Metraipolis › archive › dc_fe3acb6e2256
When Diffusion Models Forget Who You Are: Identity Preservation in Face Inpainting under Large Occlusions — arXiv:2608.04820
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04820
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:11.295Z
- SHA-256 of the archived text
0747c6441bd7889bfc8ad53f021e4e46e7abb613a74a67ef0e1a5b76dc5e2cc4- Stable URL of this page
https://metraipolis.com/documento/dc_fe3acb6e2256
How to cite
When Diffusion Models Forget Who You Are: Identity Preservation in Face Inpainting under Large Occlusions — arXiv:2608.04820 — arXiv (en), https://arxiv.org/abs/2608.04820 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe3acb6e2256 (Metraipolis archive dc_fe3acb6e2256, sha256 0747c6441bd7889bfc8ad53f021e4e46e7abb613a74a67ef0e1a5b76dc5e2cc4)
BibTeX
@misc{dcfe3acb6e2256,
title = {When Diffusion Models Forget Who You Are: Identity Preservation in Face Inpainting under Large Occlusions — arXiv:2608.04820},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04820},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe3acb6e2256; sha256 0747c6441bd7889bfc8ad53f021e4e46e7abb613a74a67ef0e1a5b76dc5e2cc4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04820. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Face inpainting with diffusion models has recently achieved impressive visual quality, yet preserving identity fidelity under significant occlusion and conflicting text guidance remains a major challenge. To address this issue, we present Reference Semantic Inpainting for Face (ReSem-Face), a cascaded diffusion framework that introduces an explicit identity-conditioned semantic prior for multi-reference face inpainting. Our approach distills representative identity features from multiple references to reconstruct missing semantic regions, which then guide the diffusion process through a multi-stream conditioning architecture. This design provides strong semantic constraints when pixels are absent and stabilizes identity reconstruction while remaining compatible with prompt-driven edits. Experiments on CelebAHQ-IDI-5 and VGGFace2 demonstrate that ReSem-Face yields more reliable identity-preserving completion under severe semantic masks and improves text-controlled editing quality compared with representative baselines. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04820 — 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 2026-10-31T11:37:40.720Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).