Local-to-global mesh saliency
- Submitting institution
-
University of Brighton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7134880
- Type
- D - Journal article
- DOI
-
10.1007/s00371-016-1334-9
- Title of journal
- Visual Computer
- Article number
- -
- First page
- 323
- Volume
- 34
- Issue
- 3
- ISSN
- 0178-2789
- Open access status
- Not compliant
- Month of publication
- November
- 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
-
3
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Detecting what is salient in a 3D model is a problem that has multiple applications in computer graphics, including shape analysis and automatically generating good renderings of the 3D shape. This paper is significant because it proposes an algorithm which combines global and local mesh saliency to improve the agreement with the human perception of the 3D shape. The research has been used as a baseline for 3D model saliency detection approaches (Leal et al., DYNA 2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -