Wavelet-based Loss for High-frequency Interface Dynamics

09/06/2022
by   Lukas Prantl, et al.
8

Generating highly detailed, complex data is a long-standing and frequently considered problem in the machine learning field. However, developing detail-aware generators remains an challenging and open problem. Generative adversarial networks are the basis of many state-of-the-art methods. However, they introduce a second network to be trained as a loss function, making the interpretation of the learned functions much more difficult. As an alternative, we present a new method based on a wavelet loss formulation, which remains transparent in terms of what is optimized. The wavelet-based loss function is used to overcome the limitations of conventional distance metrics, such as L1 or L2 distances, when it comes to generate data with high-frequency details. We show that our method can successfully reconstruct high-frequency details in an illustrative synthetic test case. Additionally, we evaluate the performance when applied to more complex surfaces based on physical simulations. Taking a roughly approximated simulation as input, our method infers corresponding spatial details while taking into account how they evolve. We consider this problem in terms of spatial and temporal frequencies, and leverage generative networks trained with our wavelet loss to learn the desired spatio-temporal signal for the surface dynamics. We test the capabilities of our method with a set of synthetic wave function tests and complex 2D and 3D dynamics of elasto-plastic materials.

READ FULL TEXT

page 4

page 7

page 8

page 9

research
12/18/2019

Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks

Convolutional neural networks were recently employed to fully reconstruc...
research
10/18/2022

WaGI : Wavelet-based GAN Inversion for Preserving High-frequency Image Details

Recent GAN inversion models focus on preserving image-specific details t...
research
03/02/2022

PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling

We propose a generative adversarial network for point cloud upsampling, ...
research
02/11/2021

SWAGAN: A Style-based Wavelet-driven Generative Model

In recent years, considerable progress has been made in the visual quali...
research
08/01/2023

Generative adversarial networks with physical sound field priors

This paper presents a deep learning-based approach for the spatio-tempor...
research
10/12/2021

SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring

Image deblurring is a classical computer vision problem that aims to rec...
research
07/22/2020

Flexible nonstationary spatio-temporal modeling of high-frequency monitoring data

Many physical datasets are generated by collections of instruments that ...

Please sign up or login with your details

Forgot password? Click here to reset