Geometry encoding for numerical simulations

Abstract

We present a notion of geometry encoding suitable for machine learning-based numerical simulation. In particular, we delineate how this notion of encoding is different than other encoding algorithms commonly used in other disciplines such as computer vision and computer graphics. We also present a model comprised of multiple neural networks including a processor, a compressor and an evaluator.These parts each satisfy a particular requirement of our encoding. We compare our encoding model with the analogous models in the literature

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• MetaSDF: Meta-learning Signed Distance Functions
• Neural Unsigned Distance Fields for Implicit Function Learning
• An unsupervised learning approach to solving heat equations on chip based on Auto Encoder and Image Gradient