File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: 3D Graph Neural Networks for RGBD Semantic Segmentation

Title3D Graph Neural Networks for RGBD Semantic Segmentation
Authors
Issue Date2017
Citation
Proceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 5209-5218 How to Cite?
Abstract© 2017 IEEE. RGBD semantic segmentation requires joint reasoning about 2D appearance and 3D geometric information. In this paper we propose a 3D graph neural network (3DGNN) that builds a k-nearest neighbor graph on top of 3D point cloud. Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images. Relying on recurrent functions, every node dynamically updates its hidden representation based on the current status and incoming messages from its neighbors. This propagation model is unrolled for a certain number of time steps and the final per-node representation is used for predicting the semantic class of each pixel. We use back-propagation through time to train the model. Extensive experiments on NYUD2 and SUN-RGBD datasets demonstrate the effectiveness of our approach.
Persistent Identifierhttp://hdl.handle.net/10722/281948
ISSN
2023 SCImago Journal Rankings: 12.263
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorLiao, Renjie-
dc.contributor.authorJia, Jiaya-
dc.contributor.authorFidler, Sanja-
dc.contributor.authorUrtasun, Raquel-
dc.date.accessioned2020-04-09T09:19:12Z-
dc.date.available2020-04-09T09:19:12Z-
dc.date.issued2017-
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision, 2017, v. 2017-October, p. 5209-5218-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/281948-
dc.description.abstract© 2017 IEEE. RGBD semantic segmentation requires joint reasoning about 2D appearance and 3D geometric information. In this paper we propose a 3D graph neural network (3DGNN) that builds a k-nearest neighbor graph on top of 3D point cloud. Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images. Relying on recurrent functions, every node dynamically updates its hidden representation based on the current status and incoming messages from its neighbors. This propagation model is unrolled for a certain number of time steps and the final per-node representation is used for predicting the semantic class of each pixel. We use back-propagation through time to train the model. Extensive experiments on NYUD2 and SUN-RGBD datasets demonstrate the effectiveness of our approach.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE International Conference on Computer Vision-
dc.title3D Graph Neural Networks for RGBD Semantic Segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCV.2017.556-
dc.identifier.scopuseid_2-s2.0-85041908073-
dc.identifier.volume2017-October-
dc.identifier.spage5209-
dc.identifier.epage5218-
dc.identifier.isiWOS:000425498405031-
dc.identifier.issnl1550-5499-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats