We present a methodology to automatically obtain Pose Space Deformation (PSD) basis for rigged garments through deep learning. Classical approaches rely on Physically Based …
We propose the first reduced model simulation framework for deformable solid dynamics using autoencoder neural networks. We provide a data‐driven approach to generating …
This paper provides a new avenue for exploiting deep neural networks to improve physics- based simulation. Specifically, we integrate the classic Lagrangian mechanics with a deep …
D Holden, BC Duong, S Datta… - Proceedings of the 18th …, 2019 - dl.acm.org
Data-driven methods for physical simulation are an attractive option for interactive applications due to their ability to trade precomputation and memory footprint in exchange …
We present SoftSMPL, a learning‐based method to model realistic soft‐tissue dynamics as a function of body shape and motion. Datasets to learn such task are scarce and expensive to …
We propose a novel method to machine-learn highly detailed, nonlinear contact deformations for real-time dynamic simulation. We depart from previous deformation …
Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin …
For a given PDE problem, three main factors affect the accuracy of FEM solutions: basis order, mesh resolution, and mesh element quality. The first two factors are easy to control …
This paper introduces a novel subspace method for the simulation of dynamic deformations. The method augments existing linear handle-based subspace formulations with nonlinear …