.png){kind=icon}
Return
Learning 3D Semantic Scene Graphs with Instance Embeddings
.png){kind=icon}
OA
AI
DOI：10.1007/s11263-021-01546-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Scene graphs
3D scene understanding
Semantic segmentation
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSave
View more