A novel dark channel prior guided variational framework for underwater image restoration

Abstract

Image captured underwater often suffers from low contrast, color distortion and noise problems, which is caused by absorbing and scattering before the light reaches the camera when traveling through water. Underwater image enhancement and restoration from a single image is known to be an ill-posed problem. To overcome these limitations, we establish an underwater total variation (UTV) model relying on underwater dark channel prior (UDCP), in which UDCP is used to estimate the transmission map. We design the data item and smooth item of the unified variational model based on the underwater image formation model. We further employ the alternating direction method of multipliers (ADMM) to accelerate the solving procedure. Numerical experiential results demonstrate that our underwater variational method obtains a good outcome on dehazing and denoising. Furthermore, compared with several other state-of-the-art algorithms, the proposed approach achieves better visual quality, which is illustrated by examples and statistics.