Underwater image enhancement combining dual color space and contrast learning

With the continuous increase of human society's demand for marine resources, underwater vision plays an increasingly important role in marine information acquisition. However, due to the absorption and scattering of light, underwater images have characteristics such as blurring, low contrast, and color distortion, which are not conducive to the acquisition of underwater image information. The rapid development of deep learning and powerful feature learning capabilities have been widely used in underwater image enhancement tasks, but current research still has problems such as loss of local details and oversaturation. Aiming at the above problems, this paper proposes an underwater image enhancement method combining dual color space and contrast learning, including RGB color space and Lab color space. The RGB color space is used for color correction and artifact removal, and the Lab color space is used to enhance saturation and detail texture. The contrastive learning of positive and negative samples makes the generated image closer to the clear underwater image and deviates from the real underwater image. Experimental results on real underwater datasets show that the proposed method achieves the best results on PSNR, SSIM and UIQM compared to other underwater image enhancement methods.