Metraipolis › archive › dc_656aa6143aed

Uncertainty-Aware Consistency Distillation for Few-Step Video Generation — arXiv:2609.39132

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39132
License (as archived): CC0-1.0
Archived: 2026-10-07T14:45:53.417Z
SHA-256 of the archived text: 217e56f45114d90dce0a314ec2677a2f6f440d0eb5cebe88db4ac5366a5a93e7
Stable URL of this page: https://metraipolis.com/documento/dc_656aa6143aed

How to cite

Uncertainty-Aware Consistency Distillation for Few-Step Video Generation — arXiv:2609.39132 — arXiv (en), https://arxiv.org/abs/2609.39132 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_656aa6143aed (Metraipolis archive dc_656aa6143aed, sha256 217e56f45114d90dce0a314ec2677a2f6f440d0eb5cebe88db4ac5366a5a93e7)

BibTeX

@misc{dc656aa6143aed,
  title = {Uncertainty-Aware Consistency Distillation for Few-Step Video Generation — arXiv:2609.39132},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39132},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_656aa6143aed; sha256 217e56f45114d90dce0a314ec2677a2f6f440d0eb5cebe88db4ac5366a5a93e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39132. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study few-step video generation, i.e., distilling a multi-step video generator, which typically requires tens of sampling steps, incurring substantial latency and compute, into a few-step student. Consistency distillation is a common recipe, in which a multi-step teacher provides the consistency targets for a few-step student. However, these teacher-guided targets are not equally trustworthy, and the content is harder to learn where it varies rapidly over time, e.g., moving foliage shadows or flowing water. We observe that supervision reliability follows the local difficulty of the content rather than semantic complexity: regions that change little yield consistent endpoint predictions, whereas regions with large temporal variation produce larger discrepancies that coincide with the largest perceptual errors. Motivated by this observation, we propose Uncertainty-Aware Consistency Distillation (UACD), which reweights consistency supervision at each spatiotemporal region using a local, parameter-free uncertainty estimate. Specifically, we construct two independently perturbed teacher-guided consistency paths, whose student endpoint predictions provide a consensus target; the discrepancy between the student's direct prediction and this target is the uncertainty proxy. We then relax the consistency penalty on high-uncertainty regions through an exponential weight, while keeping the full penalty elsewhere, since the student cannot be expected to match targets that are hard to learn. To preserve perceptual quality under aggressive step reduction, we integrate feature-space adversarial training with semantic alignment. With parameter-efficient LoRA adaptation of the 50-step Wan model, our method achieves state-of-the-art 4-step generation on VBench 2.0 (0.556 mean score) and is preferred over competing methods in a user study.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2609.39132 — 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 2026-10-07T14:19:00.685Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).