发表机构
Queensland University of Technology (QUT); CSIRO（昆士兰科技大学; 澳大利亚联邦科学与工业研究组织）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出OpenSplatGraph框架，从在线高斯语义地图构建持久3D场景图，实现开放词汇物体提取与关系推理，兼顾几何保真与结构化语义。
AI 中文摘要
稠密的三维建图与语义理解对于复杂环境中的机器人感知至关重要。近年来，基于三维高斯泼溅的建图方法能够实现高保真几何重建和高效的开放词汇感知，但通常将语义表示为非结构化的特征场，这限制了以物体为中心的推理能力。相比之下，三维场景图显式地建模物体及其关系以支持结构化推理，但通常基于稀疏的几何表示构建，未能充分利用稠密语义地图。在本工作中，我们提出了OpenSplatGraph，一个统一的框架，直接从在线的基于高斯的开放词汇语义地图构建持久的3D场景图。所提出的框架通过一个可靠性感知的语义场增强稠密语义地图，该语义场维护轻量级的观测统计信息，以实现置信度感知、查询条件下的物体提取。提取的物体实例与持久的图节点关联，使得物体属性和关系能够在多次观测和查询中增量更新。通过将稠密语义建图与持久的以物体为中心的表示紧密耦合，我们的框架同时支持语言引导的物体定位和结构化关系推理，同时保持基于高斯的建图的几何保真度。在标准3D场景理解基准和真实世界机器人实验上的全面评估表明，OpenSplatGraph在在线开放词汇感知和下游机器人任务上取得了具有竞争力的性能。项目页面：https://csiro-robotics.github.io/OpenSplatGraph。
英文摘要
Dense 3D mapping with semantic understanding is essential for robotic perception in complex environments. Recent 3D Gaussian Splatting-based mapping approaches enable high-fidelity geometry and efficient open-vocabulary perception, but typically represent semantics as unstructured feature fields that limit object-centric reasoning. In contrast, 3D scene graphs explicitly model objects and their relationships for structured reasoning, but are commonly constructed from sparse geometric representations that do not fully exploit dense semantic maps. In this work, we present OpenSplatGraph, a unified framework that constructs persistent 3D scene graphs directly from an online Gaussian-based open-vocabulary semantic map. The proposed framework augments the dense semantic map with a reliability-aware semantic field that maintains lightweight observation statistics for confidence-aware, query-conditioned object extraction. Extracted object instances are associated with persistent graph nodes, allowing object attributes and relationships to be incrementally updated across observations and queries. By tightly coupling dense semantic mapping with persistent object-centric representations, our framework supports both language-guided object grounding and structured relational reasoning while preserving the geometric fidelity of Gaussian-based mapping. Comprehensive evaluations on standard 3D scene understanding benchmarks and real-world robotic experiments demonstrate that OpenSplatGraph achieves competitive performance for online open-vocabulary perception and downstream robotic tasks. Project page: https://csiro-robotics.github.io/OpenSplatGraph.
CommentsAccepted to ACCV 2026
