首页  >  科研动态  >  正文
科研动态
邱中航(博士生)、沈焕锋的论文在IEEE GEOSCIENCE AND REMOTE SENSING LETTERS刊出
发布时间:2024-04-07 16:57:59     发布者:易真     浏览次数:

标题: Degradation-Oriented Progressive Learning for Haze-Corrupted Satellite Image Super-Resolution

作者: Qiu, ZH (Qiu, Zhonghang); Yue, LW (Yue, Linwei); Shen, HF (Shen, Huanfeng)

来源出版物: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS : 21 文献号: 6002905 DOI: 10.1109/LGRS.2024.3352731 Published Date: 2024

摘要: Image super-resolution (SR) enhances the spatial resolution and details of remote sensing images to obtain a better visual quality. However, the existing SR methods rarely consider the imaging degradation factors caused by unfavorable atmospheric conditions, which hinders them from accurately modeling the scale dependencies for the real texture features and results in artifacts in the reconstructed images. In this letter, we propose the degradation-oriented progressive learning SR (DoPSR) framework, which handles the degradation issues posed by the low resolution, together with haze, in remote sensing images. Specifically, DoPSR progressively optimizes the SR estimation for the haze-corrupted input by decomposing the challenging restoration task into feasible subproblems. It begins with two parallel subnetworks for haze component prediction and detail enhancement, respectively, and then generates the preliminary haze removal result. Furthermore, a novel collaborative refinement mechanism is introduced to encourage the refinement of the coarse result by leveraging the extracted degradation component of the former stage as prior information. In particular, a degradation-aware fusion module (DAFM) is designed to integrate the degradation prior through cross-stage feature aggregation. Extensive experimental results demonstrate the superiority of the proposed method, which outperforms competitive methods by 0.3-1.6 dB in the peak signal-to-noise ratio (PSNR) on the synthetic dataset.

作者关键词: Degradation; Image reconstruction; Feature extraction; Remote sensing; Task analysis; Data mining; Collaboration; Degradation prior; haze-corrupted; progressive learning; super-resolution (SR)

地址: [Qiu, Zhonghang; Shen, Huanfeng] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Yue, Linwei] China Univ Geosci, Sch Geog & Informat Engn, Wuhan 430074, Peoples R China.

通讯作者地址: Shen, HF (通讯作者)Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

电子邮件地址: qiu_zh@whu.edu.cn; yuelw@cug.edu.cn; shenhf@whu.edu.cn

影响因子:4.8


信息服务
学院网站教师登录 学院办公电话 学校信息门户登录

版权所有 © 太阳成tyc7111cc(股份)有限公司-搜狗百科
地址:湖北省武汉市珞喻路129号 邮编:430079 
电话:027-68778381,68778284,68778296 传真:027-68778893    邮箱:sres@whu.edu.cn