Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation

TL;DR

Point2Graph introduces an end-to-end 3D scene graph generation method from point clouds, eliminating the need for RGB-D images or camera poses, and achieves state-of-the-art results in open-vocabulary scene understanding.

Contribution

The paper presents a novel hierarchical framework that combines geometry-based and learning-based methods for open-vocabulary scene graph generation directly from point clouds.

Findings

Outperforms current SOTA in open-vocabulary room and object segmentation.

Eliminates dependence on RGB-D images and camera pose data.

Provides an end-to-end pipeline for 3D scene understanding from point clouds.

Abstract

Current open-vocabulary scene graph generation algorithms highly rely on both 3D scene point cloud data and posed RGB-D images and thus have limited applications in scenarios where RGB-D images or camera poses are not readily available. To solve this problem, we propose Point2Graph, a novel end-to-end point cloud-based 3D open-vocabulary scene graph generation framework in which the requirement of posed RGB-D image series is eliminated. This hierarchical framework contains room and object detection/segmentation and open-vocabulary classification. For the room layer, we leverage the advantage of merging the geometry-based border detection algorithm with the learning-based region detection to segment rooms and create a "Snap-Lookup" framework for open-vocabulary room classification. In addition, we create an end-to-end pipeline for the object layer to detect and classify 3D objects based solely on 3D point cloud data. Our evaluation results show that our framework can outperform the current state-of-the-art (SOTA) open-vocabulary object and room segmentation and classification algorithm on widely used real-scene datasets.