GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud

Cited 162 time in webofscience Cited 128 time in scopus
  • Hit : 187
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorYi, Liko
dc.contributor.authorZhao, Wangko
dc.contributor.authorWang, Heko
dc.contributor.authorSung, Minhyukko
dc.contributor.authorGuibas, Leonidasko
dc.date.accessioned2021-02-22T07:10:28Z-
dc.date.available2021-02-22T07:10:28Z-
dc.date.created2021-02-22-
dc.date.created2021-02-22-
dc.date.created2021-02-22-
dc.date.issued2019-06-
dc.identifier.citation32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp.3942 - 3951-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10203/280956-
dc.description.abstractWe introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, which greatly reducing proposals with low objectness.-
dc.languageEnglish-
dc.publisherIEEE COMPUTER SOC-
dc.titleGSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud-
dc.typeConference-
dc.identifier.wosid000529484004013-
dc.identifier.scopusid2-s2.0-85074407235-
dc.type.rimsCONF-
dc.citation.beginningpage3942-
dc.citation.endingpage3951-
dc.citation.publicationname32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationLong Beach, CA-
dc.identifier.doi10.1109/CVPR.2019.00407-
dc.contributor.localauthorSung, Minhyuk-
dc.contributor.nonIdAuthorYi, Li-
dc.contributor.nonIdAuthorZhao, Wang-
dc.contributor.nonIdAuthorWang, He-
dc.contributor.nonIdAuthorGuibas, Leonidas-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 162 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0