Underwater image enhancement based on color restoration and dual image wavelet fusion

Highlights：

• The paper presents an adaptive color compensation method to make up for the loss of severely attenuated channels, and color restoration is further implemented to estimate the illuminant color cast caused by the selective attenuation of light.

• Since the underwater image after color restoration still suffers from scattering and blurring, an effective method based on dual image wavelet fusion (DIWF) and Generative Adversarial Network (GAN) is designed to further enhance the edge details and improve the contrast of the color restored image.

摘要

•The paper presents an approach by integrating data-driven deep learning and hand-crafted image enhancement for the single underwater image enhancement. We argue that it is impractical only to use one method to deal with the complex underwater imaging environment. By combining deep learning and image enhancement technology, the model can process images obtained in various underwater scenes.•The paper presents an adaptive color compensation method to make up for the loss of severely attenuated channels, and color restoration is further implemented to estimate the illuminant color cast caused by the selective attenuation of light.•Since the underwater image after color restoration still suffers from scattering and blurring, an effective method based on dual image wavelet fusion (DIWF) and Generative Adversarial Network (GAN) is designed to further enhance the edge details and improve the contrast of the color restored image.