Sparse data driven mesh deformation
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 101415885
- Type
- D - Journal article
- DOI
-
10.1109/TVCG.2019.2941200
- Title of journal
- IEEE Transactions on Visualization and Computer Graphics
- Article number
- -
- First page
- 2085
- Volume
- 27
- Issue
- 3
- ISSN
- 1077-2626
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2019
- URL
-
http://dx.doi.org/10.1109/TVCG.2019.2941200
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
V - Visual computing
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Resulting from a collaboration with the Chinese Academy of Sciences and RWTH Aachen University, this paper proposes an as-consistent-as-possible shape deformation representation and sparsity regularisation for effective, real-time data-driven shape editing. The source code is publicly available (https://github.com/gaolinorange/Automatic-Unpaired-Shape-Deformation-Transfer/tree/master/ACAP_linux). Thanks to its capability to cope with substantial deformations, it has been widely used as the representation for deep learning on 3D deformable shapes, e.g.
for learning human body embedding (https://doi.org/10.1109/TVCG.2020.2988476), disentangled analysis of 3D faces (https://openaccess.thecvf.com/content_CVPR_2019/html/Jiang_Disentangled_Representation_Learning_for_3D_Face_Shape_CVPR_2019_paper.html), and simulation of deformable materials (https://doi.org/10.1109/LRA.2020.2970624). The work was presented at Eurographics Symposium on Geometry Processing 2020.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -