Metraipolis › archive › dc_593adcbffed9

SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views — arXiv:2609.11279

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11279
License (as archived): CC0-1.0
Archived: 2026-10-16T06:35:32.207Z
SHA-256 of the archived text: 15bd0f062c7b836d12571983eae9b5df644f63daabf1a652b2ba89371f564c69
Stable URL of this page: https://metraipolis.com/documento/dc_593adcbffed9

How to cite

SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views — arXiv:2609.11279 — arXiv (en), https://arxiv.org/abs/2609.11279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_593adcbffed9 (Metraipolis archive dc_593adcbffed9, sha256 15bd0f062c7b836d12571983eae9b5df644f63daabf1a652b2ba89371f564c69)

BibTeX

@misc{dc593adcbffed9,
  title = {SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views — arXiv:2609.11279},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_593adcbffed9; sha256 15bd0f062c7b836d12571983eae9b5df644f63daabf1a652b2ba89371f564c69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the rising demand to decouple objects from 3D scenes, we propose SAMV-DUSt3R, an end-to-end model that injects SAM2 2D masks into MV-DUSt3R reconstruction. A Cross Flow Mask Block uses these masks to steer the network toward the target instance, jointly improving shape accuracy and achieving object-level disentanglement without multi-stage pipelines. To ensure reconstruction stability, a lightweight Spatial RankGNN selects the optimal reference view with a selection accuracy of 73.5\%. Extensive experiments demonstrate that our method boosts average reconstruction precision by 11\% across various metrics compared to state-of-the-art baselines. These results reveal a strong instance-disentanglement capability and clear benefits for driving, robotics, AR/VR, and heritage digitisation.

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/2609.11279 — 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 2026-10-16T06:06:28.770Z 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).