Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
arXiv:2006.07818
Abstract
Data-driven simulation is an important step-forward in computational physics when traditional numerical methods meet their limits. Learning-based simulators have been widely studied in past years; however, most previous works view simulation as a general spatial-temporal prediction problem and take little physical guidance in designing their neural network architectures. In this paper, we introduce the alternating convolutional Long Short-Term Memory (Alt-ConvLSTM) that models the force propagation mechanisms in a deformable object with near-uniform material properties. Specifically, we propose an accumulation state, and let the network update its cell state and the accumulation state alternately. We demonstrate how this novel scheme imitates the alternate updates of the first and second-order terms in the forward Euler method of numerical PDE solvers. Benefiting from this, our network only requires a small number of parameters, independent of the number of the simulated particles, and also retains the essential features in ConvLSTM, making it naturally applicable to sequential data with spatial inputs and outputs. We validate our Alt-ConvLSTM on human soft tissue simulation with thousands of particles and consistent body pose changes. Experimental results show that Alt-ConvLSTM efficiently models the material kinetic features and greatly outperforms vanilla ConvLSTM with only the single state update.
References in corpus (13)
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural Relational Inference for Interacting Systems
- Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
- Video-to-Video Synthesis
- SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans
- DeepWrinkles: Accurate and Realistic Clothing Modeling
- Coercing Machine Learning to Output Physically Accurate Results
- SPNets: Differentiable Fluid Dynamics for Deep Neural Networks
- SAPIEN: A SimulAted Part-based Interactive ENvironment
- A Pixel-Based Framework for Data-Driven Clothing
- Recovering Geometric Information with Learned Texture Perturbations
- Efficient Cloth Simulation using Miniature Cloth and Upscaling Deep Neural Networks
- Predicting the Physical Dynamics of Unseen 3D Objects