OnlinePG：基于三维高斯泼溅的在线开放词表全景建图
OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
把 3D 高斯泼溅做成在线增量式全景建图系统：滑动窗口内用几何+语义的 3D 分割聚类图融合碎片实例，再用双向二分图实例匹配把局部高斯图并入全局图，可直接复用到机器人/具身场景的实时开放词表语义地图构建。
原文依据 we employ an efficient local-to-global paradigm with a sliding window
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论面向具身应用的开放词表场景理解与在线全景建图，是感知并与环境交互的关键能力。然而，现有方法大多为离线处理，或缺乏实例级理解，限制了其在真实机器人任务中的适用性。本文提出 OnlinePG，一个新颖且有效的系统，在在线设定下利用三维高斯泼溅将几何重建与开放词表感知相结合。技术上，为实现在线全景建图，我们采用带滑动窗口的高效局部到全局范式。为构建局部一致性地图，我们构建了一个联合利用几何与语义线索的三维片段聚类图，将滑动窗口内不一致的片段融合为完整实例。随后，为更新全局地图，我们为局部三维高斯地图构建显式的空间属性网格，并通过鲁棒的双向二分三维高斯实例匹配将其融合进全局地图。最后，我们利用三维空间属性网格中融合的视觉语言模型特征实现开放词表场景理解。在广泛使用的数据集上的大量实验表明，本方法在在线方法中取得了更优性能，同时保持实时效率。
英文原文摘要 1317 字符
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 spatial attribute grids 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.