PU-Mask: 3D Point Cloud Upsampling via an Implicit Virtual Mask

Simple item page
dc.contributor.authorLiu, Hao
dc.contributor.authorYuan, Hui
dc.contributor.authorHamzaoui, Raouf
dc.contributor.authorLiu, Qi
dc.contributor.authorLi, Shuai
dc.date.acceptance2024-02-21
dc.date.accessioned2024-02-27T15:13:32Z
dc.date.available2024-02-27T15:13:32Z
dc.date.issued2024-02-26
dc.descriptionThe file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.description.abstractWe present PU-Mask, a virtual mask-based network for 3D point cloud upsampling. Unlike existing upsampling methods, which treat point cloud upsampling as an “unconstrained generative” problem, we propose to address it from the perspecitive of “local filling”, i.e., we assume that the sparse input point cloud (i.e., the unmasked point set) is obtained by locally masking the original dense point cloud with virtual masks. Therefore, given the unmasked point set and virtual masks, our goal is to fill the point set hidden by the virtual masks. Specifically, because the masks do not actually exist, we first locate and form each virtual mask by a virtual mask generation module. Then, we propose a mask-guided transformer-style asymmetric autoencoder (MTAA) to restore the upsampled features. Moreover, we introduce a second-order unfolding attention mechanism to enhance the interaction between the feature channels of MTAA. Next, we generate a coarse upsampled point cloud using a pooling technique that is specific to the virtual masks. Finally, we design a learnable pseudo Laplacian operator to calibrate the coarse upsampled point cloud and generate a refined upsampled point cloud. Extensive experiments demonstrate that PU-Mask is superior to the state-of-the-art methods. Our code will be made available at: https://github.com/liuhaoyun/PU-Mask
dc.funderOther external funder (please detail below)
dc.funder.otherNational Natural Science Foundation of China
dc.funder.otherHigh-end Foreign Experts Recruitment Plan of Chinese Ministry of Science and Technology
dc.funder.otherTaishan Scholar Project of Shandong Province
dc.funder.otherNatural Science Foundation of Shandong Province
dc.funder.otherShandong Provincial Higher Education Youth Innovation Team Project
dc.identifier.citationH. Liu, H. Yuan, R. Hamzaoui, Q. Liu, S. Li, (2024) PU-Mask: 3D point cloud upsampling via an implicit virtual mask. IEEE Transactions on Circuits and Systems for Video Technology, 34 (7), pp. 6489 - 6502
dc.identifier.doihttps://doi.org/10.1109/TCSVT.2024.3370001
dc.identifier.urihttps://hdl.handle.net/2086/23587
dc.language.isoen
dc.peerreviewedYes
dc.projectid62222110, 62172259
dc.projectidG2023150003L
dc.projectidtsqn202103001
dc.projectidZR2022ZD38, ZR2023QF111
dc.projectid2022KJ268
dc.publisherIEEE
dc.researchinstituteInstitute of Engineering Sciences (IES)
dc.rightsAttribution-NonCommercial-NoDerivs 2.0 UK: England & Walesen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.0/uk/
dc.subjectTECHNOLOGY::Information technology::Signal processing
dc.titlePU-Mask: 3D Point Cloud Upsampling via an Implicit Virtual Mask
dc.typeArticle

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
IEEE_TCSVT.pdf
Size:
1.21 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
IEEE_TCSVT.pdf
Size:
17.31 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

School of Engineering and Sustainable Development