File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: PointGroup: Dual-set point grouping for 3D instance segmentation

TitlePointGroup: Dual-set point grouping for 3D instance segmentation
Authors
Issue Date2020
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, p. 4866-4875 How to Cite?
AbstractInstance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up architecture, specifically focused on better grouping the points by exploring the void space between objects. We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid. A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength. Further, we formulate the ScoreNet to evaluate the candidate instances, followed by the Non-Maximum Suppression (NMS) to remove duplicates. We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best solutions in terms of mAP with IoU threshold 0.5.
Persistent Identifierhttp://hdl.handle.net/10722/303703
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorJiang, Li-
dc.contributor.authorZhao, Hengshuang-
dc.contributor.authorShi, Shaoshuai-
dc.contributor.authorLiu, Shu-
dc.contributor.authorFu, Chi Wing-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2021-09-15T08:25:51Z-
dc.date.available2021-09-15T08:25:51Z-
dc.date.issued2020-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, p. 4866-4875-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/303703-
dc.description.abstractInstance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up architecture, specifically focused on better grouping the points by exploring the void space between objects. We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid. A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength. Further, we formulate the ScoreNet to evaluate the candidate instances, followed by the Non-Maximum Suppression (NMS) to remove duplicates. We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best solutions in terms of mAP with IoU threshold 0.5.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titlePointGroup: Dual-set point grouping for 3D instance segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR42600.2020.00492-
dc.identifier.scopuseid_2-s2.0-85094619186-
dc.identifier.spage4866-
dc.identifier.epage4875-
dc.identifier.isiWOS:000620679505015-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats