Numerical Homogenization by Continuous Super-Resolution
This work addresses the need for efficient numerical homogenization in computational physics, offering a novel method that improves super-resolution accuracy for scientists analyzing visual patterns, though it appears incremental as it builds on existing implicit neural representation techniques.
The paper tackles the problem of approximating micro and macro patterns in physical models using finite element methods by proposing a continuous super-resolution network for numerical homogenization, which achieves superior performance in both in-distribution and out-of-distribution high-resolution predictions.
Finite element methods typically require a high resolution to satisfactorily approximate micro and even macro patterns of an underlying physical model. This issue can be circumvented by appropriate numerical homogenization or multiscale strategies that are able to obtain reasonable approximations on under-resolved scales. In this paper, we study the implicit neural representation and propose a continuous super-resolution network as a numerical homogenization strategy. It can take coarse finite element data to learn both in-distribution and out-of-distribution high-resolution finite element predictions. Our highlight is the design of a local implicit transformer, which is able to learn multiscale features. We also propose Gabor wavelet-based coordinate encodings which can overcome the bias of neural networks learning low-frequency features. Finally, perception is often preferred over distortion so scientists can recognize the visual pattern for further investigation. However, implicit neural representation is known for its lack of local pattern supervision. We propose to use stochastic cosine similarities to compare the local feature differences between prediction and ground truth. It shows better performance on structural alignments. Our experiments show that our proposed strategy achieves superior performance as an in-distribution and out-of-distribution super-resolution strategy.