DeepWarp: DNN-based Nonlinear Deformation

Abstract

DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework. Unlike other deep 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 DNN is known for its rich expressivity of nonlinear functions, directly using DNN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. DeepWarp 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, DeepWarp yields an incremental displacement fix based on a simplified (therefore incorrect) simulation result other than returning the unknown displacement directly. We contrive a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. DeepWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one DNN training is able to handle a wide range of 3D models of various geometries including most examples shown in the paper. 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, and DeepWarp is able to simulate large models in real time.

arXiv comment13 papges

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
• Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors

Cited by in corpus (12)

• Simulation of hyperelastic materials in real-time using Deep Learning
• Learning Mesh-Based Simulation with Graph Networks
• Variational Barycentric Coordinates
• RigNet: Neural Rigging for Articulated Characters
• Sparse Surface Constraints for Combining Physics-based Elasticity Simulation and Correspondence-Free Object Reconstruction
• Detail-aware Deep Clothing Animations Infused with Multi-source Attributes
• HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction
• Neural Garment Dynamics via Manifold-Aware Transformers
• Efficient Cloth Simulation using Miniature Cloth and Upscaling Deep Neural Networks
• Temporal Parameter-free Deep Skinning of Animated Meshes
• A Revisit of Shape Editing Techniques: from the Geometric to the Neural Viewpoint
• Learning Elastic Constitutive Material and Damping Models