A hybrid attention network with convolutional neural network and transformer for underwater image restoration

Abstract

The analysis and communication of underwater images are often impeded by various elements such as blur, color cast, and noise. Existing restoration methods only address specific degradation factors and struggle with complex degraded images. Furthermore, traditional convolutional neural network (CNN) based approaches may only restore local color while ignoring global features. The proposed hybrid attention network combining CNN and Transformer focuses on addressing these issues. CNN captures local features and the Transformer uses multi-head self-attention to model global relationships. The network also incorporates degraded channel attention and supervised attention mechanisms to refine relevant features and correlations. The proposed method fared better than existing methods in a variety of qualitative criteria when evaluated against the public EUVP dataset of underwater images.