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.
@article{arxiv.2004.03967,
title = {Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions},
author = {Johanna Wald and Helisa Dhamo and Nassir Navab and Federico Tombari},
journal= {arXiv preprint arXiv:2004.03967},
year = {2020}
}
Comments
first two authors contributed equally, CVPR 2020, video https://youtu.be/8D3HjYf6cYw