BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023313Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T094600
DTEND;TZID=Asia/Tokyo:20241206T095800
UID:siggraphasia_SIGGRAPH Asia 2024_sess141_papers_617@linklings.com
SUMMARY:Neural Implicit Reduced Fluid Simulation
DESCRIPTION:Technical Papers\n\nYuanyuan Tao (McGill University, Huawei Ca
 nada); Ivan Puhachov (Université de Montréal); and Derek Nowrouzezahrai an
 d Paul Kry (McGill University)\n\nHigh-fidelity simulation of fluid dynami
 cs is challenging because of the high dimensional state data needed to cap
 ture fine details and the large computational cost associated with advanci
 ng the system in time. We present neural implicit reduced fluid simulation
  (NIRFS), a reduced fluid simulation technique that combines an implicit n
 eural representation of fluid shapes and a neural ordinary differential eq
 uation to model the dynamics of fluid in the reduced latent space. The lat
 ent trajectories are computed at very little cost in comparison to simulat
 ions for training, while preserving fine physical details. We show that th
 is approach can work well, capturing the shapes and dynamics involved in a
  variety of scenarios with constrained initial conditions, e.g., droplet-d
 roplet collisions, crown splashes, and fluid slosh in a container. In each
  scenario, we learn the latent implicit representation of fluid shapes wit
 h a deep-network signed distance function, as well as the energy function 
 and parameters of a damped Hamiltonian system, which helps guarantee desir
 able properties of the latent dynamics. To ensure that latent shape repres
 entations form smooth and physically meaningful trajectories, we simultane
 ously learn the latent representation and dynamics. We evaluate novel simu
 lations for conservation of volume and momentum conservation, discuss desi
 gn decisions, and demonstrate an application of our method to fluid contro
 l.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguag
 e Format: English Language\n\nSession Chair: Sheldon Andrews (École de tec
 hnologie supérieure (ÉTS))
URL:https://asia.siggraph.org/2024/program/?id=papers_617&sess=sess141
END:VEVENT
END:VCALENDAR