Learning-based texture synthesis and automatic inpainting using support vector machines
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11155506
- Type
- D - Journal article
- DOI
-
10.1109/TIE.2018.2866043
- Title of journal
- IEEE Transactions on Industrial Electronics
- Article number
- -
- First page
- 4777
- Volume
- 66
- Issue
- 6
- ISSN
- 0278-0046
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2018
- 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)
-
B - Computational Intelligence
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper explores a parametric method for learning and synthesising 3D surface textures, which significantly reduces the computational cost and required memory and can enable new applications such as mobile systems. It advances the prospect of real-time processing, e.g., in popular lightweight games and mobile applications. This work will be adapted for facial texture generation in an Innovate UK KTP project (Real-time 3D avatar for VR) for mobile applications by Emteq and the University of Portsmouth. The application is ready for submission by April 2021. Contact Emteq CTO, Dr. Charles Nduka, charles@emteq.net
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -