Metraipolis › archive › dc_9acd101ca8a1

Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization — arXiv:2608.14078

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14078
License (as archived)
CC0-1.0
Archived
2026-10-19T04:04:24.096Z
SHA-256 of the archived text
fdc71538e3347ddef092f647f7eb4037748ea0e3507405f6a4c6b319ffde054e
Stable URL of this page
https://metraipolis.com/documento/dc_9acd101ca8a1

How to cite

Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization — arXiv:2608.14078 — arXiv (en), https://arxiv.org/abs/2608.14078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9acd101ca8a1 (Metraipolis archive dc_9acd101ca8a1, sha256 fdc71538e3347ddef092f647f7eb4037748ea0e3507405f6a4c6b319ffde054e)
BibTeX
@misc{dc9acd101ca8a1,
  title = {Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization — arXiv:2608.14078},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14078},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9acd101ca8a1; sha256 fdc71538e3347ddef092f647f7eb4037748ea0e3507405f6a4c6b319ffde054e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Localized 3D stylization aims to modify the appearance of a specified object part while preserving the remaining surfaces. In large reconstruction models (LRMs), this task is challenging because style is injected into intermediate appearance representations before rendering, while compact triplane features are shared across target and non-target surfaces, causing style leakage and boundary ambiguity. We propose Owner3D, a training-free framework for localized 3D stylization that integrates localized appearance control directly into the LRM reconstruction process. Specifically, Owner3D introduces ownership-guided style writing to restrict reference-style injection to target regions, producing a single localized stylized triplane without additional training while avoiding separate global style and appearance representations. To resolve appearance ambiguity near semantic boundaries, we further introduce boundary dual slots that maintain separate local feature sources for target and non-target regions. Finally, a surface-first texture readout hierarchically combines surface, 3D, and triplane ownership evidence to robustly recover appearance under incomplete visibility. Experiments on a benchmark constructed from Google Scanned Objects and PartNet demonstrate that Owner3D consistently outperforms existing 3D stylization methods in target-region style fidelity and non-target appearance preservation, reducing appearance leakage by 86.4% and 89.9% compared with StyleSplat and LAENeRF, respectively.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.14078 — 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 2026-10-19T03:57:57.861Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).