13
IRUS TotalDownloads
Altmetric
3DPointCaps+plus : Learning 3D representations with capsule networks
File | Description | Size | Format | |
---|---|---|---|---|
s11263-022-01632-6.pdf | Published version | 2.11 MB | Adobe PDF | View/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