Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
This work offers an incremental improvement in real image denoising performance for practitioners dealing with unknown and structured noise distributions.
This paper addresses the inefficiency of existing channel attention methods in real image denoising by proposing a Sub-band Pyramid Attention (SPA) module. The SPA module recalibrates frequency components of extracted features in a more fine-grained manner, leading to remarkable improvements over benchmark naive channel attention blocks.
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.