# Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks

arXiv: https://arxiv.org/abs/1912.08776 · HTML: https://mlsanity.com/paper/1912.08776/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Overview frequency principle/spectral bias in deep learning](https://mlsanity.com/paper/2201.07395/) (2022)
- [On the Activation Function Dependence of the Spectral Bias of Neural Networks](https://mlsanity.com/paper/2208.04924/) (2022)
- [Loss Spike in Training Neural Networks](https://mlsanity.com/paper/2305.12133/) (2023)
- [Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks](https://mlsanity.com/paper/2102.00200/) (2021)
- [Frequency-adaptive Multi-scale Deep Neural Networks](https://mlsanity.com/paper/2410.00053/) (2024)
- [Frequency Principle in Deep Learning Beyond Gradient-descent-based Training](https://mlsanity.com/paper/2101.00747/) (2021)
- [An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network](https://mlsanity.com/paper/2105.11675/) (2021)

## Abstract (arXiv)

Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised L1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficiently for higher bands. This directly correlates with the quality of the perceived results, since missing high frequency details are easily noticeable. In this paper, we analyze the reconstruction quality of generative networks and present a frequency-aware loss function that is able to focus on specific bands of the dataset during training time. We show that our approach improves reconstruction quality of fluid simulation data in mid-frequency bands, yielding perceptually better results while requiring comparable training time.