Two-step approach for single underwater image enhancement

TLDR

Underwater images often suffer from color shift and contrast degradation due to absorption and scattering of light. In order to handle these issues, we present and solve two sub‑problems to improve underwater image quality. The method uses a piece‑wise linear color correction and an efficient contrast‑improvement algorithm that operates pixel‑wise, requires no prior imaging knowledge, and is suitable for real‑time use. Experiments show improved color, contrast, naturalness, and object prominence.

Abstract

Underwater images often suffer from color shift and contrast degradation due to the absorption and scattering of light while traveling in water. In order to handle these issues, we present and solve two sub-problems to improve underwater image quality. First, we introduce an effective color correcting strategy based on piece-wise linear transformation to address the color distortion. Then we discuss a novel optimal contrast improvement method, which is efficient and can reduce artifacts, to address the low contrast. Since most operations are pixel-wise calculations, the proposed method is straightforward to implement and appropriate for real-time application. In addition, prior knowledge about imaging conditions is not required. Experiments show an improvement in the enhanced image of color, contrast, naturalness and object prominence.