Single Underwater Image Restoration Based on Depth Estimation and Transmission Compensation

For undersea activities, underwater vehicles usually carry optical imaging systems for recording. The captured images and videos frequently suffer from two displeasing problems: First, color distortion; and second, poor visibility. This is mainly because that the light is exponentially attenuated while penetrating through water and the strength of attenuation is color dependent. This paper develops an effective single underwater image restoration framework based on the depth estimation and the transmission compensation. To address the consequences of scattering and absorption, our restoration scheme consists of five major phases: 1) background light estimation; 2) submerged dark channel prior; 3) transmission refinement and radiance recovery; 4) point spread function deconvolution; and 5) transmission and color compensation. A wide variety of underwater images with various scenarios were exploited to assess the restoration performance of the proposed algorithm. Various evaluation metrics were employed to analyze the experimental results. It was suggested that this new restoration algorithm outperformed many state-of-the-art methods both qualitatively and quantitatively. In addition, potential applications regarding autopilot and three-dimensional visualization were demonstrated. We believe that our underwater image restoration technique is promising in many undersea activities that require high-quality images.