Author:
Zheng Shijian,Wang Rujing,Zheng Shitao,Wang Liusan,Liu Zhigui
Abstract
Underwater applications present unique challenges such as color deviation, noise, and low contrast, which can degrade image quality. Addressing these issues, we propose a novel approach called the learnable full-frequency transformer dual generative adversarial network (LFT-DGAN). Our method comprises several key innovations. Firstly, we introduce a reversible convolution-based image decomposition technique. This method effectively separates underwater image information into low-, medium-, and high-frequency domains, enabling more thorough feature extraction. Secondly, we employ image channels and spatial similarity to construct a learnable full-frequency domain transformer. This transformer facilitates interaction between different branches of information, enhancing the overall image processing capabilities. Finally, we develop a robust dual-domain discriminator capable of learning spatial and frequency domain characteristics of underwater images. Extensive experimentation demonstrates the superiority of the LFT-DGAN method over state-of-the-art techniques across multiple underwater datasets. Our approach achieves significantly improved quality and evaluation metrics, showcasing its effectiveness in addressing the challenges posed by underwater imaging. The code can be found at https://github.com/zhengshijian1993/LFT-DGAN.
Reference48 articles.
1. Learning a deep single image contrast enhancer from multi-exposure images;Cai;IEEE Trans. Image Process.,2018
2. Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution;Chen,2019
3. Hinet: Half instance normalization network for image restoration;Chen,2021
4. Nice: Non-linear independent components estimation;Dinh;arXiv preprint arXiv:1410.8516,2014
5. Transmission estimation in underwater single images;Drews,2013
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献