Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces

CVPR 2025

1Tsinghua University 2ETH Zürich 3MPI for Informatics 4Microsoft 5Stanford University


Functional 3D Scene Graphs. Given an input sequence of posed RGB-D frames of an indoor environment, our method predicts a functional 3D scene graph by detecting objects, identifying interactive elements, and inferring functional relationships. This enables the representation of interactions, functions, and scene dynamics, going beyond existing 3D scene graph methods that are constrained to spatial relationships between static objects.

Abstract

We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images. Unlike traditional 3D scene graphs that focus on spatial relationships of objects, functional 3D scene graphs capture objects, interactive elements, and their functional relationships. Due to the lack of training data, we leverage foundation models, including visual language models (VLMs) and large language models (LLMs), to encode functional knowledge. We evaluate our approach on an extended SceneFun3D dataset and a newly collected dataset, FunGraph3D, both annotated with functional 3D scene graphs. Our method significantly outperforms adapted baselines, including Open3DSG and ConceptGraph, demonstrating its effectiveness in modeling complex scene functionalities. We also demonstrate downstream applications such as 3D question answering and robotic manipulation using functional 3D scene graphs.

Qualitative results


Scene interactive elements and their functional relationships between objects are exploited by our approach.




FunGraph3D Dataset


FunGraph3D dataset is constructed with multi-sensor data (i.e., high-fidelity 3D reconstructions, consumer-device video captures, egocentric human-scene interaction videos) and functional 3D scene graph annotations.

High-resolution 3D scan



Static RGB-D sequence



Egocentric human-scene interaction video



Functional 3D scene graph annotations

BibTeX