Feature-preserving detailed 3D face reconstruction from a single image
- Submitting institution
-
Edinburgh Napier University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1413581
- Type
- E - Conference contribution
- DOI
-
10.1145/3278471.3278473
- Title of conference / published proceedings
- CVMP '18 Proceedings of the 15th ACM SIGGRAPH European Conference on Visual Media Production
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- December
- 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
-
3
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This collaboration with Chinese researchers (Face++) resulted in winning ACM Council Europe’s best paper award (https://www.linkedin.com/pulse/our-detailed-face-reconstruction-from-single-image-wins-mitchell/). Face detail reconstruction is a highly contested challenge in computer vision and this work demonstrates superiority to works held in highest community regard accurately preserving the subject’s identity. The article serves as a model of how to correctly obtain permission and attribute copyright of photographers’ images of personalities. Subsequently a team from Shanghai worked with Mitchell with the outcome being an ICCV journal publication (#1 ranked SJR) on the same topic, developing a data efficient deep learning method.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -