arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.10484cs.CVcs.RO
收藏

OpenSGA: 在开放世界中高效的3D场景图对齐

OpenSGA: Efficient 3D Scene Graph Alignment in the Open World

Autonomous Multi-Robots Lab, Department of Cognitive Robotics, School of Mechanical Engineering, Delft University of Technology, 2628 CD, Delft, Netherlands(代尔夫特理工大学机械工程学院认知机器人学系自主多机器人实验室);Mobile Robotics Lab, School of Computation, Information and Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院移动机器人实验室)

Gang Chen, Sebastián Barbas Laina, Stefan Leutenegger, Javier Alonso-Mora

AI总结:

本文提出OpenSGA框架,通过融合视觉-语言、文本和几何特征实现高效的3D场景图对齐,包含空间注意力编码器、最小成本流分配器和全局场景嵌入生成器模块,实验表明在F2S和S2S任务中表现最佳。

摘要:

场景图对齐在两个部分重叠的观测中建立物体对应关系,使机器人 revisit 地点时能高效理解场景和物体级重定位,并实现多智能体的全局地图融合。现有方法主要关注子扫描到子扫描(S2S)对齐,依赖几何点云特征,忽视了帧到扫描(F2S)对齐和开放集视觉-语言特征。此外,现有场景图对齐数据集规模小,限制了系统训练和评估。本文提出统一且高效的场景图对齐框架,通过融合视觉-语言、文本和几何特征与空间上下文预测物体对应关系。框架包含距离门控空间注意力编码器、基于最小成本流的分配器和全局场景嵌入生成器模块,以在大坐标差异下实现准确对齐。我们进一步引入ScanNet-SG,一个大规模数据集,通过自动化标注管道生成超过70万样本,涵盖509个ScanNet标签对象类别和3000多个GPT-4o基于的标签类别。实验表明,我们的方法在F2S和S2S任务中均取得最佳整体性能,显著优于现有场景图对齐方法。我们的代码和数据集发布于:https://autonomousrobots.nl/paper_websites/opensga.

英文摘要:

Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding and object-level relocalization when a robot revisits a place, as well as global map fusion across multiple agents. Such capabilities are essential for robots that require long-term memory for long-horizon tasks involving interactions with the environment. Existing approaches mainly focus on subscan-to-subscan (S2S) alignment and depend heavily on geometric point-cloud features, leaving frame-to-scan (F2S) alignment and open-set vision-language features underexplored. In addition, existing datasets for scene graph alignment remain small-scale with limited object diversity, constraining systematic training and evaluation. We present a unified and efficient scene graph alignment framework that predicts object correspondences by fusing vision-language, textual, and geometric features with spatial context. The framework comprises modules such as a distance-gated spatial attention encoder, a minimum-cost-flow-based allocator, and a global scene embedding generator to achieve accurate alignment even under large coordinate discrepancies. We further introduce ScanNet-SG, a large-scale dataset generated via an automated annotation pipeline with over 700k samples, covering 509 object categories from ScanNet labels and over 3k categories from GPT-4o-based tagging. Experiments show that our method achieves the best overall performance on both F2S and S2S tasks, substantially outperforming existing scene graph alignment methods. Our code and dataset are released at: https://autonomousrobots.nl/paper_websites/opensga.

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。

↑