SDM-NET: deep generative network for structured deformable mesh
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 101415789
- Type
- D - Journal article
- DOI
-
10.1145/3355089.3356488
- Title of journal
- ACM Transactions on Graphics
- Article number
- 243
- First page
- -
- Volume
- 38
- Issue
- 6
- ISSN
- 0730-0301
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2019
- URL
-
http://doi.org/10.1145/3355089.3356488
- 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
-
6
- Research group(s)
-
V - Visual computing
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This collaboration with the Chinese Academy of Sciences, CU Hong Kong and Simon Fraser University proposes a novel deep generative network based on a new structured deformable mesh representation, which for the first time allows the generation of high-quality 3D shapes with flexible structure and fine details. It was presented at SIGGRAPH Asia 2019. The research led to a new international collaboration to develop new techniques based on this (arXiv:2008.05440, provisionally accepted by ACM TOG). The source code and data are available for research purposes, and the paper receives ACM Reproducibility Badge and Graphics Replicability Stamp (http://www.replicabilitystamp.org).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -