Metraipolis › archive › dc_3968b5bb98aa

SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation — arXiv:2609.20475

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20475
License (as archived)
CC0-1.0
Archived
2026-10-10T05:07:57.608Z
SHA-256 of the archived text
e57b5c911dad35f28054625ac8dba8760921d8263f7629ba5b16aab92191a163
Stable URL of this page
https://metraipolis.com/documento/dc_3968b5bb98aa

How to cite

SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation — arXiv:2609.20475 — arXiv (en), https://arxiv.org/abs/2609.20475 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3968b5bb98aa (Metraipolis archive dc_3968b5bb98aa, sha256 e57b5c911dad35f28054625ac8dba8760921d8263f7629ba5b16aab92191a163)
BibTeX
@misc{dc3968b5bb98aa,
  title = {SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation — arXiv:2609.20475},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20475},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3968b5bb98aa; sha256 e57b5c911dad35f28054625ac8dba8760921d8263f7629ba5b16aab92191a163},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20475. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-vocabulary scene understanding is fundamental for robotics, laying the groundwork for spatial reasoning and object manipulation. While closed-vocabulary 3D instance segmentation heavily leverages 3D shape information, state-of-the-art open-vocabulary methods remain predominantly restricted to 2D image features or image-distilled representations during mask labeling. In this paper, we propose SenseFuse, a label-free fusion method that balances 2D image and 3D shape encoders for robust open-vocabulary 3D instance segmentation, refining only the mask-labeling stage of existing pipelines. We reveal that 2D image and 3D shape encoders exhibit largely disjoint failure patterns and rarely share identical wrong labels, whereas two 2D image encoders frequently repeat the same errors. This distinct behavior makes the 2D and 3D pair inherently complementary. We introduce an adaptive mechanism that selects a scene-level fusion weight to maximize a label-free sensitivity measure, estimated directly from a single scene's unlabeled proposals in milliseconds. SenseFuse improves labeling accuracy in every evaluated setting across ScanNet200, Replica, and ScanNet++, recovering 67-100% (median 93%) of the gain achievable with an oracle weight, and it raises instance AP in 21 of 22 reported settings. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.20475 — 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 2026-10-10T04:26:09.608Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).