Atmospheric Scattering Model Induced Statistical Characteristics Estimation for Underwater Image Restoration

Underwater images often suffer from color deviation and low contrast due to selective absorption and light scattering, whose degradation is generally described by an Atmospheric Scattering Model (ASM). However, it is challenging to design hand-craft priors to estimate the transmission map and global light within ASM. To avoid the estimation on these two variables, in this paper, we establish a statistical characteristics relationship between underwater and recovered images based on ASM. With this relationship, a novel lightweight model is proposed for efficient Underwater Image Restoration (UIR). Within our proposed model, the UIR problem is disentangled into global restoration and local compensation, for which two modules are developed. Extensive experimental results demonstrate that our proposed method can effectively improve color deviation and low contrast while preserving details, and outperform state-of-the-art methods.

I. Introduction

Underwater images often suffer from various degradation. For example, the sea medium selectively absorbs light with different wavelengths, which causes color deviation, typically greenish and bluish in underwater images. Besides, the forward and backward light scattering reduces contrast, and blurs details of scenario. The degradation affects the visual quality of underwater images, and decreases the performance of marine applications [1] and computer vision applications. Therefore, Underwater Image Restoration (UIR) has become important for high-level computer vision tasks.