BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Data-driven image generation now and in the future
DTSTART:20191111T161500
DTEND:20191111T173000
DTSTAMP:20260408T120002Z
UID:2f780dbd281269c3e4a9ed264685475498f0b5e9a8450355fb4484a4
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Jaakko Lethinen - Aalto University\nVideo of his talk\n\nA
 bstract:\nData-driven generative image models\, particularly Generative Ad
 versarial Networks (GAN)\, have experienced dramatic advances in the last 
 two years. In this talk\, I will present the work that led to the Progress
 ive GAN\, the first high-quality megapixel-resolution generative image mod
 el\, illustrate the difficulties and solutions encountered along the way\,
  and attempt to shed light onto the models’ internal workings. I will co
 nclude with views on current GAN models’ greatest limitations\, as well 
 as potential ways of addressing them.\n\nBio:\nJaakko Lehtinen is a tenure
 d associate professor at Aalto University\, and a principal research scien
 tist at NVIDIA Research. He works on computer graphics\, computer vision\,
  and machine learning\, with particular interests in generative modelling\
 , realistic image synthesis\, and appearance acquisition and reproduction.
  Overall\, Jaakko is fascinated by the combination of machine learning tec
 hniques with physical simulators in the search for robust\, interpretable 
 AI.\n \nBefore taking his current positions\, Jaakko spent 2007-10 as a p
 ostdoc with Frédo Durand at MIT. Prior to his research career he worked f
 or the game developer Remedy Entertainment in 1996-2005 as a graphics prog
 rammer\, and contributed significantly to the graphics technology behind t
 he worldwide blockbuster hit games Max Payne (2001)\, Max Payne 2 (2003)\,
  and Alan Wake (2009). Since then\, his work on facial performance capture
  has been used extensively by Remedy in the production of the critically-a
 cclaimed Control (2019).\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR
