Underwater image recovery based on water type estimation and adaptive color correction

Abstract

In underwater environments, light propagation is affected by scattering and absorption, leading to color distortion and quality degradation of underwater images. In addition, the presence of a color cast in the image and variations in the attenuation coefficients across various water bodies bring great challenges for underwater image restoration. In this paper, an underwater image restoration method based on water body type estimation and adaptive color correction is proposed. Initially, the underwater images are categorized into color casts and non-color casts according to their hue, and a water body type estimation method based on image color and blurriness is introduced for improving the accuracy of transmission map estimation. Following this, we performed adaptive color correction on the image using a nonlinear transformation, which effectively eliminates color cast. Then the background light position is corrected using the degree of color cast of the image to restore the hue and brightness of the image more naturally. Ultimately, the acquired background light and transmission map are utilized to generate clear underwater images using the image formation model (IFM). Experiments on the widely used UIEB benchmark and SUID datasets show that our method effectively solves the problems of image color distortion and quality degradation, generating satisfactory visual effects.