OnlinePG: 在线开放词汇全景映射与3D高斯点云分裂
OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
AI总结：
本文提出OnlinePG，通过在线全景映射结合3D高斯点云分裂实现开放词汇场景理解，解决现有方法在实时性和实例级理解上的不足。
摘要：
开放词汇场景理解需要在线全景映射以支持具身应用感知和交互环境。然而，现有方法多为离线或缺乏实例级理解，限制了其在真实世界机器人任务中的应用。本文提出OnlinePG，一种新颖有效的系统，通过在线设置整合几何重建和开放词汇感知。技术上，为实现在线全景映射，采用高效的局部到全局范式与滑动窗口。构建局部一致性地图时，通过3D段聚类图联合利用几何和语义线索，将滑动窗口内的不一致段融合为完整实例。随后，通过构建具有空间属性的显式网格，将局部3D高斯点云地图融合到全局地图中。最后，利用融合的VLM特征实现开放词汇场景理解。广泛实验表明，本文方法在在线方法中表现更优，同时保持实时效率。
英文摘要：
Open-vocabulary scene understanding with online panoptic mapping is essential for embodied applications to perceive and interact with environments. However, existing methods are predominantly offline or lack instance-level understanding, limiting their applicability to real-world robotic tasks. In this paper, we propose OnlinePG, a novel and effective system that integrates geometric reconstruction and open-vocabulary perception using 3D Gaussian Splatting in an online setting. Technically, to achieve online panoptic mapping, we employ an efficient local-to-global paradigm with a sliding window. To build local consistency map, we construct a 3D segment clustering graph that jointly leverages geometric and semantic cues, fusing inconsistent segments within sliding window into complete instances. Subsequently, to update the global map, we construct explicit grids with spatial attributes for the local 3D Gaussian map and fuse them into the global map via robust bidirectional bipartite 3D Gaussian instance matching. Finally, we utilize the fused VLM features inside the 3D spatial attribute grids to achieve open-vocabulary scene understanding. Extensive experiments on widely used datasets demonstrate that our method achieves better performance among online approaches, while maintaining real-time efficiency.
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。
