Presentation / Installation


Data-free Learning of Reduced-order Kinematics
SessionMost Def: Fast, Large and Learned Deformables
DescriptionWe present a new approach for finding a small subspace that parameterizes the low-energy configurations of a physical system by "overfitting" a simple neural network. No dataset is needed, just the system's potential energy function. The method applies broadly to elastic deformables, cloth, rigid bodies, and even linkages.
Authors
Nicholas Sharp
University of Toronto
NVIDIA
Cristian Romero
Universidad Rey Juan Carlos
Alec Jacobson
University of Toronto
Adobe Research
Etienne Vouga
The University of Texas at Austin
Paul Kry
McGill University
David I.W. Levin
University of Toronto
NVIDIA
Justin Solomon
MIT
Event Type
Technical Paper
TimeWednesday, 9 August 20232:55pm - 3:05pm PDT
LocationPetree Hall C
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Wednesday, 9 August 20232pm - 3:30pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation/Simulation
Modeling
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Most Def: Fast, Large and Learned Deformables - Q&A and Interactive Discussion