BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030656Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251215T152200
DTEND;TZID=Asia/Hong_Kong:20251215T153300
UID:siggraphasia_SIGGRAPH Asia 2025_sess111_papers_1795@linklings.com
SUMMARY:Neural Kinematic Bases for Fluids
DESCRIPTION:Yibo Liu (University of Victoria), Zhixin Fang (Inworld AI), S
 une Darkner (University of Copenhagen), Noam Aigerman (University of Montr
 eal), Kenny Erleben (University of Copenhagen), Paul Kry (McGill Universit
 y), and Teseo Schneider (University of Victoria)\n\nWe propose mesh-free f
 luid simulations that exploit a kinematic neural basis for velocity fields
  represented by an MLP. We design a set of losses that ensures that these 
 neural bases approximate fundamental physical properties such as orthogona
 lity, divergence-free, boundary alignment, and smoothness. Our neural base
 s can then be used to fit an input sketch of a flow, which will inherit th
 e same fundamental properties from the bases. We then can animate such flo
 w in real-time using standard time integrators. Our neural bases can accom
 modate different domains, moving boundaries, and naturally extend to three
  dimensions.\n\nRegistration Category: Full Access, Full Access Supporter\
 n\nSession Chair: Ligang Liu (University of Science and Technology of Chin
 a)\n\n
END:VEVENT
END:VCALENDAR