BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Agnès Desolneux (Paris Saclay) Mathematical Models for Texture Im
 age Synthesis
DTSTART:20260323T100000Z
DTEND:20260323T110000Z
DTSTAMP:20261018T000500Z
UID:indico-event-14564@indico.math.cnrs.fr
DESCRIPTION:In this talk\, I will present several mathematical models for 
 the problem of texture image synthesis. This problem consists in generatin
 g new images from a single exemplar image. Two main classes of models will
  be considered. The first one is the “copy-and-paste” type\, and can b
 e formalized using Markov chains. The second one is of a statistical natur
 e: it consists in computing a set of statistics on the exemplar image and 
 then generating new images that have these statistics. I will focus in par
 ticular on this latter approach\, emphasizing models based on constrained 
 maximum entropy distributions.\n\nhttps://indico.math.cnrs.fr/event/14564/
URL:https://indico.math.cnrs.fr/event/14564/
END:VEVENT
END:VCALENDAR