Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: SceneCut: joint geometric and object segmentation for indoor scenes
Author: Pham, T.
Do, T.
Sunderhauf, N.
Reid, I.
Citation: 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018 / pp.3213-3220
Publisher: IEEE
Issue Date: 2018
Series/Report no.: Piscataway, NJ.
ISBN: 1538630818
ISSN: 1050-4729
Conference Name: IEEE International Conference on Robotics and Automation (ICRA) (21 May 2018 - 25 May 2018 : Brisbane, Australia)
Statement of
Trung T. Pham, Thanh-Toan Do, Niko Sünderhauf, Ian Reid
Abstract: This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep learning-based methods either fail to separate object instances, or fail to detect objects that were not seen during training. SceneCut automatically decomposes a scene into meaningful regions which either represent objects or scene surfaces. The decomposition is qualified by an unified energy function over objectness and geometric fitting. We show how this energy function can be optimized efficiently by utilizing hierarchical segmentation trees. Moreover, we leverage a pre-trained convolutional oriented boundary network to predict accurate boundaries from images, which are used to construct high-quality region hierarchies. We evaluate SceneCut on several different indoor environments, and the results show that SceneCut significantly outperforms all the existing methods.
Rights: ©2018 IEEE
RMID: 0030111876
DOI: 10.1109/ICRA.2018.8461108
Grant ID:
Appears in Collections:Computer Science publications

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

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