Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising

TL;DR

This paper introduces IGNet, a lightweight CNN architecture for image denoising that leverages inter-frequency guidance via wavelet decomposition to improve performance while reducing model size.

Contribution

The novel IGNet architecture uses iterative wavelet-based frequency decomposition and inter-frequency guidance to enhance denoising, achieving competitive results with fewer parameters.

Findings

Competitive denoising performance on public datasets

Reduced model size compared to state-of-the-art methods

Effective utilization of inter-frequency prior information

Abstract

Image denoising is of vital importance in many imaging or computer vision related areas. With the convolutional neural networks showing strong capability in computer vision tasks, the performance of image denoising has also been brought up by CNN based methods. Though CNN based image denoisers show promising results on this task, most of the current CNN based methods try to learn the mapping from noisy image to clean image directly, which lacks the explicit exploration of prior knowledge of images and noises. Natural images are observed to obey the reciprocal power law, implying the low-frequency band of image tend to occupy most of the energy. Thus in the condition of AGWN (additive gaussian white noise) deterioration, low-frequency band tend to preserve a higher PSNR than high-frequency band. Considering the spatial morphological consistency of different frequency bands, low-frequency band with more fidelity can be used as a guidance to refine the more contaminated high-frequency bands. Based on this thought, we proposed a novel network architecture denoted as IGNet, in order to refine the frequency bands from low to high in a progressive manner. Firstly, it decomposes the feature maps into high- and low-frequency subbands using DWT (discrete wavelet transform) iteratively, and then each low band features are used to refine the high band features. Finally, the refined feature maps are processed by a decoder to recover the clean result. With this design, more inter-frequency prior and information are utilized, thus the model size can be lightened while still perserves competitive results. Experiments on several public datasets show that our model obtains competitive performance comparing with other state-of-the-art methods yet with a lightweight structure.