Jul 6, 2021 · In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater and in-air ...

Sep 12, 2024 · Our experimental results show that the proposed method is able to perform high-quality restoration for unconstrained underwater images without ...

This paper employs the Jaffe-McGlamery degeneration theory to design a generator and use neural networks to model the process of underwater visual ...

Jan 1, 2023 · In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater ...

Sep 7, 2023 · In this section, a hybrid physical-neural underwater image restoration framework (HybrUR) is discussed. The data flow and implementation of ...

In this paper, we propose a data- and physics-driven unsupervised architecture to perform underwater image restoration from unpaired underwater and in-air ...

Jul 6, 2021 · In this paper, we propose a data- and physics-driven unsupervised architecture that learns underwater vision restoration from unpaired underwater-terrestrial ...

Experimental results show that the proposed method can be used to perform high-quality restoration of unconstrained underwater images without supervision. Paper

In this project, we use Ubuntu 16.04.5, Python 3.7, Pytorch 1.7.1 and one NVIDIA RTX 2080Ti GPU. Running. Testing.

HybrUR. A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration. Requirements. Python 3; Pytorch (with CUDA); Opencv-Python; Pyyaml ...