Efficient and flexible deformation representation for data-driven surface modeling
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96598394
- Type
- D - Journal article
- DOI
-
10.1145/2908736
- Title of journal
- ACM Transactions on Graphics
- Article number
- 158
- First page
- -
- Volume
- 35
- Issue
- 5
- ISSN
- 0730-0301
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2016
- URL
-
https://doi.org/10.1145/2908736
- 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
-
4
- Research group(s)
-
V - Visual computing
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work was highlighted on the cover of ACM Transactions on Graphics journal (https://dl.acm.org/doi/10.1145/2908736) and presented at ACM SIGGRAPH 2016. Through collaboration with the Chinese Academy of Sciences (CAS) and Tsinghua University, it presents a new rotation invariant mesh deformation representation that eliminates global rotations, which handles extremely large-scale rotations and supports both interpolation and extrapolation. It was used as an effective deformation representation for deep generative models for 3D meshes (https://openaccess.thecvf.com/content_cvpr_2018/html/Tan_Variational_Autoencoders_for_CVPR_2018_paper.html) and 3D caricature generation (https://openaccess.thecvf.com/content_cvpr_2018/html/Wu_Alive_Caricature_From_CVPR_2018_paper.html). It provided the research basis that led to a Royal Society Newton Mobility Grant with CAS (IE150731) and a Newton Advanced Fellowship (NAF\R2\192151).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
