Metraipolis › archive › dc_c90e1aade240

Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes — arXiv:2609.25247

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25247
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:16.024Z
SHA-256 of the archived text
231be4d22c653ee59cf7ec09865f8554f1735dac701e23221617f3c4c2364cc8
Stable URL of this page
https://metraipolis.com/documento/dc_c90e1aade240

How to cite

Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes — arXiv:2609.25247 — arXiv (en), https://arxiv.org/abs/2609.25247 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c90e1aade240 (Metraipolis archive dc_c90e1aade240, sha256 231be4d22c653ee59cf7ec09865f8554f1735dac701e23221617f3c4c2364cc8)
BibTeX
@misc{dcc90e1aade240,
  title = {Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes — arXiv:2609.25247},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25247},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c90e1aade240; sha256 231be4d22c653ee59cf7ec09865f8554f1735dac701e23221617f3c4c2364cc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25247. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their predictions can inform one another. A closed cabinet door, for instance, reveals a movable surface but may leave the hinge side ambiguous; its handle helps resolve this ambiguity, while the part provides context for localizing and interpreting the small handle. Building on this observation, we present SEGMENT-SNAP, which combines geometric and semantic evidence through part-handle coupling. Three independently trained predictors recover movable parts, dense handles, and part-associated handle proposals. We couple their outputs in two directions. For part motion, a training-free geometric decoder fits predicted part surfaces under explicit physical priors and uses detected handles to select candidate hinge lines. For handle prediction, a part-conditioned branch proposes additional handles, while standalone part classes refine their rotation/translation labels, with dense-handle labels as a fallback. Each transfer is applied once, without iterative feedback. On the Articulate3D validation set, handle guidance raises motion-gated AP from 13.74 to 40.98 under fixed masks and axes. Additional handle proposals raise handle AP from 24.63 to 29.65, and full contextual class correction raises it to 30.99 in the reference configuration. Fixed-input controls, retraining ablations, learned-decoder comparisons, and paired visualizations together characterize the benefits and limits of this coupling. Our system also achieved first place in the Articulate3D Challenge.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25247 — 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 2026-10-08T13:18:38.219Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).