MDNet: A Fusion Generative Adversarial Network for Underwater Image Enhancement

Underwater images are widely used in ocean resource exploration and environment surveillance. However, due to the influence of light attenuation noise, underwater usually display degradation phenomena such as blurring color deviation; an enhancement method is required make more visible. Currently, there two major approaches for image enhancement: traditional methods based on physical or non-physical models, deep learning method. Inspired by fusion-based idea, this paper attempts combine with proposes a multi-input dense connection generator network (MDNet) enhancement. Raw processed input into together, shallow information fully utilized connection, trained generative adversarial manner. We also design multiple loss function improve visual quality generated images. conduct both qualitative quantitative experiments, then compare results state-of-the-art comprehensively using three representative datasets. Results show that proposed can effectively perceptual statistical