Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Synthesizing mesh deformation sequences with bidirectional LSTM

Qiao, Yi-Ling, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680, Fu, Hongbo and Gao, Lin 2022. Synthesizing mesh deformation sequences with bidirectional LSTM. IEEE Transactions on Visualization and Computer Graphics 28 (4) , pp. 1906-1916. 10.1109/TVCG.2020.3028961

[thumbnail of Synthesizing_Mesh_Deformation_Sequences_with_Bidirectional_LSTM_TVCG2020.pdf]
Preview
PDF - Accepted Post-Print Version
Download (19MB) | Preview

Abstract

Synthesizing realistic 3D mesh deformation sequences is a challenging but important task in computer animation. To achieve this, researchers have long been focusing on shape analysis to develop new interpolation and extrapolation techniques. However, such techniques have limited learning capabilities and therefore often produce unrealistic deformation. Although there are already networks defined on individual meshes, deep architectures that operate directly on mesh sequences with temporal information remain unexplored due to the following major barriers: irregular mesh connectivity, rich temporal information, and varied deformation. To address these issues, we utilize convolutional neural networks defined on triangular meshes along with a shape deformation representation to extract useful features, followed by long short-term memory(LSTM) that iteratively processes the features. To fully respect the bidirectional nature of actions, we propose a new share-weight bidirectional scheme to better synthesize deformations. An extensive evaluation shows that our approach outperforms existing methods in sequence generation, both qualitatively and quantitatively. Published in: IEEE Transactions on Visualization and Computer Graphics

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 1077-2626
Funders: The Royal Society
Date of First Compliant Deposit: 9 October 2020
Date of Acceptance: 21 September 2020
Last Modified: 03 May 2023 23:23
URI: https://orca.cardiff.ac.uk/id/eprint/135493

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics