Generation of High-Level Concepts in 3D Scene Graphs via Autoregressive Diffusion

2026-08-28

AI Summary

本文提出一种基于自回归扩散的图生成模型，用于从观测到的垂直平面自下而上构建3D场景图，解决了现有方法在生成高级概念时对特定规则和单独模型依赖的问题。

Abstract

Indoor 3D Scene Graphs (3DSGs) represent environments as multi-layer hierarchies that connect observed geometric primitives (e.g., planes) to higher-level metric-semantic concepts (e.g., rooms, floors, buildings), enabling incremental spatial reasoning for robotic perception and SLAM. However, classical high-level concept generation approaches rely on hand-crafted rules for specific concept classes, while learning-based methods require separate models for graph structure and spatial node features (e.g., centroids), which limits scalability to novel classes and more complex hierarchies. We propose a unified autoregressive diffusion-based graph generative model that jointly learns structure and features, constructing complete 3DSGs bottom-up from observed vertical planes across arbitrary hierarchy depths. Our method consistently surpasses all learning-based and random baselines across 3DSG datasets spanning synthetic scenes, real architectural floor plans, and robotic sensor data, with varying layout complexity and hierarchy depth, and surpasses a one-shot model with oracle access to the target graph size on the largest hierarchy and on real single-floor data. Finally, we propose an adaptation of the Fused Gromov--Wasserstein distance for principled graph-level evaluation of generated 3DSGs against ground truth.

Problem

• 3D Scene Graphs
• High-Level Concepts
• Autoregressive Diffusion
• Graph Generative Model
• Spatial Reasoning

Innovation

• autoregressive diffusion
• unified generative model
• 3D Scene Graphs
• bottom-up construction
• Fused Gromov--Wasserstein distance