Line drawings for face portraits from photos using global and local structure based GANs
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 106590662
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2020.2987931
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 0
- Volume
- 0
- Issue
- -
- ISSN
- 0162-8828
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2020
- URL
-
http://dx.doi.org/10.1109/TPAMI.2020.2987931
- 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
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper proposes a learning-based approach to generating delicate line drawings for face portraits from photos (which is challenging due to their highly abstract nature). An app based on the technique (as a mini-program on the WeChat platform) received 400K user clicks in 2 weeks of release and source code and data are publicly available (https://github.com/yiranran/APDrawingGAN2). The work is an extension of a conference paper presented at CVPR 2019 selected for oral presentation (5.6% acceptance rate) and was funded by a Royal Society Newton Advanced Fellowship (NA150431).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -