Metraipolis › archive › dc_f750bf0ff951

Training-Free Target-Aware Refinement of 3D Gaussian Language Map — arXiv:2610.21619

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21619
License (as archived)
CC0-1.0
Archived
2026-10-16T10:39:41.615Z
SHA-256 of the archived text
786e3826745d097d66b0db08068c5a19834f73ee352827daa619b5a73a48b401
Stable URL of this page
https://metraipolis.com/documento/dc_f750bf0ff951

How to cite

Training-Free Target-Aware Refinement of 3D Gaussian Language Map — arXiv:2610.21619 — arXiv (en), https://arxiv.org/abs/2610.21619 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f750bf0ff951 (Metraipolis archive dc_f750bf0ff951, sha256 786e3826745d097d66b0db08068c5a19834f73ee352827daa619b5a73a48b401)
BibTeX
@misc{dcf750bf0ff951,
  title = {Training-Free Target-Aware Refinement of 3D Gaussian Language Map — arXiv:2610.21619},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21619},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f750bf0ff951; sha256 786e3826745d097d66b0db08068c5a19834f73ee352827daa619b5a73a48b401},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21619. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distilling vision-language features into 3D Gaussian Splatting yields a language map that can be queried with arbitrary text. In deployment, however, a small set of user-specified targets must be reliably located, which current distilled maps often miss, while open-vocabulary queryability for other words must remain intact. We propose a training-free, target-aware refinement of an already-distilled language map. Guided by a text-promptable segmenter, the visual embedding inside each detected target region is blended with the target text embedding, a convex combination whose coefficient sets the amount of injected prior, while non-target regions are left untouched. Injecting too much overwrites appearance cues and general queryability, so we seek, for each target, the smallest coefficient that still lets it win, and we obtain every coefficient in closed form, leaving no hyperparameters to tune. We further identify a failure mode of injection in language-goal localization. Text embeddings share a common component, and injecting them makes the standard cosine read-out query-agnostic, which a centering step in the read-out removes. Across three benchmarks, the refinement consistently improves open-vocabulary segmentation, roughly doubling the base mIoU on Replica, and localizes language goals more reliably than the base map. It also transfers as a plug-in to off-the-shelf field-based and object-level language maps and supports a real-world demonstration in which a legged robot navigates to natural-language goals. Project page and code: this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21619 — 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 2026-10-16T08:52:02.767Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).