SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4035-4043
DOI: 10.1609/aaai.v38i5.28197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Changsheng Lv und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Lv, C., Qi, M., Li, X., Yang, Z., & Ma, H. (2024). SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4035-4043. https://doi.org/10.1609/aaai.v38i5.28197
Vancouver
Lv C, Qi M, Li X, Yang Z, Ma H. SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4035-4043. doi:10.1609/aaai.v38i5.28197
BibTeX
@article{Lv2024,
author = {Lv, Changsheng and Qi, Mengshi and Li, Xia and Yang, Zhengyuan and Ma, Huadong},
title = {SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {5},
pages = {4035--4043},
doi = {10.1609/aaai.v38i5.28197}
}
EUVIMED