Get to know your neighbors" Seminar series - Prof. Pascal F
 ua
DTSTART:20220117T151500
DTEND:20220117T161500
DTSTAMP:20260916T044051Z
UID:1de5c4eee5c3184ba3f6a27060ad8fdcd4e8518497ec05e5c89b54ae
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Pascal Fua\nTitle: Deep Surface Meshes\nGeometric Deep L
 earning has recently made striking progress with the advent of Deep Implic
 it Fields (SDFs). They allow for detailed modeling of watertight surfaces 
 of arbitrary topology while not relying on a 3D Euclidean grid\, resulting
  in a learnable 3D surface parameterization that is not limited in resolut
 ion. Unfortunately\, they have not yet reached their full potential for ap
 plications that require an explicit surface representation in terms of ver
 tices and facets because converting the SDF to such a 3D mesh representati
 on requires a marching-cube algorithm\, whose output cannot be easily diff
 erentiated with respect to the SDF parameters.\nIn this talk\, I will our 
 approach to overcoming this limitation and implementing convolutional neur
 al nets that output complex 3D surface meshes while remaining fully-differ
 entiable and end-to-end trainable. I will also present applications to sin
 gle view reconstruction\, physically-driven Shape optimization\, and bio-m
 edical image segmentation.\n\nBio:\nPascal Fua received an engineering deg
 ree from Ecole Polytechnique\, Paris\, in 1984 and a Ph.D. in Computer Sci
 ence from the University of Orsay in 1989. He joined EPFL (Swiss Federal I
 nstitute of Technology) in 1996 where he is a Professor in the School of C
 omputer and Communication Science and head of the Computer Vision Lab. Bef
 ore that\, he worked at SRI International and at INRIA Sophia-Antipolis as
  a Computer Scientist. His research interests include shape modeling and m
 otion recovery from images\, analysis of microscopy images\, and Augmented
  Reality. He has (co)authored over 300 publications in refereed journals a
 nd conferences. He has received several ERC grants. He is an IEEE Fellow a
 nd has been an Associate Editor of IEEE journal Transactions for Pattern A
 nalysis and Machine Intelligence. He often serves as program committee mem
 ber\, area chair\, and program chair of major vision conferences and has c
 ofounded three spinoff companies.\n\nThe Center for Intelligent Systems at
  EPFL (CIS) is a collaboration among IC\, ENAC\, SB\; SV and STI that brin
 gs together researchers working on different aspects of Intelligent System
 s.\nIn order to promote exchanges among researchers and encourage the crea
 tion of new\, collaborative projects\, CIS is organizing a "Get to know yo
 ur neighbors" series. Each seminar will consist of one short overview pres
 entation geared to the general public at EPFL.   \n\nThe CIS seminar wi
 ll take place live on Zoom: https://epfl.zoom.us/j/61326856335\n\nPlease c
 onnect to your zoom account using your "@epfl.ch" address\, as this live e
 vent is only open to the EPFL community\nMonday\, January 17th\, 2022 from
  3:15 to 4:15 pm\nNB: Video recordings of the seminars will be made availa
 ble on our website and published on our social media pages
LOCATION:Hybride TBD https://epfl.zoom.us/j/61326856335
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR