Metraipolis › archive › dc_e62cfdf63315

GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations — arXiv:2609.06628

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06628
License (as archived)
CC0-1.0
Archived
2026-10-16T15:09:14.845Z
SHA-256 of the archived text
4a16e0f7901065276833d413725570e9c7f62964957873255aefdb72a3051151
Stable URL of this page
https://metraipolis.com/documento/dc_e62cfdf63315

How to cite

GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations — arXiv:2609.06628 — arXiv (en), https://arxiv.org/abs/2609.06628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e62cfdf63315 (Metraipolis archive dc_e62cfdf63315, sha256 4a16e0f7901065276833d413725570e9c7f62964957873255aefdb72a3051151)
BibTeX
@misc{dce62cfdf63315,
  title = {GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations — arXiv:2609.06628},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06628},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e62cfdf63315; sha256 4a16e0f7901065276833d413725570e9c7f62964957873255aefdb72a3051151},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Object-centric video models represent scenes with slots, yet exposed geometry can vary in meaning with appearance. In Invariant Slot Attention (ISA), explicit position and scale can disagree with the decoded center and extent; edits can yield unexpected motion or resizing, and replacing appearance can shift geometry. GeoCo-SAVi promotes geometric authority and semantic alignment. Its spatially equivariant, object-wise decoder makes position and scale effective commands: changing them moves or resizes the rendered support. Factual position alignment ties position to the decoded center, and normalized attention overlap discourages duplicate allocation. Appearance transplantation aligns geometry semantics across objects, so recipient geometry governs layout while donor appearance supplies shape. On Obj3D, GeoCo-SAVi matches ISA reconstruction, reduces latent-position-to-decoded-centroid error by nearly 90%, and reduces appearance-induced size variation while producing the expected translation and scale responses. On 250 MOVi-C videos, it improves reconstruction and instance grouping over both same-protocol references, and video editing over STAITUS. GeoCo-SAVi transforms explicit geometry into compositional control, making both position and scale more readable and editable. Project page: this https URL .

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/2609.06628 — 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 2026-10-16T14:49:57.105Z 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).