Metraipolis › archive › dc_ee8226ac480a

LiveVVT: High-Fidelity Video Virtual Try-On in Real Time — arXiv:2608.26714

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26714
License (as archived)
CC0-1.0
Archived
2026-10-17T14:27:59.780Z
SHA-256 of the archived text
7f1dc99e82fb5ab886b5acfea9e91db299082d16e4bbe23962e412b7f1fc8030
Stable URL of this page
https://metraipolis.com/documento/dc_ee8226ac480a

How to cite

LiveVVT: High-Fidelity Video Virtual Try-On in Real Time — arXiv:2608.26714 — arXiv (en), https://arxiv.org/abs/2608.26714 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee8226ac480a (Metraipolis archive dc_ee8226ac480a, sha256 7f1dc99e82fb5ab886b5acfea9e91db299082d16e4bbe23962e412b7f1fc8030)
BibTeX
@misc{dcee8226ac480a,
  title = {LiveVVT: High-Fidelity Video Virtual Try-On in Real Time — arXiv:2608.26714},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26714},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee8226ac480a; sha256 7f1dc99e82fb5ab886b5acfea9e91db299082d16e4bbe23962e412b7f1fc8030},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26714. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence incurs prohibitive latency and computational overhead in practical continuous deployment. Naively enforcing causality disrupts pretrained bidirectional priors and substantially degrades synthesis quality. We introduce LiveVVT, a rolling streaming diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation. Within a fixed-size window, LiveVVT jointly denoises multiple video chunks under bounded look-ahead, preserving local bidirectional interactions while emitting one clean chunk per iteration. Beyond the window, two complementary memories sustain long-term consistency: a bounded temporal memory propagates recent dynamics and occlusion context, whereas a persistent global appearance memory, constructed once from the target garment and a frontal try-on keyframe, anchors garment details and dressed appearance throughout the stream. We further introduce a progressive distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching Distillation, which couples teacher-distribution matching with rolling flow matching on real videos to align optimization with recurrent inference. Experiments on paired and unpaired long-sequence benchmarks demonstrate superior generation quality over similarly sized models, with $26\times$ lower latency and $11\times$ higher throughput, enabling high-fidelity real-time streaming VVT.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26714 — 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 2026-10-17T13:16:53.656Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).