This website requires JavaScript.

Underwater Images Super-Resolution Using Generative Adversarial Network-based Model

Alireza Aghelan
Nov 2022
摘要
Single image super-resolution (SISR) methods can enhance the resolution andquality of underwater images. Enhancing the resolution of underwater imagesleads to better performance of autonomous underwater vehicles. In this work, wefine-tune the Real-Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN) model to increase the resolution of underwater images. In ourproposed approach, the pre-trained generator and discriminator networks of theReal-ESRGAN model are fine-tuned using underwater image datasets. We used theUSR-248 and UFO-120 datasets to fine-tune the Real-ESRGAN model. Our fine-tunedmodel produces images with better resolution and quality compared to theoriginal model.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答