Development and validation of BVB-UIE: an underwater image-enhancement model with two-layer deep neural network

Abstract

Abstract Due to the absorption and scattering of light in water, underwater visual visibility is poor, and underwater images usually suffer from color distortion and feature loss, which poses a great challenge for underwater vision tasks. To handle these issues, we present an underwater image enhancement (UIE) method. A Gaussian pyramid is constructed for the degraded underwater images based on an improved visual saliency model, with the characteristics of luminance, orientation, texture, and color. By combining channel and spatial attention mechanisms, a deep asymmetric feature enhancement network is built to preserve the high-dimensional features of the image. In addition, a polynomial loss function is used for the depth hopping supervising constraints during the enhancement process, and the gating signals are employed to control the importance of the features at different spatial locations. These innovations maximize the efficiency of the feature extraction while simplifying the network complexity. Experiments on an open benchmark dataset for UIE show that our method effectively eliminates the color bias and contrast distortion problems while preserving the complex image details compared to the existing UIE algorithms. Objective metrics show a significant improvement in the algorithm, with a 15% increment in the peak signal-to-noise ratio metric compared to the closest competing algorithm.