GMRV Publications

Learning Contact Corrections for Handle-Based Subspace Dynamics

Cristian Romero, Dan Casas, Jesus Perez, Miguel A. Otaduy
ACM Trans. on Graphics (Proc. of ACM SIGGRAPH), Volume 40, Number 4 - 2021
Download the publication : Romero_SIG2021_final.pdf [19.5Mo]  
This paper introduces a novel subspace method for the simulation of dynamic deformations. The method augments existing linear handle-based subspace formulations with nonlinear learning-based corrections parameterized by the same subspace. Together, they produce a compact nonlinear model that combines the fast dynamics and overall contact-based interaction of subspace methods, with the highly detailed deformations of learning-based methods. We propose a formulation of the model with nonlinear corrections applied on the local undeformed setting, and decoupling internal and external contact-driven corrections. We define a simple mapping of these corrections to the global setting, an efficient implementation for dynamic simulation, and a training pipeline to generate examples that efficiently cover the interaction space. Altogether, the method achieves unprecedented combination of speed and contact-driven deformation detail.

Images and movies

TeaserSmall.png [232Ko]
 

BibTex references

@Article\{RCPO21,
  author       = "Romero, Cristian and Casas, Dan and Perez, Jesus and Otaduy, Miguel A.",
  title        = "Learning Contact Corrections for Handle-Based Subspace Dynamics",
  journal      = "ACM Trans. on Graphics (Proc. of ACM SIGGRAPH)",
  number       = "4",
  volume       = "40",
  year         = "2021",
  url          = "http://gmrv.es/Publications/2021/RCPO21"
}

Other publications in the database

» Cristian Romero
» Dan Casas
» Jesus Perez
» Miguel A. Otaduy