SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
This addresses the limitation of deep learning methods that fail on unseen objects or instance separation in complex indoor scenes for robotics applications.
The paper tackles the problem of jointly discovering unseen objects and non-object surfaces from single RGB-D images in indoor scenes, with results showing SceneCut significantly outperforms all existing methods.
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.