Metraipolis › archive › dc_6d4ea127d7ef
LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians — arXiv:2609.11616
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11616
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:35:45.174Z
- SHA-256 of the archived text
c89b63d4aff62f4d1fc6da6c39c3c76c9433b03ec1f20cafe997713acf9e67c4- Stable URL of this page
https://metraipolis.com/documento/dc_6d4ea127d7ef
How to cite
LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians — arXiv:2609.11616 — arXiv (en), https://arxiv.org/abs/2609.11616 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6d4ea127d7ef (Metraipolis archive dc_6d4ea127d7ef, sha256 c89b63d4aff62f4d1fc6da6c39c3c76c9433b03ec1f20cafe997713acf9e67c4)
BibTeX
@misc{dc6d4ea127d7ef,
title = {LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians — arXiv:2609.11616},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11616},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6d4ea127d7ef; sha256 c89b63d4aff62f4d1fc6da6c39c3c76c9433b03ec1f20cafe997713acf9e67c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11616. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language Gaussian fields implicitly assume that the primitive carrying semantics remains identifiable across views. This assumption breaks in scalable anchor-decoded representations, where persistent anchors generate view-conditioned child Gaussians whose geometry and appearance vary with the camera. We introduce Ours, a persistent language field for such structured Gaussian scenes. Our key idea is semantic ownership: transient children route observations, while persistent decoder slots and their parent anchors own the language field. We use alpha-compositing responsibilities to accumulate additive directional evidence at slots; these statistics marginalize exactly to anchors. We then complete weakly supported slots with anchor-aligned evidence while preserving the anchor direction, and represent slot detail through low-rank residuals in anchor-relative semantic coordinates. Our primary model, Ours (base), stores anchor features together with compact slot residuals. Ours (light) retains only anchor features, whereas Ours (max) stores the full-dimensional completed slot features explicitly. Without scene-specific semantic optimization, Ours (base) nearly matches Ours (max) across KITTI, Virtual KITTI, and Waymo. On KITTI, it achieves 34.19 2D mIoU with a 2.72 GiB effective feature footprint, compared with 34.20 mIoU and 12.90 GiB for Ours (max). The same accuracy-storage trend holds on Virtual KITTI and Waymo. These results show that language fields on view-conditioned splats require persistent semantic ownership, conserved evidence, and a hierarchy that balances stability, detail, and representation cost. Our code, checkpoints, and benchmark suite will be publicly available. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.11616 — 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 2026-10-16T06:06:28.798Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).