Synthesizing Mesh Deformation Sequences With Bidirectional LSTM

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 capabilitie...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2022-04, Vol.28 (4), p.1906-1916
Main Authors: Qiao, Yi-Ling, Lai, Yu-Kun, Fu, Hongbo, Gao, Lin
Format: Article
Language:English
Subjects:
Animation
Artificial neural networks
Computer animation
Computer architecture
deep learning
Deformation
Feature extraction
Interpolation
LSTM
Machine learning
Mesh deformation
mesh sequences
Shape
shape generation
Strain
Synthesis
Three-dimensional displays
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2020.3028961