MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments

TL;DR

This paper introduces MA3DSG, a multi-agent framework for large-scale 3D scene graph generation that overcomes scalability limitations of single-agent methods, using a training-free graph alignment and a new benchmark.

Contribution

We propose the first multi-agent 3D scene graph generation framework with a training-free graph alignment algorithm and a comprehensive benchmark for diverse environments.

Findings

Enables scalable 3DSGG with multiple agents

Achieves effective graph merging without learnable parameters

Provides a versatile benchmark for evaluation

Abstract

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.