Underwater Image Restoration using Deep Networks to Estimate Background Light and Scene Depth

 Abstract

Images taken underwater often suffer color distortion and low contrast because of light scattering and absorption. An underwater image can be modeled as a blend of a clear image and a background light, with the relative amounts of each determined by the depth from the camera. In this paper, we propose two neural network structures to estimate background light and scene depth, to restore underwater images. Experimental results on synthetic and real underwater images demonstrate the effectiveness of the proposed method.

 

由于光的散射和吸收，在水下拍摄的图像通常会出现颜色失真和低对比度。 可以将水下图像建模为清晰图像和背景光的混合，每种图像的相对量由距相机的深度确定。 在本文中，我们提出了两