Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer
share
Underwater vision suffers from severe effects due to selective attenuation and scattering when light propagates through water. Such degradation not only affects the quality of underwater images but limits the ability of vision tasks. Different from existing image enhancement and restoration methods which either ignore the wavelength dependency of the attenuation or assume a specific spectral profile, we tackle color distortion problem of underwater image from a new view. In this letter, we propose a weakly supervised color transfer method to correct color distortion. Inspired by Cycle-Consistent Adversarial Networks, we design a multi-term loss function including adversarial loss, cycle consistency loss, and SSIM (Structural Similarity Index Measure) loss. In this way, we translate the color of underwater image as if it is taken in the air, and preserve the content and structure of original underwater image. Experiments on underwater images captured under diverse scenes show that the proposed method can produce visually pleasing results, even outperforms the art-of-the-state methods. Besides, our method can improve the performance of vision tasks.
READ FULL TEXT