Due to the selective attenuation of light in water, captured underwater images exhibit poor visibility and cause considerable challenges for vision tasks. The structural and statistical properties of different regions of degraded underwater images are damaged at different levels, resulting in a global nonuniform drift of the feature representation, causing further degradation of visual performance. To handle these issues, we present an underwater image enhancement method via multi-interval subhistogram perspective equalization to address the issues posed by underwater images. We estimate the degree of feature drifts in each area of an image by extracting the statistical characteristics of the image, using this information to guide feature enhancement to achieve adaptive feature enhancement, thereby improving the visual effect of degraded images. We first design a variational model that uses the difference between data items and regular items to improve the color correction performance of the method based on subinterval linear transformation. In addition, a multithreshold selection method, which adaptively selects a threshold array for interval division, is developed. Ultimately, a multi-interval subhistogram equalization method, which performs histogram equalization in each subhistogram to improve the image contrast, is presented. Experiments on underwater images with various scenarios demonstrate that our method significantly outperforms many state-of-the-art methods qualitatively and quantitatively.

Underwater image enhancement presents a significant challenge due to the complex and diverse underwater environments that result in severe degradation phenomena such as light absorption, scattering, and color distortion. More importantly, obtaining paired training data for these scenarios is a challenging task, which further hinders the generalization performance of enhancement models. To address these issues, we propose a novel approach, the Hybrid Contrastive Learning Regularization (HCLR-Net). Our method is built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples. This approach enables the network to develop a more robust sample distribution. Notably, we utilize non-paired data for both positive and negative samples, with negative samples are innovatively reconstructed using local patch perturbations. This strategy overcomes the constraints of relying solely on paired data, boosting the model’s potential for generalization. The HCLR-Net also incorporates an Adaptive Hybrid Attention module and a Detail Repair Branch for effective feature extraction and texture detail restoration, respectively. Comprehensive experiments demonstrate the superiority of our method, which shows substantial improvements over several state-of-the-art methods in terms of quantitative metrics, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability. Our code is available at: https://github.com/zhoujingchun03/HCLR-Net.