典型文献
Unsupervised Martian Dust Storm Removal via Disentangled Representation Learning
文献摘要：
Mars exploration has become a hot spot in recent years and is still advancing rapidly. However, Mars has massive dust storms that may cover many areas of the planet and last for weeks or even months. The local/global dust storms are so influential that they can significantly reduce visibility, and thereby the images captured by the cameras on the Mars rover are degraded severely. This work presents an unsupervised Martian dust storm removal network via disentangled representation learning (DRL). The core idea of the DRL framework is to use the content encoder and dust storm encoder to disentangle the degraded images into content features (on domain-invariant space) and dust storm features (on domain-specific space). The dust storm features carry the full dust storm-relevant prior knowledge from the dust storm images. The"cleaned"content features can be effectively decoded to generate more natural, faithful, clear images. The primary advantages of this framework are twofold. First, it is among the first to perform unsupervised training in Martian dust storm removal with a single image, avoiding the synthetic data requirements. Second, the model can implicitly learn the dust storm-relevant prior knowledge from the real-world dust storm data sets, avoiding the design of the complicated handcrafted priors. Extensive experiments demonstrate the DRL framework's effectiveness and show the promising performance of our network for Martian dust storm removal.
文献关键词：
中图分类号：
作者姓名：
Dong Zhao;Jia Li;Hongyu Li;Long Xu
作者机构：
State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China;State Key Laboratory of Space Weather,National Space Science Center,Chinese Academy of Sciences,Beijing 100190,China;Peng Cheng Laboratory,Shenzhen 518000,China
文献出处：
引用格式：
[1]Dong Zhao;Jia Li;Hongyu Li;Long Xu-.Unsupervised Martian Dust Storm Removal via Disentangled Representation Learning)[J].天文和天体物理学研究,2022(09):255-266
A类：
Disentangled
B类：
Unsupervised,Martian,Dust,Storm,Removal,via,Representation,Learning,Mars,exploration,has,become,hot,spot,recent,years,still,advancing,rapidly,However,massive,dust,storms,that,may,cover,many,areas,planet,last,weeks,even,months,local,global,so,influential,they,significantly,reduce,visibility,thereby,images,captured,cameras,rover,degraded,severely,This,presents,unsupervised,removal,network,disentangled,representation,learning,DRL,core,idea,framework,use,content,encoder,into,features,domain,invariant,space,specific,carry,full,relevant,knowledge,from,cleaned,effectively,decoded,generate,more,natural,faithful,clear,primary,advantages,this,twofold,First,among,first,training,single,avoiding,synthetic,data,requirements,Second,model,implicitly,real,world,sets,design,complicated,handcrafted,priors,Extensive,experiments,demonstrate,effectiveness,show,promising,performance,our
AB值：
0.528383
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。
