On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments

arXiv:2404.13842v1 Announce Type: new
Abstract: Over the years, scene understanding has attracted a growing interest in computer vision, providing the semantic and physical scene information necessary for robots to complete some particular tasks autonomously. In 3D scenes, rich spatial geometric and topological information are often ignored by RGB-based approaches for scene understanding. In this study, we develop a bottom-up approach for scene understanding that infers support relations between objects from a point cloud. Our approach utilizes the spatial topology information …

3d scenes abstract arxiv cloud computer computer vision construction cs.cg cs.cv environments graph inference information relations robots semantic spatial support tasks type understanding vision