Metraipolis › archive › dc_bc01d5aaffde

One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time — arXiv:2611.02964

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02964
License (as archived): CC0-1.0
Archived: 2026-11-03T11:26:44.445Z
SHA-256 of the archived text: 6275ded1981440f1d3094fdfafed9cffb28edab7ec91469f299db236b1b834e4
Stable URL of this page: https://metraipolis.com/documento/dc_bc01d5aaffde

How to cite

One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time — arXiv:2611.02964 — arXiv (en), https://arxiv.org/abs/2611.02964 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc01d5aaffde (Metraipolis archive dc_bc01d5aaffde, sha256 6275ded1981440f1d3094fdfafed9cffb28edab7ec91469f299db236b1b834e4)

BibTeX

@misc{dcbc01d5aaffde,
  title = {One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time — arXiv:2611.02964},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02964},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc01d5aaffde; sha256 6275ded1981440f1d3094fdfafed9cffb28edab7ec91469f299db236b1b834e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02964. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pose-driven human video diffusion animates a person from a single reference image and a target pose sequence, yet it struggles to preserve identity, rendering the face and garments unfaithfully as the pose departs from it. Personalization is the standard remedy, but its supervision is missing: one image fixes identity at a single pose, while a multi-pose subject video cannot be assumed in practice. Instead, we synthesize the missing supervision. A domain-tuned, pose-conditioned generator produces pseudo-ground-truth frames at selected key poses. An inference-time reference-only sampler steers these candidates toward the subject and keeps the most identity-consistent. A per-subject low-rank adapter then trains on static clips of them, configured from the reference alone, with no subject video, ground truth, or labels. Although lower in fidelity, these synthetic frames supervise more effectively than real ones. Real frames as captured carry motion that erodes the temporal prior, while a static clip conveys appearance alone. On TikTok and UBC Fashion, the adapted model improves the base on every metric, inverts the identity-versus-motion trade-off, and matches or surpasses adaptation on five real frames despite using none. Code and weights are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02964 — 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 2026-11-03T11:02:37.896Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).