English

Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning

Computer Vision and Pattern Recognition 2025-11-11 v1

Abstract

Understanding 3D scenes in open-world settings poses fundamental challenges for vision and robotics, particularly due to the limitations of closed-vocabulary supervision and static annotations. To address this, we propose a unified framework for Open-World 3D Scene Graph Generation with Retrieval-Augmented Reasoning, which enables generalizable and interactive 3D scene understanding. Our method integrates Vision-Language Models (VLMs) with retrieval-based reasoning to support multimodal exploration and language-guided interaction. The framework comprises two key components: (1) a dynamic scene graph generation module that detects objects and infers semantic relationships without fixed label sets, and (2) a retrieval-augmented reasoning pipeline that encodes scene graphs into a vector database to support text/image-conditioned queries. We evaluate our method on 3DSSG and Replica benchmarks across four tasks-scene question answering, visual grounding, instance retrieval, and task planning-demonstrating robust generalization and superior performance in diverse environments. Our results highlight the effectiveness of combining open-vocabulary perception with retrieval-based reasoning for scalable 3D scene understanding.

Keywords

Cite

@article{arxiv.2511.05894,
  title  = {Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning},
  author = {Fei Yu and Quan Deng and Shengeng Tang and Yuehua Li and Lechao Cheng},
  journal= {arXiv preprint arXiv:2511.05894},
  year   = {2025}
}

Comments

Accepted by AAAI 2026

R2 v1 2026-07-01T07:27:28.878Z