arXiv 2603.163012026-03-18cs.RO

OGScene3D: 增量式开放词汇3D高斯场景图映射用于场景理解

OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding

Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）；University of Technology Nuremberg（纽伦堡技术大学）；Nanyang Technological University（南洋理工大学）；Department of Automation, Key Laboratory of System Control and Information Processing of Ministry of Education, State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University（自动化系，教育部系统控制与信息处理重点实验室，航空系统集成与航空系统-of-系统综合国家重点实验室，上海导航与定位基于服务重点实验室，上海交通大学）

Siting Zhu, Ziyun Lu, Guangming Wang, Chenguang Huang, Yongbo Chen, I-Ming Chen, Wolfram Burgard, Hesheng Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

OGScene3D通过增量式3D高斯场景图映射，实现开放词汇场景理解，结合高斯表示与层次优化策略，提升语义一致性与长期优化能力。

摘要：

开放词汇场景理解对机器人应用至关重要，使机器人能理解复杂3D环境并支持导航与操作等任务。然而，现有方法需预建完整3D语义地图才能构建场景图，限制了机器人探索环境时的应用。为此，我们提出OGScene3D系统，实现增量式3D语义映射与场景图构建。系统采用基于置信度的高斯语义表示，联合建模语义预测与可靠性，实现稳健的场景建模。在此基础上，引入层次3D语义优化策略，通过局部对应建立与全局细化实现语义一致性。此外，设计长期全局优化方法，利用历史观测的时序记忆增强语义预测。通过整合2D-3D语义一致性与高斯渲染贡献，该方法持续优化整个场景的语义理解。进一步开发渐进图构建方法，动态创建与更新节点及语义关系，实现3D场景图的连续更新。在广泛使用的数据集和真实场景上的实验验证了OGScene3D在开放词汇场景理解中的有效性。

英文摘要：

Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods require pre-built complete 3D semantic maps to construct scene graphs for scene understanding, which limits their applicability in robotic scenarios where environments are explored incrementally. To address this challenge, we propose OGScene3D, an open-vocabulary scene understanding system that achieves accurate 3D semantic mapping and scene graph construction incrementally. Our system employs a confidence-based Gaussian semantic representation that jointly models semantic predictions and their reliability, enabling robust scene modeling. Building on this representation, we introduce a hierarchical 3D semantic optimization strategy that achieves semantic consistency through local correspondence establishment and global refinement, thereby constructing globally consistent semantic maps. Moreover, we design a long-term global optimization method that leverages temporal memory of historical observations to enhance semantic predictions. By integrating 2D-3D semantic consistency with Gaussian rendering contribution, this method continuously refines the semantic understanding of the entire scene. Furthermore, we develop a progressive graph construction approach that dynamically creates and updates both nodes and semantic relationships, allowing continuous updating of the 3D scene graphs. Extensive experiments on widely used datasets and real-world scenes demonstrate the effectiveness of our OGScene3D on open-vocabulary scene understanding.

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。