Metraipolis › archive › dc_2d31e789d714

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception — arXiv:2610.07569

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07569
License (as archived)
CC0-1.0
Archived
2026-10-07T11:20:51.909Z
SHA-256 of the archived text
06d8ca6d54957b931d265f9535741aec43897a7b6387b8b346e35bc1a014916b
Stable URL of this page
https://metraipolis.com/documento/dc_2d31e789d714

How to cite

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception — arXiv:2610.07569 — arXiv (en), https://arxiv.org/abs/2610.07569 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d31e789d714 (Metraipolis archive dc_2d31e789d714, sha256 06d8ca6d54957b931d265f9535741aec43897a7b6387b8b346e35bc1a014916b)
BibTeX
@misc{dc2d31e789d714,
  title = {OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception — arXiv:2610.07569},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07569},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d31e789d714; sha256 06d8ca6d54957b931d265f9535741aec43897a7b6387b8b346e35bc1a014916b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07569. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.07569 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:15:24.734Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).