A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising
It addresses image denoising for applications requiring high-quality visual data, but is incremental as it builds on existing CNN and attention methods.
The paper tackles image denoising by proposing a multi-head convolutional neural network (MHCNN) that uses rotated input images and a multi-path attention mechanism, achieving higher PSNR results than state-of-the-art models like BRDNet and RIDNet.
Recently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image, limiting the richness of extracted features. Therefore, a novel CNN with multiple heads (MH) named MHCNN is proposed in this paper, whose heads will receive the input images rotated by different rotation angles. MH makes MHCNN simultaneously utilize features of rotated images to remove noise. To integrate these features effectively, we present a novel multi-path attention mechanism (MPA). Unlike previous attention mechanisms that handle pixel-level, channel-level, or patch-level features, MPA focuses on features at the image level. Experiments show MHCNN surpasses other state-of-the-art CNN models on additive white Gaussian noise (AWGN) denoising and real-world image denoising. Its peak signal-to-noise ratio (PSNR) results are higher than other networks, such as BRDNet, RIDNet, PAN-Net, and CSANN. The code is accessible at https://github.com/JiaHongZ/MHCNN.