BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_522@linklings.com
SUMMARY:Efficient Neural Style Transfer for Volumetric Simulations
DESCRIPTION:Technical Papers\n\nEfficient Neural Style Transfer for Volume
 tric Simulations\n\nAurand, Ortiz, Nauer, C. Azevedo\n\nArtistically contr
 olling fluids has always been a challenging task. Recently, volumetric Neu
 ral Style Transfer (NST) techniques have been used to artistically manipul
 ate smoke simulation data with 2D images. In this work, we revisit previou
 s volumetric NST techniques for smoke, proposing a suite of upgrades that 
 enable stylizations that are significantly faster, simpler, more controlla
 ble and less prone to artifacts. \nMoreover,  the energy minimization solv
 ed by previous methods is camera dependent. To avoid that, a computational
 ly expensive iterative optimization performed for multiple views sampled a
 round the original simulation is needed, which can take up to several minu
 tes per frame. We propose a simple feed-forward neural network architectur
 e that is able to infer view-independent stylizations that are three order
 s of the magnitude faster than its optimization-based counterpart.\n\nRegi
 stration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS,
  TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_522&sess=sess15
 3
END:VEVENT
END:VCALENDAR