---
title: "Hybrid Frequency Modulation Network for Image Restoration"
authors:
  - "Yuning Cui"
  - "Mingyu Liu"
  - "Wenqi Ren"
  - "Alois Knoll"
doi: "10.24963/ijcai.2024/80"
url: "https://ijcai.org/proceedings/2024/80"
pdf: "https://ijcai.org/proceedings/2024/0080.pdf"
venue: "Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence"
year: 2024
pages: "722-730"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Applications"
  - "Computer Vision: CV: Representation learning"
  - "Computer Vision: CV: Computational photography"
---

# Hybrid Frequency Modulation Network for Image Restoration

Yuning Cui, Mingyu Liu, Wenqi Ren, Alois Knoll

*Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence*, pages 722-730. DOI: [10.24963/ijcai.2024/80](https://doi.org/10.24963/ijcai.2024/80)

## Abstract

Image restoration involves recovering a high-quality image from its corrupted counterpart. This paper presents an effective and efficient framework for image restoration, termed CSNet, based on ``channel + spatial" hybrid frequency modulation. Different feature channels include different degradation patterns and degrees, however, most current networks ignore the importance of channel interactions. To alleviate this issue, we propose a frequency-based channel feature modulation module to facilitate channel interactions through the channel-dimension Fourier transform. Furthermore, based on our observations, we develop a multi-scale frequency-based spatial feature modulation module to refine the direct-current component of features using extremely lightweight learnable parameters. This module contains a densely connected coarse-to-fine learning paradigm for enhancing multi-scale representation learning. In addition, we introduce a frequency-inspired loss function to achieve omni-frequency learning. Extensive experiments on nine datasets demonstrate that the proposed network achieves state-of-the-art performance for three image restoration tasks, including image dehazing, image defocus deblurring, and image desnowing. The code and models are available at https://github.com/c-yn/CSNet.