Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107977
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Hierarchical higher-order regression forest fields: an application to 3D indoor scene labelling
Author: Pham, T.
Reid, I.
Latif, Y.
Gould, S.
Citation: Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015 / vol.2015 International Conference on Computer Vision, ICCV 2015, pp.2246-2254
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE International Conference on Computer Vision
ISBN: 9781467383912
ISSN: 1550-5499
Conference Name: 2015 IEEE International Conference on Computer Vision (ICCV 2015) (07 Dec 2015 - 13 Dec 2015 : Santiago, CHILE)
Statement of
Responsibility: 
Trung T. Pham, Ian Reid, Yasir Latif, Stephen Gould
Abstract: This paper addresses the problem of semantic segmentation of 3D indoor scenes reconstructed from RGB-D images. Traditionally label prediction for 3D points is tackled by employing graphical models that capture scene features and complex relations between different class labels. However, the existing work is restricted to pairwise conditional random fields, which are insufficient when encoding rich scene context. In this work we propose models with higher-order potentials to describe complex relational information from the 3D scenes. Specifically, we relax the labelling problem to a regression, and generalize the higher-order associative Pn Potts model to a new family of arbitrary higherorder models based on regression forests. We show that these models, like the robust Pn models, can still be decomposed into the sum of pairwise terms by introducing auxiliary variables. Moreover, our proposed higher-order models also permit extension to hierarchical random fields, which allows for the integration of scene context and features computed at different scales. Our potential functions are constructed based on regression forests encoding Gaussian densities that admit efficient inference. The parameters of our model are learned from training data using a structured learning approach. Results on two datasets show clear improvements over current state-of-the-art methods.
Keywords: Three-dimensional displays, labeling, semantics, solid modeling, computational modeling, robustness, context modeling
Rights: © 2015 IEEE
RMID: 0030049442
DOI: 10.1109/ICCV.2015.259
Grant ID: http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FL130100102
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107977.pdfRestricted Access1.22 MBAdobe PDFView/Open


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