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:20260817T171534Z
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:Yuanyuan Tao (McGill University, Huawei Canada); Ivan Puhachov
  (Université de Montréal); and Derek Nowrouzezahrai and Paul Kry (McGill U
 niversity)\n\nHigh-fidelity simulation of fluid dynamics is challenging be
 cause of the high dimensional state data needed to capture fine details an
 d the large computational cost associated with advancing the system in tim
 e. We present neural implicit reduced fluid simulation (NIRFS), a reduced 
 fluid simulation technique that combines an implicit neural representation
  of fluid shapes and a neural ordinary differential equation to model the 
 dynamics of fluid in the reduced latent space. The latent trajectories are
  computed at very little cost in comparison to simulations for training, w
 hile preserving fine physical details. We show that this approach can work
  well, capturing the shapes and dynamics involved in a variety of scenario
 s with constrained initial conditions, e.g., droplet-droplet collisions, c
 rown splashes, and fluid slosh in a container. In each scenario, we learn 
 the latent implicit representation of fluid shapes with a deep-network sig
 ned distance function, as well as the energy function and parameters of a 
 damped Hamiltonian system, which helps guarantee desirable properties of t
 he latent dynamics. To ensure that latent shape representations form smoot
 h and physically meaningful trajectories, we simultaneously learn the late
 nt representation and dynamics. We evaluate novel simulations for conserva
 tion of volume and momentum conservation, discuss design decisions, and de
 monstrate an application of our method to fluid control.\n\nRegistration C
 ategory: Full Access, Full Access Supporter\n\nLanguage Format: English La
 nguage\n\nSession Chair: Sheldon Andrews (École de Technologie Supérieure 
 (ÉTS), McGill University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_617&sess=sess141
END:VEVENT
END:VCALENDAR