Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention

TL;DR

This paper introduces a Sub-band Pyramid Attention mechanism that enhances channel attention in real image denoising by leveraging wavelet sub-band pyramids for more detailed frequency component recalibration, leading to improved denoising performance.

Contribution

It proposes a novel SPA module based on wavelet sub-band pyramids to improve frequency-level channel attention in denoising networks, outperforming existing methods.

Findings

Significant performance improvement over baseline channel attention methods.

Pyramid level influences the effectiveness of SPA blocks.

SPA blocks demonstrate strong generalization across different scenarios.

Abstract

Convolutional layers in Artificial Neural Networks (ANN) treat the channel features equally without feature selection flexibility. While using ANNs for image denoising in real-world applications with unknown noise distributions, particularly structured noise with learnable patterns, modeling informative features can substantially boost the performance. Channel attention methods in real image denoising tasks exploit dependencies between the feature channels, hence being a frequency component filtering mechanism. Existing channel attention modules typically use global statics as descriptors to learn the inter-channel correlations. This method deems inefficient at learning representative coefficients for re-scaling the channels in frequency level. This paper proposes a novel Sub-band Pyramid Attention (SPA) based on wavelet sub-band pyramid to recalibrate the frequency components of the extracted features in a more fine-grained fashion. We equip the SPA blocks on a network designed for real image denoising. Experimental results show that the proposed method achieves a remarkable improvement than the benchmark naive channel attention block. Furthermore, our results show how the pyramid level affects the performance of the SPA blocks and exhibits favorable generalization capability for the SPA blocks.