Metraipolis › archive › dc_5ff999df8edb

A Scene Language Model for Open-Vocabulary Scene Mapping — arXiv:2609.21400

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21400
License (as archived)
CC0-1.0
Archived
2026-10-10T02:23:12.654Z
SHA-256 of the archived text
0123dbc754caa63810dca644cbd1c03d1baa69df7f75fad0c47a3ca55a4f4e04
Stable URL of this page
https://metraipolis.com/documento/dc_5ff999df8edb

How to cite

A Scene Language Model for Open-Vocabulary Scene Mapping — arXiv:2609.21400 — arXiv (en), https://arxiv.org/abs/2609.21400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ff999df8edb (Metraipolis archive dc_5ff999df8edb, sha256 0123dbc754caa63810dca644cbd1c03d1baa69df7f75fad0c47a3ca55a4f4e04)
BibTeX
@misc{dc5ff999df8edb,
  title = {A Scene Language Model for Open-Vocabulary Scene Mapping — arXiv:2609.21400},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21400},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ff999df8edb; sha256 0123dbc754caa63810dca644cbd1c03d1baa69df7f75fad0c47a3ca55a4f4e04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-vocabulary 3D scene mapping aims to build a persistent representation of the objects in an environment. Existing systems typically rely on engineered mapping pipelines to associate observations, merge information across views, and maintain a consistent scene representation over time. Many additionally store feature-rich object representations, such as embeddings or image crops, increasing the size and complexity of the persistent memory. We introduce SceneLM, a Scene-Language Model that directly maintains a textual scene map. The full scene is represented as a structured text list of objects, which serves as the model's only persistent memory. For each input image, the model reads the current scene state and updates the map by adding, editing, and removing objects. To learn this behavior, we introduce supervision tasks for iterative scene map maintenance together with an automatic annotation pipeline that generates training data from images without human labels. We evaluate SceneLM on both a language-grounded retrieval benchmark and a localization benchmark. Across both benchmarks, the model produces a scene map that achieves competitive performance with complete mapping systems built from dedicated perception and geometric modules while producing a scene representation that is 6-12x more compact. We further show that SceneLM can be run online on an edge device through experiments on a quadruped. These results show that a persistent open-vocabulary 3D scene map can be maintained directly by a single vision-language model using only a lightweight text representation. Training and inference code is available on this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.21400 — 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 2026-10-10T02:07:36.045Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).