Metraipolis › archive › dc_ed97ffc9a90c

Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement — arXiv:2609.27462

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27462
License (as archived)
CC0-1.0
Archived
2026-10-08T12:34:52.043Z
SHA-256 of the archived text
ad60ee7a3b2e2aa9caee9fa9dec39104fb316450e2f48dc85dccdd18345b798f
Stable URL of this page
https://metraipolis.com/documento/dc_ed97ffc9a90c

How to cite

Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement — arXiv:2609.27462 — arXiv (en), https://arxiv.org/abs/2609.27462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed97ffc9a90c (Metraipolis archive dc_ed97ffc9a90c, sha256 ad60ee7a3b2e2aa9caee9fa9dec39104fb316450e2f48dc85dccdd18345b798f)
BibTeX
@misc{dced97ffc9a90c,
  title = {Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement — arXiv:2609.27462},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27462},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed97ffc9a90c; sha256 ad60ee7a3b2e2aa9caee9fa9dec39104fb316450e2f48dc85dccdd18345b798f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-vocabulary 3D segmentation localizes objects from free-form text queries, but remains challenging in real image sequences: incomplete or noisy 2D supervision destabilizes multi-view identity assignment, while full-scene semantic learning weakens object-level discriminability. We introduce Hybrid Gaussians, a unified 3D representation jointly modeling object association and language-aligned semantics. Its Multi-View Object Association mechanism combines Observation Fusion and Semantic Contrastive Learning to improve identity consistency and semantic discrimination. Boundary Reconstruction Optimization further refines local boundary structure to improve contour quality. Experiments on LERF and 3D-OVS demonstrate strong quantitative and qualitative performance. Our method achieves 59.1\% mIoU on LERF, yielding a 13.4\% relative gain over the baseline. Project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.27462 — 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 2026-10-08T12:12:35.685Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).