Automatic semantic modeling of indoor scenes from low-quality RGB-D data using contextual information
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 95723115
- Type
- D - Journal article
- DOI
-
10.1145/2661229.2661239
- Title of journal
- ACM Transactions on Graphics
- Article number
- 208
- First page
- -
- Volume
- 33
- Issue
- 6
- ISSN
- 0730-0301
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2014
- URL
-
http://dx.doi.org/10.1145/2661229.2661239
- 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
-
4
- Research group(s)
-
V - Visual computing
- Citation count
- 65
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first robust and fully automatic semantic reconstruction of indoor scenes from poor quality output of cheap depth cameras. It effectively exploits contextual information, significantly reducing the cost and effort for 3D scene reconstruction. The paper was presented at SIGGRAPH Asia 2014 and selected as one of the three Research Highlights in the conference. The work has influenced multiple groups, e.g., researchers at Stanford University have followed the learning approach in their work (https://doi.org/10.1145/2816795.2818057).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -