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

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. The code and results can be found from the link of https://rmcong.github.io/proj_PUGAN.html.

Automated summary

Due to light absorption and scattering in water, underwater images often suffer from degradation issues such as low contrast, color distortion, and blurriness, making underwater understanding tasks more challenging. To address this, the study proposes a physical model-guided GAN model called PUGAN, which combines the advantages of GANs in visual aesthetics and physical model-based methods in scene adaptability. The proposed model includes a Parameters Estimation subnetwork for physical model inversion and a Two-Stream Interaction Enhancement subnetwork with a Degradation Quantization module. Dual-Discriminators are also designed for adversarial constraint to improve authenticity and visual aesthetics.