File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Pointweb: Enhancing local neighborhood features for point cloud processing

TitlePointweb: Enhancing local neighborhood features for point cloud processing
Authors
KeywordsScene Analysis and Understanding
Grouping and Shape
Segmentation
3D from Multiview and Sensors
Issue Date2019
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, v. 2019-June, p. 5560-5568 How to Cite?
AbstractThis paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.
Persistent Identifierhttp://hdl.handle.net/10722/303638
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhao, Hengshuang-
dc.contributor.authorJiang, Li-
dc.contributor.authorFu, Chi Wing-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2021-09-15T08:25:43Z-
dc.date.available2021-09-15T08:25:43Z-
dc.date.issued2019-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, v. 2019-June, p. 5560-5568-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/303638-
dc.description.abstractThis paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.subjectScene Analysis and Understanding-
dc.subjectGrouping and Shape-
dc.subjectSegmentation-
dc.subject3D from Multiview and Sensors-
dc.titlePointweb: Enhancing local neighborhood features for point cloud processing-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2019.00571-
dc.identifier.scopuseid_2-s2.0-85076681284-
dc.identifier.volume2019-June-
dc.identifier.spage5560-
dc.identifier.epage5568-
dc.identifier.isiWOS:000529484005075-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats