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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Yirum, Kim, Jaewoo, Kim, Ue-Hwan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915773028499456
author Kim, Yirum
Kim, Jaewoo
Kim, Ue-Hwan
author_facet Kim, Yirum
Kim, Jaewoo
Kim, Ue-Hwan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04152
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
Kim, Yirum
Kim, Jaewoo
Kim, Ue-Hwan
Robotics
Artificial Intelligence
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.
title MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2602.04152