13
IRUS Total
Downloads
  Altmetric

3DPointCaps+plus : Learning 3D representations with capsule networks

File Description SizeFormat 
s11263-022-01632-6.pdfPublished version2.11 MBAdobe PDFView/Open
Title: 3DPointCaps+plus : Learning 3D representations with capsule networks
Authors: Zhao, Y
Fang, G
Guo, Y
Guibas, L
Tombari, F
Birdal, T
Item Type: Journal Article
Abstract: We present 3DPointCaps++ for learning robust, flexible and generalizable 3D object representations without requiring heavy annotation efforts or supervision. Unlike conventional 3D generative models, our algorithm aims for building a structured latent space where certain factors of shape variations, such as object parts, can be disentangled into independent sub-spaces. Our novel decoder then acts on these individual latent sub-spaces (i.e. capsules) using deconvolution operators to reconstruct 3D points in a self-supervised manner. We further introduce a cluster loss ensuring that the points reconstructed by a single capsule remain local and do not spread across the object uncontrollably. These contributions allow our network to tackle the challenging tasks of part segmentation, part interpolation/replacement as well as correspondence estimation across rigid / non-rigid shape, and across / within category. Our extensive evaluations on ShapeNet objects and human scans demonstrate that our network can learn generic representations that are robust and useful in many applications.
Issue Date: 30-Jul-2022
Date of Acceptance: 27-Apr-2022
URI: http://hdl.handle.net/10044/1/103602
DOI: 10.1007/s11263-022-01632-6
ISSN: 0920-5691
Publisher: Springer
Start Page: 2321
End Page: 2336
Journal / Book Title: International Journal of Computer Vision
Volume: 130
Issue: 9
Copyright Statement: © The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Publication Status: Published
Online Publication Date: 2022-07-30
Appears in Collections:Computing



This item is licensed under a Creative Commons License Creative Commons