Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
This work addresses the problem of physics-based simulation for computational physics researchers, offering an incremental improvement by incorporating physical guidance into neural network design.
The paper tackles data-driven simulation of deformable objects by introducing Alternating ConvLSTM (Alt-ConvLSTM), which models force propagation with alternate state updates, resulting in efficient modeling of material kinetic features and outperforming vanilla ConvLSTM on human soft tissue simulation with thousands of particles.
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.