首页|Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning

Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existing point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual annotation.To address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given structures.Specifically,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point cloud.Besides,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different granularity.It dynamically splits and merges point groups,resulting in a scene graph with high precision.Experiments show that our methods outperform other baseline methods.They output reliable graphs describing the object-level relationships without additional manual labeled data.

scene graph generationstructural representationpoint cloud

Chao Qi、Jianqin Yin、Zhicheng Zhang、Jin Tang

展开 >

School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China

Standard and Metrology Research Institute,China Academy of Railway Sciences Corporation Limited,Beijing 100081,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaFundamental Research Funds for the Central UniversitiesBUPT Excellent PhD Students Foundation

62173045616731922020XD-A04-2CX2021222

2024

10.26599/TST.2023.9010002

清华大学学报自然科学版(英文版)
清华大学

清华大学学报自然科学版(英文版)

CSTPCDEI
影响因子：0.474
ISSN：1007-0214
年,卷(期)：2024.29(1)
  • 34