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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Fei, Deng, Quan, Tang, Shengeng, Li, Yuehua, Cheng, Lechao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908638554095616
author Yu, Fei
Deng, Quan
Tang, Shengeng
Li, Yuehua
Cheng, Lechao
author_facet Yu, Fei
Deng, Quan
Tang, Shengeng
Li, Yuehua
Cheng, Lechao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
Yu, Fei
Deng, Quan
Tang, Shengeng
Li, Yuehua
Cheng, Lechao
Computer Vision and Pattern Recognition
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.
title Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.05894