BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20190331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20191027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260405T190416Z
UID:5d64e6902e95d161584222@ist.ac.at
DTSTART:20190902T143000
DTEND:20190902T153000
DESCRIPTION:Speaker: Anna Frühstück\nhosted by Bernd Bickel\nAbstract: Hi
 gh-quality textures are an important component in many applications rangin
 g from architectural rendering to game design and often require the work o
 f skilled artists. The synthesis of natural textures is therefore an impor
 tant problem\, but the complexity of texture synthesis increases exponenti
 ally with the target size of the output texture. Recent advances in the fi
 eld of Generative Adversarial Networks allow for novel techniques in this 
 field with unprecedented visual quality. TileGAN tackles the problem of te
 xture synthesis in the setting where many input images are given and a lar
 ge-scale output is required. We propose an algorithm to combine outputs of
  GANs to produce high-resolution texture maps with virtually no boundary a
 rtifacts. Our user interface enables artistic control and allows for an in
 teractive guided synthesis.
LOCATION:Meeting room 2nd floor / Office Bldg West (I21.01.132)\, ISTA
ORGANIZER:cpetz@ist.ac.at
SUMMARY:Anna Frühstück: Tiling Generative Adversarial Networks for Large-
 Scale Texture Synthesis
URL:https://talks-calendar.ista.ac.at/events/2079
END:VEVENT
END:VCALENDAR