Roto++: accelerating professional rotoscoping using shape manifolds
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 146393551
- Type
- D - Journal article
- DOI
-
10.1145/2897824.2925973
- Title of journal
- ACM Transactions on Graphics
- Article number
- 62
- First page
- -
- Volume
- 35
- Issue
- 4
- ISSN
- 0730-0301
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2897824.2925973&file=a62.mp4&download=true
- 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)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper marks the first advance in a practical rotoscoping system since Agarwala et al.(2004). The work was informed by discussions with industry end users and was demonstrated to offer a quantitative efficiency improvement of over 30% for typical rotoscoping tasks when used by actual professional artists in a user study. Within the first month of publication, the code was downloaded over 1,600 times and the core technology is being built into industry software from Foundry (world leading post-production software house) and DNeg (academy award winning post-production studio) as part of the Innovate UK SmartRoto project.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -