典型文献
Image De-occlusion via Event-enhanced Multi-modal Fusion Hybrid Network
文献摘要：
Seeing through dense occlusions and reconstructing scene images is an important but challenging task.Traditional frame-based image de-occlusion methods may lead to fatal errors when facing extremely dense occlusions due to the lack of valid information available from the limited input occluded frames.Event cameras are bio-inspired vision sensors that record the brightness changes at each pixel asynchronously with high temporal resolution.However,synthesizing images solely from event streams is ill-posed since only the brightness changes are recorded in the event stream,and the initial brightness is unknown.In this paper,we propose an event-en-hanced multi-modal fusion hybrid network for image de-occlusion,which uses event streams to provide complete scene information and frames to provide color and texture information.An event stream encoder based on the spiking neural network(SNN)is proposed to en-code and denoise the event stream efficiently.A comparison loss is proposed to generate clearer results.Experimental results on a large-scale event-based and frame-based image de-occlusion dataset demonstrate that our proposed method achieves state-of-the-art perform-ance.
文献关键词：
中图分类号：
作者姓名：
Si-Qi Li;Yue Gao;Qiong-Hai Dai
作者机构：
Beijing National Research Center for Information Science and Technology,Tsinghua University,Beijing 100084,China;Institute for Brain and Cognitive Sciences,Tsinghua University,Beijing 100084,China;Beijing Laboratory of Brain and Cognitive Intelligence,Beijing Municipal Education Commission,Tsinghua University,Beijing 100084,China;Key Laboratory for Information System Security,School of Software,Tsinghua University,Beijing 100084,China;Department of Automation,Tsinghua University,Beijing 100084,China
文献出处：
引用格式：
[1]Si-Qi Li;Yue Gao;Qiong-Hai Dai-.Image De-occlusion via Event-enhanced Multi-modal Fusion Hybrid Network)[J].机器智能研究（英文）,2022(04):307-318
A类：
asynchronously,denoise
B类：
Image,De,via,Event,enhanced,Multi,modal,Fusion,Hybrid,Network,Seeing,through,dense,occlusions,reconstructing,scene,images,important,but,challenging,task,Traditional,methods,may,lead,fatal,errors,when,facing,extremely,due,lack,valid,information,available,from,limited,input,occluded,frames,cameras,bio,inspired,vision,sensors,that,brightness,changes,each,pixel,high,temporal,resolution,However,synthesizing,solely,event,streams,ill,since,only,recorded,initial,unknown,In,this,paper,multi,fusion,hybrid,network,which,uses,provide,complete,color,texture,An,encoder,spiking,neural,SNN,proposed,efficiently,comparison,loss,generate,clearer,results,Experimental,large,scale,dataset,demonstrate,our,achieves,state,art,perform
AB值：
0.558578
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。
