Large pose 3D face reconstruction from a single image via direct volumetric CNN regression
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-05-1339
- Type
- E - Conference contribution
- DOI
-
10.1109/ICCV.2017.117
- Title of conference / published proceedings
- 2017 IEEE International Conference on Computer Vision (ICCV)
- First page
- 1031
- Volume
- -
- Issue
- -
- ISSN
- 2380-7504
- Open access status
- Not compliant
- Month of publication
- -
- Year of publication
- 2017
- 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
-
-
- Research group(s)
-
-
- Citation count
- 84
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduces a novel 3D face reconstruction approach from a single 2D facial image. The proposed method offers a new pipeline overcoming the required multiple stages of morphable models and providing accurate reconstructions even for parts that are not visible. The online demonstrator has received more than 3M model views and the associated open-access software (https://cvl-demos.cs.nott.ac.uk/vrn/ and https://github.com/AaronJackson/vrn) has been awarded over 4200 stars and 700 forks. This research is of interest to security, biometrics, face analysis, augmented reality, special effects for movies, and medical applications, e.g., cosmetic surgeries, as it can reduce dramatically their cost.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -