Detail-focused and polarization-guided multi-modality fusion for underwater image clarity enhancing

Underwater optics imaging typically suffer from the impurities scattering and light absorption in dynamic and complex underwater environment, which significantly effect the clarity and visibility of images. Existing cutting-edge Underwater Image Enhancement (UIE) methods mostly focus on color correction and contrast enhancement neglect the textual and detail information of objects, leading to imbalance exposure and edge features missing. To overcome these problems, we propose a novel detail-focused and polarization guided multi-modality fusion network (DFPG-Net), for enhancing underwater images. Unlike the previous methods, we first construct a Detail-Focused Convolution (DFC) block for extracting features from underwater multimodal images, which integrates difference convolutions to capture prior and edge information. Meanwhile, polarization information is introduced with a Multi-scale Polarization Guided (MPG) fusion module, which intends to maintain and enhance the texture and details information from the degree of polarization information and angle of polarization information obtained from the polarized image. Additionally, a parallel progressive attention network is designed to explore and combine the valuable and discriminative information in feature learning stage. Extensive experiments on the constructed underwater dataset validate the effectiveness and superior performance of the proposed DFPG-Net, which against state-of-the-art methods in both machine evaluation metrics and visual perception.