PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators

TL;DR

PUGAN is a novel underwater image enhancement model that combines physical modeling with GANs, utilizing dual discriminators and a parameter estimation subnetwork to produce clearer, more visually appealing underwater images.

Contribution

The paper introduces PUGAN, integrating physical model inversion with GANs and dual discriminators for improved underwater image enhancement.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Produces images with better clarity and color accuracy.

Enhances visual aesthetics and scene details.

Abstract

Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement sub-network (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.