BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163645Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T143500
DTEND;TZID=Australia/Melbourne:20231214T144500
UID:siggraphasia_SIGGRAPH Asia 2023_sess151_papers_637@linklings.com
SUMMARY:Neural Stress Fields for Reduced-order Elastoplasticity and Fractu
 re
DESCRIPTION:Zeshun Zong and Xuan Li (University of California Los Angeles)
 ; Minchen Li (University of California Los Angeles, Carnegie Mellon Univer
 sity); Maurizio M. Chiaramonte (Meta Reality Labs Research); Wojciech Matu
 sik (MIT CSAIL); Eitan Grinspun (University of Toronto); Kevin Carlberg (M
 eta Reality Labs Research); Chenfanfu Jiang (University of California Los 
 Angeles); and Peter Yichen Chen (MIT CSAIL)\n\nThe material point method (
 MPM) is a versatile simulation framework for large-deformation elastoplast
 icity and fracture. However, MPM's long runtime and large memory consumpti
 ons render it unsuitable for applications constrained by computation time 
 and memory usage, e.g., virtual reality. To overcome these barriers, we pr
 opose a reduced-order MPM framework. Our key innovation is training a low-
 dimensional manifold for the Kirchhoff stress field via an implicit neural
  representation. This low-dimensional neural stress field (NSF) enables ef
 ficient evaluations of stress values and, correspondingly, internal forces
  at arbitrary spatial locations. In addition, we also train neural deforma
 tion and affine fields to build low-dimensional manifolds for the deformat
 ion and affine momentum fields. These neural stress, deformation, and affi
 ne fields share the same low-dimensional latent space, which uniquely embe
 ds the high-dimensional MPM simulation state. After training, we run new s
 imulations by evolving in this single latent space, which drastically redu
 ces the computation time and memory consumption. Our general continuum-mec
 hanics-based reduced-order framework is applicable to any phenomena govern
 ed by the elastodynamics equation. To showcase the versatility of our fram
 ework, we simulate a wide range of material behaviors, including elastica,
  sand, metal, non-Newtonian fluids, fracture, contact, and collision. We d
 emonstrate dimension reduction by up to 100,000X and time savings by up to
  10X.\n\nRegistration Category: Full Access\n\nSession Chair: Tao Du (Tsin
 ghua University, Shanghai Qi Zhi Institute)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_637&sess=sess151
END:VEVENT
END:VCALENDAR