HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration
This addresses the challenge of robust vision restoration for underwater imaging, where lack of paired data limits supervised approaches, though it is incremental as it builds on existing unsupervised frameworks.
The paper tackles the problem of unsupervised underwater image restoration by proposing a hybrid physical-neural architecture that integrates the Jaffe-McGlamery degeneration theory with neural networks, resulting in high-quality restoration that outperforms state-of-the-art supervised and unsupervised methods on multiple benchmarks.
Robust vision restoration of underwater images remains a challenge. Owing to the lack of well-matched underwater and in-air images, unsupervised methods based on the cyclic generative adversarial framework have been widely investigated in recent years. However, when using an end-to-end unsupervised approach with only unpaired image data, mode collapse could occur, and the color correction of the restored images is usually poor. In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater and in-air images. For effective color correction and quality enhancement, an underwater image degeneration model must be explicitly constructed based on the optically unambiguous physics law. Thus, we employ the Jaffe-McGlamery degeneration theory to design a generator and use neural networks to model the process of underwater visual degeneration. Furthermore, we impose physical constraints on the scene depth and degeneration factors for backscattering estimation to avoid the vanishing gradient problem during the training of the hybrid physical-neural model. Experimental results show that the proposed method can be used to perform high-quality restoration of unconstrained underwater images without supervision. On multiple benchmarks, the proposed method outperforms several state-of-the-art supervised and unsupervised approaches. We demonstrate that our method yields encouraging results in real-world applications.