Bidirectional Edge-Based 3D Scene Graph Generation from Point Clouds

Shan Yang, Ruofan Wang, Lijin Fang, Chule Yang, Yi Yang, Yufeng Yue*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The study of 3D scene understanding is a crucial area in computer vision and has received much attention. While ignoring the relationships between objects, current research on 3D scene understanding mostly focuses on object-level knowledge. In recent years, 3D scene graph has become an effective tool for attaining greater comprehension and perception of the surroundings. However, the long-tailed distribution of the training data causes existing 3D scene graph prediction models to yield sub-optimal scene graphs. In this paper, we provide a straightforward but effective 3D scene graph prediction model. Experiments on the 3DSSG dataset demonstrate that the model described in this research when compared to the baseline model, can increase relationship prediction's effectiveness and accuracy while successfully reducing the long-tailed distribution impact brought on by dataset labeling.

Original languageEnglish
Title of host publicationProceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023
EditorsRong Song
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1714-1719
Number of pages6
ISBN (Electronic)9798350316308
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Unmanned Systems, ICUS 2023 - Hefei, China
Duration: 13 Oct 202315 Oct 2023

Publication series

NameProceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023

Conference

Conference2023 IEEE International Conference on Unmanned Systems, ICUS 2023
Country/TerritoryChina
CityHefei
Period13/10/2315/10/23

Keywords

  • 3D scene graph
  • bidirectional edge
  • point clouds
  • scene understanding

Fingerprint

Dive into the research topics of 'Bidirectional Edge-Based 3D Scene Graph Generation from Point Clouds'. Together they form a unique fingerprint.

Cite this