Metraipolis › archive › dc_0fd44aaac7cb

Content-Preserving Principal Feature Blending for Training-Free Style Personalization — arXiv:2611.00683

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00683
License (as archived)
CC0-1.0
Archived
2026-11-03T18:53:13.521Z
SHA-256 of the archived text
02511799a8cb0a9b5be24e39aa376bba6ec892d9377ed964509c36a3f1c98aae
Stable URL of this page
https://metraipolis.com/documento/dc_0fd44aaac7cb

How to cite

Content-Preserving Principal Feature Blending for Training-Free Style Personalization — arXiv:2611.00683 — arXiv (en), https://arxiv.org/abs/2611.00683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fd44aaac7cb (Metraipolis archive dc_0fd44aaac7cb, sha256 02511799a8cb0a9b5be24e39aa376bba6ec892d9377ed964509c36a3f1c98aae)
BibTeX
@misc{dc0fd44aaac7cb,
  title = {Content-Preserving Principal Feature Blending for Training-Free Style Personalization — arXiv:2611.00683},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00683},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fd44aaac7cb; sha256 02511799a8cb0a9b5be24e39aa376bba6ec892d9377ed964509c36a3f1c98aae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reference-based style personalization should reproduce the appearance of a style reference while preserving the subject specified by a content prompt. In visual autoregressive models, dominant reference features can also carry object and spatial information, causing content leakage. We propose Content-Preserving Principal Feature Blending (CoPFB), a training-free method that estimates a low-rank content basis from a clean generation branch and removes the content-aligned component of the style residual. CoPFB applies rank-one blending at the first two autoregressive scales, followed by weaker content-projected refinement at the next three scales. On 1,900 combinations of Parti content prompts and FineStyle reference images, CoPFB improves text alignment from 0.293 to 0.297 and the harmonic score from 0.391 to 0.393 over PFB+SAC, while style similarity decreases from 0.590 to 0.577. CoPFB requires no fine-tuning or learnable parameters. Project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00683 — 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 2026-11-03T18:16:52.892Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).