典型文献
Depth estimation using an improved stereo network
文献摘要：
Self-supervised depth estimation approaches present excellent results that are comparable to those of the fully supervised approaches, by employing view synthesis between the target and reference images in the training data. ResNet, which serves as a backbone network, has some structural deficiencies when applied to downstream fields, because its original purpose was to cope with classification problems. The low-texture area also deteriorates the performance. To address these problems, we propose a set of improvements that lead to superior predictions. First, we boost the information flow in the network and improve the ability to learn spatial structures by improving the network structures. Second, we use a binary mask to remove the pixels in low-texture areas between the target and reference images to more accurately reconstruct the image. Finally, we input the target and reference images randomly to expand the dataset and pre-train it on ImageNet, so that the model obtains a favorable general feature representation. We demonstrate state-of-the-art performance on an Eigen split of the KITTI driving dataset using stereo pairs.
文献关键词：
中图分类号：
作者姓名：
Wanpeng XU;Ling ZOU;Lingda WU;Yue QI;Zhaoyong QIAN
作者机构：
Science and Technology on Complex Electronic System Simulation Laboratory,Space Engineering University,Beijing 101416,China;Digital Media School,Beijing Film Academy,Beijing 100088,China;Peng Cheng Laboratory,Shenzhen 518055,China
文献出处：
引用格式：
[1]Wanpeng XU;Ling ZOU;Lingda WU;Yue QI;Zhaoyong QIAN-.Depth estimation using an improved stereo network)[J].信息与电子工程前沿（英文）,2022(05):777-789
A类：
B类：
Depth,estimation,using,improved,stereo,network,Self,supervised,depth,approaches,excellent,results,that,comparable,those,fully,by,employing,view,synthesis,between,target,reference,images,training,ResNet,which,serves,backbone,has,some,structural,deficiencies,when,applied,downstream,fields,because,its,original,purpose,was,cope,classification,problems,texture,also,deteriorates,performance,To,address,these,propose,improvements,lead,superior,predictions,First,boost,information,flow,ability,learn,spatial,structures,improving,Second,binary,mask,remove,pixels,areas,more,accurately,reconstruct,Finally,input,randomly,expand,dataset,ImageNet,model,obtains,favorable,general,feature,representation,We,demonstrate,state,art,Eigen,split,KITTI,driving,pairs
AB值：
0.626594
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。
