# Frequency Domain-based Perceptual Loss for Super Resolution

arXiv: https://arxiv.org/abs/2007.12296 · HTML: https://mlsanity.com/paper/2007.12296/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

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

- [Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting](https://mlsanity.com/paper/2410.23159/) (2024)
- [Local-Selective Feature Distillation for Single Image Super-Resolution](https://mlsanity.com/paper/2111.10988/) (2021)
- [Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss](https://mlsanity.com/paper/2105.10214/) (2021)
- [Semantic and Geometric Unfolding of StyleGAN Latent Space](https://mlsanity.com/paper/2107.04481/) (2021)
- [MGHF: Multi-Granular High-Frequency Perceptual Loss for Image Super-Resolution](https://mlsanity.com/paper/2411.13548/) (2024)
- [A Sub-band Approach to Deep Denoising Wavelet Networks and a Frequency-adaptive Loss for Perceptual Quality](https://mlsanity.com/paper/2102.07973/) (2021)
- [Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Process](https://mlsanity.com/paper/2601.09410/) (2026)

## Abstract (arXiv)

We introduce Frequency Domain Perceptual Loss (FDPL), a loss function for single image super resolution (SR). Unlike previous loss functions used to train SR models, which are all calculated in the pixel (spatial) domain, FDPL is computed in the frequency domain. By working in the frequency domain we can encourage a given model to learn a mapping that prioritizes those frequencies most related to human perception. While the goal of FDPL is not to maximize the Peak Signal to Noise Ratio (PSNR), we found that there is a correlation between decreasing FDPL and increasing PSNR. Training a model with FDPL results in a higher average PSRN (30.94), compared to the same model trained with pixel loss (30.59), as measured on the Set5 image dataset. We also show that our method achieves higher qualitative results, which is the goal of a perceptual loss function. However, it is not clear that the improved perceptual quality is due to the slightly higher PSNR or the perceptual nature of FDPL.