Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2013.8
DC FieldValue
dc.title3D-based reasoning with blocks, support, and stability
dc.contributor.authorJia Z.
dc.contributor.authorGallagher A.
dc.contributor.authorSaxena A.
dc.contributor.authorChen T.
dc.date.accessioned2018-08-21T04:55:42Z
dc.date.available2018-08-21T04:55:42Z
dc.date.issued2013
dc.identifier.citationJia Z., Gallagher A., Saxena A., Chen T. (2013). 3D-based reasoning with blocks, support, and stability. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 1-8. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2013.8
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/146097
dc.description.abstract3D volumetric reasoning is important for truly understanding a scene. Humans are able to both segment each object in an image, and perceive a rich 3D interpretation of the scene, e.g., the space an object occupies, which objects support other objects, and which objects would, if moved, cause other objects to fall. We propose a new approach for parsing RGB-D images using 3D block units for volumetric reasoning. The algorithm fits image segments with 3D blocks, and iteratively evaluates the scene based on block interaction properties. We produce a 3D representation of the scene based on jointly optimizing over segmentations, block fitting, supporting relations, and object stability. Our algorithm incorporates the intuition that a good 3D representation of the scene is the one that fits the data well, and is a stable, self-supporting (i.e., one that does not topple) arrangement of objects. We experiment on several datasets including controlled and real indoor scenarios. Results show that our stability-reasoning framework improves RGB-D segmentation and scene volumetric representation.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentOFFICE OF THE PROVOST
dc.contributor.departmentDEPT OF COMPUTER SCIENCE
dc.description.doi10.1109/CVPR.2013.8
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.page1-8
dc.description.codenPIVRE
dc.published.statepublished
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

75
checked on Nov 21, 2021

WEB OF SCIENCETM
Citations

59
checked on Oct 4, 2021

Page view(s)

48
checked on Nov 18, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.