Metraipolis › archive › dc_d9f501edecec

Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System — arXiv:2609.04151

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04151
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:35.910Z
SHA-256 of the archived text
dc4a7e2065cc292adaff79bd3f464299737cdf89458cb65e38d57aa7b757ecb7
Stable URL of this page
https://metraipolis.com/documento/dc_d9f501edecec

How to cite

Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System — arXiv:2609.04151 — arXiv (en), https://arxiv.org/abs/2609.04151 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9f501edecec (Metraipolis archive dc_d9f501edecec, sha256 dc4a7e2065cc292adaff79bd3f464299737cdf89458cb65e38d57aa7b757ecb7)
BibTeX
@misc{dcd9f501edecec,
  title = {Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System — arXiv:2609.04151},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04151},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9f501edecec; sha256 dc4a7e2065cc292adaff79bd3f464299737cdf89458cb65e38d57aa7b757ecb7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04151. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve who or what is being depicted. When generating or editing images of a specific subject, identity may drift as the pose, expression, appearance, viewpoint, or surrounding scene changes. Existing subject-driven methods make fundamentally different choices about where identity is represented: through the input context (GPT-Image-2, NB2), as trainable subject-specific model parameters (LoRA), or as a persistent identity layer (PHOTA IDENTITY) reusable across generations and edits. We systematically benchmark these paradigms across subject-driven generation, editing, restoration, and multi-subject settings, with tasks designed to increasingly stress identity preservation. Our results show that identity preservation remains a distinct limitation of current generative foundation models: strong image quality and instruction following do not necessarily imply strong identity fidelity, and identity degradation becomes more pronounced under iterative edits, small subject scales, severe image degradation, and multi-subject composition. Persistent identity substantially reduces this degradation across generation, editing, and restoration, consistently improving identity preservation when applied to different foundation models while maintaining comparable instruction adherence and perceptual image quality. These results suggest that identity does not simply emerge from increasingly capable generative models, but can instead be represented as persistent subject knowledge that is composed independently with the underlying generative model.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04151 — 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 2026-10-17T02:27:19.014Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).