Learning 3D Semantic Scene Graphs with Instance Embeddings
Wald J, Navab N, Tombari F (2022)
Publication Type: Journal article
Publication year: 2022
Journal
Book Volume: 130
Pages Range: 630-651
Journal Issue: 3
DOI: 10.1007/s11263-021-01546-9
Abstract
A 3D scene is more than the geometry and classes of the objects it comprises. An essential aspect beyond object-level perception is the scene context, described as a dense semantic network of interconnected nodes. Scene graphs have become a common representation to encode the semantic richness of images, where nodes in the graph are object entities connected by edges, so-called relationships. Such graphs have been shown to be useful in achieving state-of-the-art performance in image captioning, visual question answering and image generation or editing. While scene graph prediction methods so far focused on images, we propose instead a novel neural network architecture for 3D data, where the aim is to learn to regress semantic graphs from a given 3D scene. With this work, we go beyond object-level perception, by exploring relations between object entities. Our method learns instance embeddings alongside a scene segmentation and is able to predict semantics for object nodes and edges. We leverage 3DSSG, a large scale dataset based on 3RScan that features scene graphs of changing 3D scenes. Finally, we show the effectiveness of graphs as an intermediate representation on a retrieval task.
Involved external institutions
Germany (DE)How to cite
APA:
Wald, J., Navab, N., & Tombari, F. (2022). Learning 3D Semantic Scene Graphs with Instance Embeddings. International Journal of Computer Vision, 130(3), 630-651. https://doi.org/10.1007/s11263-021-01546-9
MLA:
Wald, Johanna, Nassir Navab, and Federico Tombari. "Learning 3D Semantic Scene Graphs with Instance Embeddings." International Journal of Computer Vision 130.3 (2022): 630-651.
BibTeX: Download