典型文献
Arbitrary Scale Super Resolution Network for Satellite Imagery
文献摘要：
Recently,satellite imagery has been widely applied in many areas.However,due to the limitations of hardware equipment and transmission bandwidth,the images received on the ground have low resolu-tion and weak texture.In addition,since ground ter-minals have various resolutions and real-time playing requirements,it is essential to achieve arbitrary scale super-resolution(SR)of satellite images.In this paper,we propose an arbitrary scale SR network for satel-lite image reconstruction.First,we propose an ar-bitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbi-trary scale enlarged SR outputs.Second,we design an edge reinforcement module to enhance the high-frequency details in satellite images through a two-branch network.Finally,extensive upsample experi-ments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counter-parts.
文献关键词：
中图分类号：
作者姓名：
Jing Fang;Jing Xiao;Xu Wang;Dan Chen;Ruimin Hu
作者机构：
National Engineering Research Center for Multimedia Software,School of Computer Science,Wuhan University,Wuhan 430072,China;Collaborative Innovation Center of Geospatial Technology,Wuhan 430079,China;National University of Defense Technology,Wuhan 430015,China
文献出处：
引用格式：
[1]Jing Fang;Jing Xiao;Xu Wang;Dan Chen;Ruimin Hu-.Arbitrary Scale Super Resolution Network for Satellite Imagery)[J].中国通信（英文版）,2022(08):234-246
A类：
bitrary,upsample
B类：
Arbitrary,Scale,Super,Resolution,Network,Satellite,Imagery,Recently,satellite,imagery,has,been,widely,applied,many,areas,However,due,limitations,hardware,equipment,transmission,bandwidth,images,received,ground,have,low,weak,texture,In,addition,since,minals,various,resolutions,real,playing,requirements,essential,achieve,arbitrary,SR,this,paper,propose,network,reconstruction,First,upscale,module,that,can,map,features,enlarged,outputs,Second,design,edge,reinforcement,enhance,high,frequency,details,through,branch,Finally,extensive,WHU,RS19,NWPU,RESISC45,datasets,subsequent,segmentation,experiments,both,show,superiority,our,method,over,counter,parts
AB值：
0.587225
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
