Show simple item record

dc.contributor.authorLi, Tingtingen_US
dc.contributor.authorFu, Yunfeien_US
dc.contributor.authorHan, Xiaoguangen_US
dc.contributor.authorLiang, Huien_US
dc.contributor.authorZhang, Jian Junen_US
dc.contributor.authorChang, Jianen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:39:35Z
dc.date.available2022-10-04T06:39:35Z
dc.date.issued2022
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14663
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14663
dc.description.abstractPoint cloud generation aims to synthesize point clouds that do not exist in supervised dataset. Generating a point cloud with certain semantic labels remains an under-explored problem. This paper proposes a formulation called DiffusionPointLabel, which completes point-label pair generation based on a DDPM generative model (Denoising Diffusion Probabilistic Model). Specifically, we use a point cloud diffusion generative model and aggregate the intermediate features of the generator. On top of this, we propose Feature Interpreter that transforms intermediate features into semantic labels. Furthermore, we employ an uncertainty measure to filter unqualified point-label pairs for a better quality of generated point cloud dataset. Coupling these two designs enables us to automatically generate annotated point clouds, especially when supervised point-labels pairs are scarce. Our method extends the application of point cloud generation models and surpasses state-of-the-art models.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Methods and Applications → Point-Based Methods
dc.subjectMethods and Applications → Point
dc.subjectBased Methods
dc.titleDiffusionPointLabel: Annotated Point Cloud Generation with Diffusion Modelen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersPoint Cloud Generation
dc.description.volume41
dc.description.number7
dc.identifier.doi10.1111/cgf.14663
dc.identifier.pages131-139
dc.identifier.pages9 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 41-Issue 7
    Pacific Graphics 2022 - Symposium Proceedings

Show simple item record