Example-Guided Style-Consistent Image Synthesis from Semantic Labeling
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 203059236
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2019.00159
- Title of conference / published proceedings
- Computer Vision and Pattern Recognition, CVPR 2019
- First page
- 1495
- Volume
- -
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Exception within 3 months of publication
- Month of publication
- January
- Year of publication
- 2020
- URL
-
-
- 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)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Synthesising photographs from (eg) cartoon like pictures is fast becoming an important direction in Visual Computing. Typically, GANs are used, but early work was unconstrained. This work showed how to synthesis so that output is closer to user requirements (eg make a woman not a man). For a young paper, its impact in the academia has been notable. It has been used in Computer Graphics, Computer Vision and Multimedia. Extended to include portraiture, human motion, video, and VR content creation. It has influenced other fields such as style transfer and cross-domain matching.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -