Metraipolis › archive › dc_281ea2c4d00b

Query-Time Calibration of CLIP Features for Open-Vocabulary 3D Segmentation — arXiv:2610.30908

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30908
License (as archived)
CC0-1.0
Archived
2026-10-25T08:34:42.613Z
SHA-256 of the archived text
68d1c606f5346528b9b4b2376482770d84de93c25e781f33b943a9bb23a89cde
Stable URL of this page
https://metraipolis.com/documento/dc_281ea2c4d00b

How to cite

Query-Time Calibration of CLIP Features for Open-Vocabulary 3D Segmentation — arXiv:2610.30908 — arXiv (en), https://arxiv.org/abs/2610.30908 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_281ea2c4d00b (Metraipolis archive dc_281ea2c4d00b, sha256 68d1c606f5346528b9b4b2376482770d84de93c25e781f33b943a9bb23a89cde)
BibTeX
@misc{dc281ea2c4d00b,
  title = {Query-Time Calibration of CLIP Features for Open-Vocabulary 3D Segmentation — arXiv:2610.30908},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30908},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_281ea2c4d00b; sha256 68d1c606f5346528b9b4b2376482770d84de93c25e781f33b943a9bb23a89cde},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30908. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Lifting vision-language features such as CLIP into 3D Gaussian reconstructions enables open-vocabulary segmentation through natural-language queries. Although CLIP represents a broad range of semantic concepts, the lifted features of individual scenes can exhibit strong directional concentration, while raw cosine similarity does not account for the scene-specific feature distribution. We show that substantial segmentation gains can be obtained by changing how a fixed lifted feature field is compared with text. Our method partially subtracts a shared scene direction from visual features and text prototypes and whitens text prototypes using a fixed reference vocabulary of generic terms. It then uses soft clustering for multiclass prediction and CSLS with a relevance margin against the reference vocabulary for single-query prediction. Beyond reducing directional concentration, scene centering improves class-relative feature separation in every evaluated scene. Across seven lifting methods and four datasets, the resulting query-time calibration consistently improves mean intersection over union in both multiclass and single-query segmentation. These gains require no retraining, source-image re-encoding, or feature re-lifting, demonstrating the value of scene-conditioned comparison for making better use of existing lifted representations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30908 — 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 2026-10-25T08:31:13.199Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).