Metraipolis › archive › dc_00edfff9cfaa

Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization — arXiv:2610.41373

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41373
License (as archived)
CC0-1.0
Archived
2026-11-02T05:03:39.229Z
SHA-256 of the archived text
66caf99846257072f5887093567e13e9f296270163ba2a1f71a7af06012a4242
Stable URL of this page
https://metraipolis.com/documento/dc_00edfff9cfaa

How to cite

Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization — arXiv:2610.41373 — arXiv (en), https://arxiv.org/abs/2610.41373 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00edfff9cfaa (Metraipolis archive dc_00edfff9cfaa, sha256 66caf99846257072f5887093567e13e9f296270163ba2a1f71a7af06012a4242)
BibTeX
@misc{dc00edfff9cfaa,
  title = {Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization — arXiv:2610.41373},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41373},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00edfff9cfaa; sha256 66caf99846257072f5887093567e13e9f296270163ba2a1f71a7af06012a4242},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41373. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Queryable Gaussian View Index (QGVI) for querying existing Gaussian scene assets and their associated calibrated reference data. Text-view retrieval and selective RGB camera localization return poses in the asset's coordinate frame. QGVI-T turns Gaussian-rendered views into a language-searchable index of scene locations, binding structured captions to known camera poses and place identifiers. Semantic and lexical retrieval select views from distinct places without online rendering, VLM calls, or a scene-specific pose network. The image route, QGVI-I, filters LoGS-based geometric estimates using distinct inlier query keypoints. It omits photometric refinement and preserves accepted pose coordinates. On nine development scenes, QGVI-T achieves 58.3% Top-1 and 78.3% Top-5 joint relevance-and-validity success, compared with 26.1% and 34.6% for our CityLoC reimplementation with refinement. QGVI-I achieves 97.3% scene-mean pose success at 1 m/2 degrees, with pooled false-acceptance and false-rejection rates of 0.707% and 1.142%. A paired cached evaluation retains all 1,775 initializer poses correct at this threshold. Recorded median text query latency is 0.020 s. Matched controls show competitive BM25 retrieval and slightly lower false acceptance for thresholded full LoGS; grid augmentation suggests modest gains on novel-view-derived descriptions. We report model-judged semantic success separately from source-camera recovery, with source-verified or estimated scales for geometric evaluation.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41373 — 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 2026-11-02T04:49:13.252Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).