Metraipolis › archive › dc_69fcd4b2d1d8

Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFs — arXiv:2609.07724

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07724
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:57.739Z
SHA-256 of the archived text
25a78e78b1a8d0c1cd048c97762cd5da92dc5ce886d0a73815a21d1358505a3e
Stable URL of this page
https://metraipolis.com/documento/dc_69fcd4b2d1d8

How to cite

Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFs — arXiv:2609.07724 — arXiv (en), https://arxiv.org/abs/2609.07724 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69fcd4b2d1d8 (Metraipolis archive dc_69fcd4b2d1d8, sha256 25a78e78b1a8d0c1cd048c97762cd5da92dc5ce886d0a73815a21d1358505a3e)
BibTeX
@misc{dc69fcd4b2d1d8,
  title = {Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFs — arXiv:2609.07724},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07724},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69fcd4b2d1d8; sha256 25a78e78b1a8d0c1cd048c97762cd5da92dc5ce886d0a73815a21d1358505a3e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07724. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate 3D plant organ segmentation is fundamental to automated phenotyping. Existing approaches rely on annotated training data or species-specific model configurations. We present an annotation-free pipeline for 3D plant organ segmentation, combining text-prompted SAM3 segmentation with semantic neural radiance fields (NeRFs). Given only multi-view RGB images and a list of class names, our zero-shot pipeline produces semantically labeled 3D point clouds without manual annotation, per-species fine-tuning, or domain-specific preprocessing. Multi-view NeRF fusion acts as effective implicit consensus mechanism that lifts imperfect per-frame masks into accurate 3D labels. On a controlled Begonia maculata testbed the SAM3 pipeline achieves 92.6% mIoU, reaching 95.9% of the oracle upper bound established with perfect ground-truth masks. The pipeline was further evaluated on a new dataset spanning ten diverse plant point clouds reaching an average 0.856 mIoU, with leaf and pot IoU above 0.91 and 0.90 for every species, respectively. These results demonstrate that annotation-free 3D plant organ segmentation is now feasible and approaching the range of supervised methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07724 — 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 2026-10-16T14:49:57.248Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).