MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
This work addresses the problem of limited scalability in 3D scene graph generation for real-world scenarios, providing a foundational approach for multi-agent systems in this domain.
The paper tackles the scalability challenge of 3D scene graph generation in large-scale indoor environments by introducing the MA3DSG model, which uses multiple agents and a training-free graph alignment algorithm to merge partial graphs into a unified global scene graph, enabling collaborative operation without learnable parameters.
Current 3D scene graph generation (3DSGG) approaches heavily rely on a single-agent assumption and small-scale environments, exhibiting limited scalability to real-world scenarios. In this work, we introduce Multi-Agent 3D Scene Graph Generation (MA3DSG) model, the first framework designed to tackle this scalability challenge using multiple agents. We develop a training-free graph alignment algorithm that efficiently merges partial query graphs from individual agents into a unified global scene graph. Leveraging extensive analysis and empirical insights, our approach enables conventional single-agent systems to operate collaboratively without requiring any learnable parameters. To rigorously evaluate 3DSGG performance, we propose MA3DSG-Bench-a benchmark that supports diverse agent configurations, domain sizes, and environmental conditions-providing a more general and extensible evaluation framework. This work lays a solid foundation for scalable, multi-agent 3DSGG research.