Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
By: Fei Yu , Quan Deng , Shengeng Tang and more
Potential Business Impact:
Lets computers understand 3D worlds like humans.
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.
Similar Papers
Open World Scene Graph Generation using Vision Language Models
CV and Pattern Recognition
Lets computers understand pictures without training.
Structured Interfaces for Automated Reasoning with 3D Scene Graphs
CV and Pattern Recognition
Robots understand spoken words by seeing objects.
Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning
CV and Pattern Recognition
Helps computers understand how things work together.