Metraipolis › archive › dc_44476f9cd8ea

DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes — arXiv:2611.06160

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06160
License (as archived): CC0-1.0
Archived: 2026-11-05T18:29:58.582Z
SHA-256 of the archived text: 642789a369771f39994c88472a1fd8442e5d389f9aa33773cf3991b77c10a7d2
Stable URL of this page: https://metraipolis.com/documento/dc_44476f9cd8ea

How to cite

DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes — arXiv:2611.06160 — arXiv (en), https://arxiv.org/abs/2611.06160 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44476f9cd8ea (Metraipolis archive dc_44476f9cd8ea, sha256 642789a369771f39994c88472a1fd8442e5d389f9aa33773cf3991b77c10a7d2)

BibTeX

@misc{dc44476f9cd8ea,
  title = {DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes — arXiv:2611.06160},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06160},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44476f9cd8ea; sha256 642789a369771f39994c88472a1fd8442e5d389f9aa33773cf3991b77c10a7d2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06160. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing reasoning segmentation frameworks typically employ multimodal large language models (MLLMs) with broad world knowledge to extract semantics in a human-like manner and generate corresponding segmentation masks. Nevertheless, these frameworks lack the necessary scene-specific awareness. This paper introduces driving scene reasoning segmentation (DSRS), a scene-specific task that requires models to interpret implicit instructions, infer spatial relations, detect potential risks, handle challenging conditions, and comprehend underlying traffic rules, ultimately generating accurate segmentation masks. Meanwhile, we establish a benchmark dataset to facilitate future research on the DSRS task. To pioneer this task, we propose DSRS-Net, a novel architecture with advanced reasoning segmentation capability for automated driving. Specifically, DSRS-Net seamlessly infuses geometric features for deeper reasoning segmentation, without compromising the original multimodal fusion mechanism. This strategy effectively mitigates the modality representation mismatch in MLLMs caused by RGB-only pretraining, while enhancing the integration of geometric, contextual, and linguistic features. Extensive experiments demonstrate the superior performance of DSRS-Net in both driving scene reasoning segmentation and other language-driven segmentation tasks across various public datasets. The source code and dataset will be released upon publication.

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/2611.06160 — 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 2026-11-05T18:19:49.053Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).