SG-Reg：具备泛化性的高效场景图配准方法
SG-Reg: Generalizable and Efficient Scene Graph Registration
AI总结：
针对现有场景图配准依赖手工描述子或真值标注的问题，提出融合多模态特征的SG-Reg方法，采用从粗到细匹配与鲁棒位姿估计，在双智能体SLAM基准上性能更优且通信带宽需求更低。
摘要：
本文致力于解决两个刚性语义场景图的配准难题——这是自主智能体将自身地图与远端智能体地图、或与先验地图配准时的核心能力。经典语义辅助配准依赖手工设计的描述子，而基于学习的场景图配准依赖真值标注，二者的缺陷都阻碍了其在真实环境中的实际应用。为应对上述挑战，我们设计了一种场景图网络，用于编码语义节点的多模态特征：开放集语义特征、具备空间感知的局部拓扑特征以及形状特征，并将这些模态融合生成紧凑的语义节点特征。匹配层随后以从粗到细的方式搜索对应关系。后端部分，我们采用鲁棒位姿估计器，根据匹配对应关系计算变换矩阵。我们成功维持了稀疏且分层的场景表示，在多智能体任务中，该方法所需GPU资源更少，通信带宽更低。此外，我们设计了一种全新的数据生成方法，利用视觉基础模型和语义建图模块重建语义场景图，这与以往依赖真值语义标注生成数据的工作存在显著差异。我们在双智能体SLAM基准上验证了所提方法，其配准成功率显著优于手工设计的基线方法。与视觉回环检测网络相比，我们的方法配准召回率略高，且每帧查询仅需52KB通信带宽。代码已开源至：http://github.com/HKUST-Aerial-Robotics/SG-Reg。
英文摘要：
This paper addresses the challenges of registering two rigid semantic scene graphs, an essential capability when an autonomous agent needs to register its map against a remote agent, or against a prior map. The hand-crafted descriptors in classical semantic-aided registration, or the ground-truth annotation reliance in learning-based scene graph registration, impede their application in practical real-world environments. To address the challenges, we design a scene graph network to encode multiple modalities of semantic nodes: open-set semantic feature, local topology with spatial awareness, and shape feature. These modalities are fused to create compact semantic node features. The matching layers then search for correspondences in a coarse-to-fine manner. In the back-end, we employ a robust pose estimator to decide transformation according to the correspondences. We manage to maintain a sparse and hierarchical scene representation. Our approach demands fewer GPU resources and fewer communication bandwidth in multi-agent tasks. Moreover, we design a new data generation approach using vision foundation models and a semantic mapping module to reconstruct semantic scene graphs. It differs significantly from previous works, which rely on ground-truth semantic annotations to generate data. We validate our method in a two-agent SLAM benchmark. It significantly outperforms the hand-crafted baseline in terms of registration success rate. Compared to visual loop closure networks, our method achieves a slightly higher registration recall while requiring only 52 KB of communication bandwidth for each query frame. Code available at: \href{http://github.com/HKUST-Aerial-Robotics/SG-Reg}{http://github.com/HKUST-Aerial-Robotics/SG-Reg}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
