SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation
This addresses the problem of parsing 3D scenes into semantic graphs for applications like robotics and AR/VR, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles 3D scene graph generation from point clouds by proposing SGFormer, which uses Transformer layers for global information passing and incorporates linguistic knowledge from ChatGPT, achieving a 40.94% absolute improvement in relationship prediction's R@50 and an 88.36% boost on complex scenes over state-of-the-art methods.
In this paper, we propose a novel model called SGFormer, Semantic Graph TransFormer for point cloud-based 3D scene graph generation. The task aims to parse a point cloud-based scene into a semantic structural graph, with the core challenge of modeling the complex global structure. Existing methods based on graph convolutional networks (GCNs) suffer from the over-smoothing dilemma and can only propagate information from limited neighboring nodes. In contrast, SGFormer uses Transformer layers as the base building block to allow global information passing, with two types of newly-designed layers tailored for the 3D scene graph generation task. Specifically, we introduce the graph embedding layer to best utilize the global information in graph edges while maintaining comparable computation costs. Furthermore, we propose the semantic injection layer to leverage linguistic knowledge from large-scale language model (i.e., ChatGPT), to enhance objects' visual features. We benchmark our SGFormer on the established 3DSSG dataset and achieve a 40.94% absolute improvement in relationship prediction's R@50 and an 88.36% boost on the subset with complex scenes over the state-of-the-art. Our analyses further show SGFormer's superiority in the long-tail and zero-shot scenarios. Our source code is available at https://github.com/Andy20178/SGFormer.