Underwater image enhancement via color conversion and white balance-based fusion.

The task of enhancing underwater images presents a significant challenge due to the refraction and absorption of light in water, resulting in images that often appear bluish or greenish with diminished contrast. Furthermore, the scarcity of underwater datasets complicates the achievement of robust generalization capacity to address complex underwater scenarios. In this study, we introduce generalized underwater image enhancement model with color-guided adaptive feature fusion (GU-CAFF), designed to rectify various degraded underwater images, utilizing a minimal amount of training data. GU-CAFF primarily comprises two modules: a multi-level color-feature encoder (MCE) and a white balance-based fusion (WBF) module. The MCE integrates physical models to extract features from underwater images exhibiting different color deviations, emphasizing essential features while preserving their structural information. In addition, WBF, in conjunction with a statistical model, is proposed to fuse the features extracted by the encoder and rectify the color distortion of specific pixels in degraded images. The proposed method can be trained once on our developed dataset and exhibits robust generalization capabilities on other datasets. Quantitative and qualitative comparisons are conducted with several state-of-the-art underwater image enhancement models, demonstrating our superior performance in enhancing underwater images.The source code will be available at https://github.com/shiningZZ/GU-CAFF. [ABSTRACT FROM AUTHOR]