NNWarp: Neural Network-based Nonlinear Deformation
- 15 November 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. PP (10772626) , 1
Abstract
NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g. an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model - the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.Keywords
All Related Versions
Funding Information
- NSF (1637092, 1717972)
- NSF (1464306)
- Air Force Research Laboratory (FA9453-18-2-0022)
This publication has 72 references indexed in Scilit:
- Physics-inspired upsampling for cloth simulation in gamesACM Transactions on Graphics, 2011
- Data-driven elastic models for clothACM Transactions on Graphics, 2011
- Multi-resolution isotropic strain limitingACM Transactions on Graphics, 2010
- Motion fields for interactive character locomotionACM Transactions on Graphics, 2010
- Unified simulation of elastic rods, shells, and solidsACM Transactions on Graphics, 2010
- Example-based wrinkle synthesis for clothing animationACM Transactions on Graphics, 2010
- An efficient multigrid method for the simulation of high-resolution elastic solidsACM Transactions on Graphics, 2010
- Skipping steps in deformable simulation with online model reductionACM Transactions on Graphics, 2009
- Optimizing cubature for efficient integration of subspace deformationsACM Transactions on Graphics, 2008
- Meshless animation of fracturing solidsACM Transactions on Graphics, 2005