arXiv：cs.AI· Binh Long Nguyen, Kien Nguyen, Clinton Fookes, Peyman Moghadam·· 6 小时前AI 评分32
OpenSplatGraph：从稠密语义地图到结构化场景图的开放词汇机器人感知框架
OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception
AI 导读
OpenSplatGraph 是一个统一框架，可直接从在线高斯开放词汇语义地图构建持久 3D 场景图，通过引入可靠性感知语义场实现置信度感知、查询条件下的物体提取，并将物体实例关联到持久图节点以增量更新属性与关系。该框架兼顾语言引导的物体定位与结构化关系推理，在标准 3D 场景理解基准和真实机器人实验中取得有竞争力的表现，已被 ACCV 2026 接收。
正文
Abstract: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.
| Comments: | Accepted to ACCV 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.07569 [cs.RO] |
| (or arXiv:2610.07569v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07569 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Binh Long Nguyen [view email]
[v1]
Tue, 6 Oct 2026 00:58:30 UTC (3,768 KB)
来源：arXiv：cs.AI · arxiv.org