典型文献
Neighborhood co-occurrence modeling in 3D point cloud segmentation
文献摘要:
A significant performance boost has been achieved in point cloud semantic segmentation by utilization of the encoder-decoder architecture and novel convolution operations for point clouds.However,co-occurrence relationships within a local region which can directly influence segmentation results are usually ignored by current works.In this paper,we propose a neighborhood co-occurrence matrix(NCM)to model local co-occurrence relationships in a point cloud.We generate target NCM and prediction NCM from semantic labels and a prediction map respectively.Then,Kullback-Leibler(KL)divergence is used to maximize the similarity between the target and prediction NCMs to learn the co-occurrence relationship.Moreover,for large scenes where the NCMs for a sampled point cloud and the whole scene differ greatly,we introduce a reverse form of KL divergence which can better handle the difference to supervise the prediction NCMs.We integrate our method into an existing backbone and conduct comprehensive experiments on three datasets:Semantic3D for outdoor space segmentation,and S3DIS and ScanNet v2 for indoor scene segmentation.Results indicate that our method can significantly improve upon the backbone and outperform many leading competitors.
文献关键词:
中图分类号:
作者姓名:
Jingyu Gong;Zhou Ye;Lizhuang Ma
作者机构:
Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;Shanghai CLS Fintech Co.,LTD,Shanghai 200030,China;MoE Key Lab of Artificial Intelligence,Shanghai Jiao Tong University,Shanghai 200240,China
文献出处:
引用格式:
[1]Jingyu Gong;Zhou Ye;Lizhuang Ma-.Neighborhood co-occurrence modeling in 3D point cloud segmentation)[J].计算可视媒体(英文),2022(02):303-315
A类:
NCMs
B类:
Neighborhood,occurrence,modeling,point,segmentation,performance,boost,has,been,achieved,semantic,by,utilization,encoder,decoder,architecture,novel,convolution,operations,clouds,However,relationships,within,local,region,which,directly,influence,results,are,usually,ignored,current,works,In,this,paper,propose,neighborhood,matrix,We,generate,target,prediction,from,labels,map,respectively,Then,Kullback,Leibler,KL,divergence,used,maximize,similarity,between,learn,Moreover,large,scenes,where,sampled,whole,greatly,introduce,reverse,better,handle,difference,supervise,integrate,our,method,into,existing,backbone,conduct,comprehensive,experiments,three,datasets,Semantic3D,outdoor,space,S3DIS,ScanNet,v2,indoor,Results,indicate,that,significantly,improve,upon,outperform,many,leading,competitors
AB值:
0.583464
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。