SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Authors:
- 1 May 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception AgeIEEE Transactions on Robotics, 2016
- Hierarchical Higher-Order Regression Forest Fields: An Application to 3D Indoor Scene Labelling2015
- Supervised Evaluation of Image Segmentation and Object Proposal TechniquesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- SLAM with object discovery, modeling and mapping2014
- Object Partitioning Using Local Convexity2014
- Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images2013
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Boundary Extraction in Natural Images Using Ultrametric Contour Maps2006
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004