Metraipolis › archive › dc_22cef66d60b7

OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization — arXiv:2608.29905

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29905
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:11.682Z
SHA-256 of the archived text
1425d6caf440daa489bd79e29bf177764ff24fa0ebb067a56f4cafd6cc27a62b
Stable URL of this page
https://metraipolis.com/documento/dc_22cef66d60b7

How to cite

OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization — arXiv:2608.29905 — arXiv (en), https://arxiv.org/abs/2608.29905 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22cef66d60b7 (Metraipolis archive dc_22cef66d60b7, sha256 1425d6caf440daa489bd79e29bf177764ff24fa0ebb067a56f4cafd6cc27a62b)
BibTeX
@misc{dc22cef66d60b7,
  title = {OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization — arXiv:2608.29905},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29905},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22cef66d60b7; sha256 1425d6caf440daa489bd79e29bf177764ff24fa0ebb067a56f4cafd6cc27a62b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29905. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapid progress in 3D shape modeling, faithfully stylizing an existing asset remains challenging when the desired stylization involves fine-grained structural ornamentation, which requires the model to preserve the source geometry and object identity, while coherently integrating new style-specific details. We propose \textbf{OrnaStyler}, a zero-shot framework for text-guided ornament-aware 3D stylization. Built upon rectified flow-based generative modeling, OrnaStyler introduces an inversion-guided editing strategy that recovers content-aware latent representations at both geometry and appearance levels in a staged manner to facilitate faithful editing. Our core idea is to explicitly model the spatial configuration of stylistic elements, thereby mitigating the fundamental tension between content preservation and style expression in the voxel space. Specifically, at the geometry level, we manipulate voxel representations through flow inversion to synthesize ornament-enhanced structures while preserving the spatial identity of the source asset. Then, at the appearance level, we introduce an adjacency-aware feature inpainting mechanism to harmonize newly generated ornaments with the original content, yielding coherent geometry-appearance integration. Our approach operates solely in the inference phase and enables selective editing over geometric augmentation or appearance stylization. Extensive experiments on both generated and real-world 3D assets against prior methods demonstrate that OrnaStyler achieves state-of-the-art editing performance in terms of content preservation, style fidelity, and overall visual realism. Code is available at: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29905 — 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 2026-10-17T09:28:48.082Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).