# Guided Frequency Loss for Image Restoration

arXiv: https://arxiv.org/abs/2309.15563 · HTML: https://mlsanity.com/paper/2309.15563/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks](https://mlsanity.com/paper/1901.06523/) (2019)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving](https://mlsanity.com/paper/2011.13611/) (2020)
- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Spectral Distribution Aware Image Generation](https://mlsanity.com/paper/2012.03110/) (2020)
- [Y-Net: A Spatiospectral Dual-Encoder Networkfor Medical Image Segmentation](https://mlsanity.com/paper/2204.07613/) (2022)
- [NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2204.09197/) (2022)
- [SurroundNet: Towards Effective Low-Light Image Enhancement](https://mlsanity.com/paper/2110.05098/) (2021)

## Built on by (most cited first, 3 of 3)

- [EAGLE: An Edge-Aware Gradient Localization Enhanced Loss for CT Image Reconstruction](https://mlsanity.com/paper/2403.10695/) (2024)
- [Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy](https://mlsanity.com/paper/2502.12125/) (2025)
- [The Devil is in the Dark Pixels: Toward Brightness Bias-Robust Denoising](https://mlsanity.com/paper/2607.16320/) (2026)

## Abstract (arXiv)

Image Restoration has seen remarkable progress in recent years. Many generative models have been adapted to tackle the known restoration cases of images. However, the interest in benefiting from the frequency domain is not well explored despite its major factor in these particular cases of image synthesis. In this study, we propose the Guided Frequency Loss (GFL), which helps the model to learn in a balanced way the image's frequency content alongside the spatial content. It aggregates three major components that work in parallel to enhance learning efficiency; a Charbonnier component, a Laplacian Pyramid component, and a Gradual Frequency component. We tested GFL on the Super Resolution and the Denoising tasks. We used three different datasets and three different architectures for each of them. We found that the GFL loss improved the PSNR metric in most implemented experiments. Also, it improved the training of the Super Resolution models in both SwinIR and SRGAN. In addition, the utility of the GFL loss increased better on constrained data due to the less stochasticity in the high frequencies' components among samples.