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.
Original language | English |
---|---|
Title of host publication | 2018 IEEE International Conference on Robotics and Automation (ICRA 2018) |
Editors | Peter Corke, Nancy M Amato, Megan Emmons, Yoshihiko Nakamura, Markus Vincze |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 3213-3220 |
Number of pages | 8 |
ISBN (Electronic) | 9781538630815, 9781538630808 |
ISBN (Print) | 9781538630822 |
DOIs | |
Publication status | Published - 2018 |
Externally published | Yes |
Event | IEEE International Conference on Robotics and Automation 2018 - Brisbane Convention & Exhibition Centre, Brisbane, Australia Duration: 21 May 2018 → 25 May 2018 https://icra2018.org/ (Website) https://ieeexplore.ieee.org/xpl/conhome/8449910/proceeding (Proceedings) |
Publication series
Name | Proceedings - IEEE International Conference on Robotics and Automation |
---|---|
Publisher | Institute of Electrical and Electronics Engineers, Inc. |
ISSN (Print) | 1050-4729 |
ISSN (Electronic) | 2577-087X |
Conference
Conference | IEEE International Conference on Robotics and Automation 2018 |
---|---|
Abbreviated title | ICRA 2018 |
Country/Territory | Australia |
City | Brisbane |
Period | 21/05/18 → 25/05/18 |
Internet address |
|