Open Access Issue
Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning
Tsinghua Science and Technology 2024, 29 (1): 232-243
Published: 21 August 2023

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.

total 1