基于自回归扩散的3D场景图中高层概念生成

中文摘要 AI 辅助

室内3D场景图（3DSG）将环境表示为多层层级结构，连接观测到的几何基元（如平面）与高层度量语义概念（如房间、楼层、建筑物），支持机器人感知与同步定位与建图（SLAM）的增量空间推理。然而，传统高层概念生成方法依赖针对特定概念类别的手工规则，而基于学习的方法需为图结构与空间节点特征（如质心）分别构建模型，这限制了其对新类别及更复杂层级的可扩展性。我们提出一种统一的基于自回归扩散的图生成模型，联合学习结构与特征，从观测到的垂直平面自底向上构建任意层级深度的完整3DSG。在涵盖合成场景、真实建筑平面图及机器人传感器数据、布局复杂度与层级深度各异的3DSG数据集上，我们的方法始终优于所有基于学习的基线与随机基线，且在最大层级及真实单层数据上，优于可获取目标图大小先验的单样本模型。最后，我们提出融合格罗莫夫-瓦瑟斯坦距离（Fused Gromov--Wasserstein distance）的适配方案，用于对生成的3DSG与真实值进行原则性的图级评估。

英文摘要

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.

发表机构

• University of Luxembourg（卢森堡大学）
• University of Padova（帕多瓦大学）
• Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
• Faculty of Science, Technology and Medicine（科学、技术与医学学院）

机构由 AI 辅助整理，请以论文原文为准。