Perceptual illumination-structure patch decomposition for enhancing complex lighted underwater images

Abstract

Due to the influence of natural and artificial lighting, complicated illuminated underwater images suffer from uneven exposure, accompanied by color cast, low contrast, and blurred details. Existing methods often struggle to brighten dark areas and suppress overexposed areas. To this end, a perceptual illumination-structure patch decomposition (PISPD) model is proposed to enhance complex lighted underwater images. The PISPD method is firstly based on two complementary inputs, including a contrast-enhanced image and a detail-sharpened image. To combine the complementary information of two inputs and balance brightness, the PISPD model decomposes the inputs into four elements: perceptual illumination map, contrast, structure, and average intensity. The perceptual illumination map is used to balance brightness, while the contrast, structure, and average intensity are used to integrate the features of the inputs. Moreover, a weighted edge-preserving factor is introduced in the decomposition-fusion process of contrast, structure, and mean intensity to avoid artifacts. This study also provides a benchmark dataset, namely, CLUID, containing 990 complex lighted underwater images. Experiments with qualitative and quantitative analyses show that our PISPD outperforms eight state-of-the-art approaches.