Skip navigation
Skip navigation

Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference

Zhuo, Wei; Salzmann, Mathieu; He, Xuming; Miaomiao, Liu

Description

Over the years, indoor scene parsing has attracted a growing interest in the computer vision community. Existing methods have typically focused on diverse subtasks of this challenging problem. In particular, while some of them aim at segmenting the image into regions, such as object instances, others aim at inferring the semantic labels of given regions, or their support relationships. These different tasks are typically treated as separate ones. However, they bear strong connections: good...[Show more]

dc.contributor.authorZhuo, Wei
dc.contributor.authorSalzmann, Mathieu
dc.contributor.authorHe, Xuming
dc.contributor.authorMiaomiao, Liu
dc.date.accessioned2017-12-21T23:45:41Z
dc.date.available2017-12-21T23:45:41Z
dc.identifier.urihttp://hdl.handle.net/1885/139037
dc.description.abstractOver the years, indoor scene parsing has attracted a growing interest in the computer vision community. Existing methods have typically focused on diverse subtasks of this challenging problem. In particular, while some of them aim at segmenting the image into regions, such as object instances, others aim at inferring the semantic labels of given regions, or their support relationships. These different tasks are typically treated as separate ones. However, they bear strong connections: good regions should respect the semantic labels; support can only be defined for meaningful regions; support relationships strongly depend on semantics. In this paper, we, therefore, introduce an approach to jointly segment the object instances and infer their semantic labels and support relationships from a single input image. By exploiting a hierarchical segmentation, we formulate our problem as that of jointly finding the regions in the hierarchy that correspond to instances and estimating their class labels and pairwise support relationships. We express this via a Markov Random Field, which allows us to further encode links between the different types of variables. Inference in this model can be done exactly via integer linear programming, and we learn its parameters in a structural SVM framework. Our experiments on NYUv2 demonstrate the benefits of reasoning jointly about all these subtasks of indoor scene parsing.
dc.description.sponsorshipChinese Scholarship Council; CSIRO-Data61;
dc.format.mimetypeapplication/pdf
dc.publisherConference on Computer Vision and Pattern Recognition, 2017
dc.rights© 2017 IEEE. The publisher permission to archive the version was granted via email in 2014.
dc.source.urihttp://openaccess.thecvf.com/content_cvpr_2017/papers/Zhuo_Indoor_Scene_Parsing_CVPR_2017_paper.pdf
dc.subjectIndoor Scene
dc.subjectInstance Segmentation
dc.subjectSemantic Labelling
dc.subjectSupport Relationship Inference
dc.titleIndoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference
dc.typeConference paper
dc.date.issued2017-07
local.type.statusAccepted Version
local.contributor.affiliationZhuo, W., ANU College of Engineering & Computer Science, The Australian National University
local.contributor.affiliationHe, Xuming, ANU College of Engineering & Computer Science, The Australian National University
local.contributor.affiliationLiu, Miaomiao, ANU College of Engineering & Computer Science, The Australian National University
local.identifier.doi10.1109/CVPR.2017.664
dcterms.accessRightsOpen Access
CollectionsANU Research Publications

Download

File Description SizeFormat Image
cvpr2017_Zhuo_Mathieu_He_Liu.pdf2.84 MBAdobe PDFThumbnail


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

Updated:  22 January 2019/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator