Learning 3D semantic scene graphs from 3D indoor reconstructions
Wald J, Dhamo H, Navab N, Tombari F (2020)
Publication Type: Conference contribution
Publication year: 2020
Journal
Publisher: IEEE Computer Society
Pages Range: 3960-3969
Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Event location: Virtual, Online, USA
DOI: 10.1109/CVPR42600.2020.00402
Abstract
Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic segmentation and scene layout prediction. In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges. We leverage inference on scene graphs as a way to carry out 3D scene understanding, mapping objects and their relationships. In particular, we propose a learned method that regresses a scene graph from the point cloud of a scene. Our novel architecture is based on PointNet and Graph Convolutional Networks (GCN). In addition, we introduce 3DSSG, a semi-automatically generated dataset, that contains semantically rich scene graphs of 3D scenes. We show the application of our method in a domain-agnostic retrieval task, where graphs serve as an intermediate representation for 3D-3D and 2D-3D matching.
Involved external institutions
Germany (DE)How to cite
APA:
Wald, J., Dhamo, H., Navab, N., & Tombari, F. (2020). Learning 3D semantic scene graphs from 3D indoor reconstructions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 3960-3969). Virtual, Online, USA: IEEE Computer Society.
MLA:
Wald, Johanna, et al. "Learning 3D semantic scene graphs from 3D indoor reconstructions." Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Virtual, Online, USA IEEE Computer Society, 2020. 3960-3969.
BibTeX: Download