Metraipolis › archive › dc_27e348556bfa
Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding — arXiv:2608.21136
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21136
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:56:19.215Z
- SHA-256 of the archived text
68d4852283f4ae3d232d4cbe2ad22744f148a30b0c500db491284b6d732e2f82- Stable URL of this page
https://metraipolis.com/documento/dc_27e348556bfa
How to cite
Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding — arXiv:2608.21136 — arXiv (en), https://arxiv.org/abs/2608.21136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27e348556bfa (Metraipolis archive dc_27e348556bfa, sha256 68d4852283f4ae3d232d4cbe2ad22744f148a30b0c500db491284b6d732e2f82)
BibTeX
@misc{dc27e348556bfa,
title = {Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding — arXiv:2608.21136},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21136},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27e348556bfa; sha256 68d4852283f4ae3d232d4cbe2ad22744f148a30b0c500db491284b6d732e2f82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supervised methods. However, deploying these models in real-world scenarios is severely hindered by their inability to efficiently handle streaming RGB-D inputs and their inherent vulnerability to noise 2D segmentation masks. To address these critical limitations, we propose Stream3Dv2, a novel training-free framework designed for robust streaming 3D perception. Stream3Dv2 processes sequential data through an original nested local-to-historical architecture, capturing multi-view consistency while circumventing the high computational overhead so as to support timely responses. At its core, we introduce a comprehensive geometric-semantic fusion mechanism that resolves geometric noise and semantic ambiguity by explicitly utilizing semantic guidance and formulating 3D segmentation as solving point-and-set merging and partitioning problems. Furthermore, we present an innovative manifold-distance-based point cloud refinement strategy. This approach leverages local manifold graphs for point-to-manifold optimization that mitigates the boundary delineation failures caused by Euclidean-distance metrics, and employs geometric bounding boxes to dynamically activate and update historical instances for achieving rapid manifold-to-manifold refinement. Extensive experiments on public datasets demonstrate that Stream3Dv2 consistently outperforms existing baselines in foundational open-vocabulary streaming 3D segmentation and detection. Finally, we show that integrating our framework with an LLM-based agent enables advanced language-driven 3D scene understanding, underscoring its potential for open-world embodied intelligence. Code will be updated at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.21136 — 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 2026-10-18T10:48:13.599Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).