Deep deformation detail synthesis for thin shell models

Chen, Lan, Gao, Lin, Yang, Jie, Xu, Shibiao, Ye, Juntao, Zhang, Xiaopeng and Lai, YuKun ORCID: https://orcid.org/0000-0002-2094-5680 2023. Deep deformation detail synthesis for thin shell models. Computer Graphics Forum 42 (5) , e14903. 10.1111/cgf.14903 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 10 August 2024 due to copyright restrictions. Download (17MB)

Abstract

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes obtained through simulation, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the spatial and temporal Transformer network that consists of vertex-level and frame-level attention mechanisms to ensure detail enhancement and temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates with superior detail synthesis abilities compared to existing methods.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Wiley
ISSN:	0167-7055
Funders:	The Royal Society
Date of First Compliant Deposit:	20 September 2023
Date of Acceptance:	15 June 2023
Last Modified:	15 Nov 2023 16:24
URI:	https://orca.cardiff.ac.uk/id/eprint/162647

Actions (repository staff only)

Edit Item