典型文献
BLNet:Bidirectional learning network for point clouds
文献摘要：
The key challenge in processing point clouds lies in the inherent lack of ordering and irregularity of the 3D points.By relying on per-point multi-layer perceptions(MLPs),most existing point-based approaches only address the first issue yet ignore the second one.Directly convolving kernels with irregular points will result in loss of shape information.This paper introduces a novel point-based bidirectional learning network(BLNet)to analyze irregular 3D points.BLNet optimizes the learning of 3D points through two iterative operations:feature-guided point shifting and feature learning from shifted points,so as to minimise intra-class variances,leading to a more regular distribution.On the other hand,explicitly modeling point positions leads to a new feature encoding with increased structure-awareness.Then,an attention pooling unit selectively combines important features.This bidirectional learning alternately regularizes the point cloud and learns its geometric features,with these two procedures iteratively promoting each other for more effective feature learning.Experiments show that BLNet is able to learn deep point features robustly and efficiently,and outperforms the prior state-of-the-art on multiple challenging tasks.
文献关键词：
中图分类号：
作者姓名：
Wenkai Han;Hai Wu;Chenglu Wen;Cheng Wang;Xin Li
作者机构：
School of Informatics,Xiamen University,422 Siming South Road,Xiamen 361005,China;School of Electrical Engineering and Computer Science,Louisiana State University,Baton Rouge,LA 70803,USA
文献出处：
引用格式：
[1]Wenkai Han;Hai Wu;Chenglu Wen;Cheng Wang;Xin Li-.BLNet:Bidirectional learning network for point clouds)[J].计算可视媒体（英文）,2022(04):585-596
A类：
MLPs,convolving,regularizes
B类：
BLNet,Bidirectional,learning,network,clouds,key,challenge,processing,lies,inherent,lack,ordering,irregularity,points,By,relying,layer,perceptions,most,existing,approaches,only,address,first,issue,yet,ignore,second,one,Directly,kernels,will,result,loss,shape,information,This,paper,introduces,novel,bidirectional,analyze,optimizes,through,operations,guided,shifting,from,shifted,so,minimise,intra,class,variances,leading,more,distribution,On,other,hand,explicitly,modeling,positions,leads,new,encoding,increased,structure,awareness,Then,attention,pooling,unit,selectively,combines,important,features,alternately,learns,its,geometric,these,procedures,iteratively,promoting,each,effective,Experiments,show,that,able,deep,robustly,efficiently,outperforms,prior,state,art,multiple,challenging,tasks
AB值：
0.606756
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。
