mlsanityData to 7 Oct 2026

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

arXiv 2602.04152 ↗First posted 4 Feb 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

35 of 51 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 289
  3. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 280
  4. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  5. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  6. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 187
  7. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 175
  8. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  9. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  10. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  11. 20203D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humanscited by 141
  12. 2020Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphscited by 87
23 more
  1. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 83
  2. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
  3. 20193-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agentscited by 74
  4. 2019GOT: An Optimal Transport framework for Graph comparisoncited by 64
  5. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  6. 2022Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Trainingcited by 56
  7. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  8. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
  9. 2022Continuous Scene Representations for Embodied AIcited by 39
  10. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  11. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  12. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27
  13. 20223D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphscited by 24
  14. 2023Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systemscited by 21
  15. 2023Hydra-Multi: Collaborative Online Construction of 3D Scene Graphs with Multi-Robot Teamscited by 21
  16. 2023Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph predictioncited by 18
  17. 2022maplab 2.0 -- A Modular and Multi-Modal Mapping Frameworkcited by 14
  18. 2024Deep Reinforcement Learning-based Large-scale Robot Explorationcited by 12
  19. 2024SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Taskscited by 10
  20. 2023Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMUcited by 4
  21. 2021Behavioral assessment of a humanoid robot when attracting pedestrians in a mallcited by 2
  22. 2022Multi-domain Cooperative SLAM: The Enabler for Integrated Sensing and Communicationscited by 1
  23. 2023Enabling the Deployment of Any-Scale Robotic Applications in Microservice Architectures through Automated Containerizationcited by 1

Built on by

Not cited yet.