Metraipolis › archive › dc_cdbf57be33d5

SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation — arXiv:2609.25490

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25490
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:15.146Z
SHA-256 of the archived text
3b5808b87f70468c817a1e962ce5c3fcc3868c28fdd161f91246edadfdbc8591
Stable URL of this page
https://metraipolis.com/documento/dc_cdbf57be33d5

How to cite

SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation — arXiv:2609.25490 — arXiv (en), https://arxiv.org/abs/2609.25490 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdbf57be33d5 (Metraipolis archive dc_cdbf57be33d5, sha256 3b5808b87f70468c817a1e962ce5c3fcc3868c28fdd161f91246edadfdbc8591)
BibTeX
@misc{dccdbf57be33d5,
  title = {SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation — arXiv:2609.25490},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25490},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdbf57be33d5; sha256 3b5808b87f70468c817a1e962ce5c3fcc3868c28fdd161f91246edadfdbc8591},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25490. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typically perform 3D instance segmentation on point clouds or rely on offline 2D mask-matching pipelines. However, 3D instance segmentation is limited by scarce 3D annotations, while offline 2D matching suffers from object identity ambiguity across frames. To leverage strong 2D and 3D priors jointly, we propose SAM-V (Geometry-Aware Segment Anything for Multi-View Instance Segmentation). Instead of combining the two priors through post-hoc matching, SAM-V directly integrates features from a feed-forward geometry model (VGGT) into a 2D segmentation foundation model (SAM), trained end-to-end for cross-view instance prediction. SAM-V introduces a prompt-fusion mechanism that enriches sparse SAM prompt tokens with view-specific camera tokens and local VGGT features, making the prompt representation both view-aware and spatially grounded, together with a mask decoder that attends to dense 2D and 3D features. By conditioning the mask decoding directly on multi-view geometry, SAM-V produces consistent multi-view segmentation of a prompted object in a single forward pass without offline mask matching or explicit 3D reconstruction. On the IGGT 3D tracking benchmark, where consistent instance identity across frames directly determines performance, SAM-V improves overall IoU by 5 points and frame-level recall by 12 points on the ScanNet++ split over the state-of-the-art multi-view instance segmentation baseline and leads on all metrics in the zero-shot ScanNet split. Our code and pretrained models are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25490 — 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 2026-10-08T14:37:29.533Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).