Metraipolis › archive › dc_083bd8f398ba

RefDiT: Local Attribute Guidance in Reference-Based Image Generation — arXiv:2609.04976

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04976
License (as archived)
CC0-1.0
Archived
2026-10-16T23:41:17.821Z
SHA-256 of the archived text
2bd91ca26af7dd25dd4a4dfa810612512fc4321c44d9e5f1c3d169a1efbccb53
Stable URL of this page
https://metraipolis.com/documento/dc_083bd8f398ba

How to cite

RefDiT: Local Attribute Guidance in Reference-Based Image Generation — arXiv:2609.04976 — arXiv (en), https://arxiv.org/abs/2609.04976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_083bd8f398ba (Metraipolis archive dc_083bd8f398ba, sha256 2bd91ca26af7dd25dd4a4dfa810612512fc4321c44d9e5f1c3d169a1efbccb53)
BibTeX
@misc{dc083bd8f398ba,
  title = {RefDiT: Local Attribute Guidance in Reference-Based Image Generation — arXiv:2609.04976},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04976},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_083bd8f398ba; sha256 2bd91ca26af7dd25dd4a4dfa810612512fc4321c44d9e5f1c3d169a1efbccb53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Personalization models generate new images guided by a few subject references, while style transfer methods aim to produce images aligned with a global style derived from a reference image. Recent approaches perform well when the reference image contains a single object, effectively capturing a global style that encompasses all implicit attributes. However, when applied to complex real-world scenes containing multiple objects with distinct attribute characteristics, these methods, due to their global-level guidance, fail to localize relevant elements in the reference image. The global guidance restricts their ability to generate new images based on the local attributes in the reference image. Moreover, existing methods typically employ a single identifier token to capture all details from the reference, resulting in a lack of individual, attribute-level control. Motivated by these limitations, we propose RefDiT, a novel framework for reference-guided image generation. RefDiT takes as input a reference image, a text prompt, and an optional user-provided guidance context. RefDiT employs local region guidance using the attributes of local elements. It constructs an attribute-aware conditioning signal from the reference image by performing attribute-level decomposition of the identifier token and performs context adjustment in the inference prompt to train low-rank adapter (LoRA) blocks of a diffusion transformer (DiT)-based generative model. RefDiT learns the correspondence between identifier tokens and local regions in the reference image, enabling more effective local guidance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04976 — 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 2026-10-16T23:16:11.429Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).