A Deep Learning Framework for Character Motion Synthesis and Editing
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 34462366
- Type
- D - Journal article
- DOI
-
10.1145/2897824.2925975
- Title of journal
- ACM Transactions on Graphics
- Article number
- 138
- First page
- -
- Volume
- 35
- Issue
- 4
- ISSN
- 0730-0301
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2016
- 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
-
2
- Research group(s)
-
D - Language, Interaction and Robotics
- Citation count
- 125
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper is presented/published in SIGGRAPH 2016/ACM Transactions on Graphics, which is one of the best conferences/journals in computer science. This is one of the first papers to apply deep learning techniques for character animation, that shows high level user inputs can be mapped to complex full body motion. The code is downloaded by researchers in the world, and has many follow-up researches. Our follow-up work obtained a best student paper award in Pacific Graphics 2018. The paper has led to a Google VR Research Faculty Award (contact: program manager AR/VR) and a keynote talk at CVMP2017.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -