Metraipolis › archive › dc_24969f128efd

UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on — arXiv:2608.05745

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05745
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:11.312Z
SHA-256 of the archived text
ed576885c553a57506047adea68c62b4a23fd98cf59f126c2c84b21b1c21e9f8
Stable URL of this page
https://metraipolis.com/documento/dc_24969f128efd

How to cite

UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on — arXiv:2608.05745 — arXiv (en), https://arxiv.org/abs/2608.05745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24969f128efd (Metraipolis archive dc_24969f128efd, sha256 ed576885c553a57506047adea68c62b4a23fd98cf59f126c2c84b21b1c21e9f8)
BibTeX
@misc{dc24969f128efd,
  title = {UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on — arXiv:2608.05745},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05745},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24969f128efd; sha256 ed576885c553a57506047adea68c62b4a23fd98cf59f126c2c84b21b1c21e9f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This multi-stage design complicates deployment and, more critically, allows errors in explicit geometric priors to propagate irreversibly into the generated video. We present UniVVT, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference. At its core, a scene-task perceiver built on a Multimodal Large Language Model jointly encodes the source video, target garment, and task instruction into compact, task-aware latent tokens, implicitly capturing what to transfer and where and how to transfer it. A lightweight semantic bridge then aligns these tokens with the conditioning space of a diffusion-based video generator, enabling coherent garment transfer. To robustly couple the heterogeneous components, we devise a three-stage progressive training strategy comprising semantic alignment, joint task adaptation, and flexible-resolution refinement. Extensive experiments demonstrate that UniVVT achieves state-of-the-art performance across multiple benchmarks, validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.05745 — 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 2026-10-31T10:23:31.008Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).