Multiscale mesh deformation component analysis with attention-based autoencoders

Yang, Jie, Gao, Lin, Tan, Qingyang, Huang, Yi-Hua, Xia, Shihong and Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 2023. Multiscale mesh deformation component analysis with attention-based autoencoders. IEEE Transactions on Visualization and Computer Graphics 29 (2) , pp. 1301-1317. 10.1109/TVCG.2021.3112526

PDF - Accepted Post-Print Version Download (3MB)

Abstract

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this paper, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1077-2626
Funders:	Royal Society
Date of First Compliant Deposit:	13 September 2021
Date of Acceptance:	28 August 2021
Last Modified:	04 May 2023 07:00
URI:	https://orca.cardiff.ac.uk/id/eprint/144060

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item