Metraipolis › archive › dc_d2811a5ba260

Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editing — arXiv:2609.21268

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21268
License (as archived)
CC0-1.0
Archived
2026-10-10T02:23:02.105Z
SHA-256 of the archived text
26eded0a6d08f18a32990e504cec39e1046109135ac5c9ff96dd6c18444523a2
Stable URL of this page
https://metraipolis.com/documento/dc_d2811a5ba260

How to cite

Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editing — arXiv:2609.21268 — arXiv (en), https://arxiv.org/abs/2609.21268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2811a5ba260 (Metraipolis archive dc_d2811a5ba260, sha256 26eded0a6d08f18a32990e504cec39e1046109135ac5c9ff96dd6c18444523a2)
BibTeX
@misc{dcd2811a5ba260,
  title = {Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editing — arXiv:2609.21268},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21268},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2811a5ba260; sha256 26eded0a6d08f18a32990e504cec39e1046109135ac5c9ff96dd6c18444523a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-guided video editing modifies target content while preserving the appearance and temporal coherence of unedited regions. Training-based approaches provide strong control but demand substantial data and computation. Training-free methods fall into inversion-free and inversion-based paradigms. Inversion-free approaches avoid trajectory recovery, but their source-preserving guidance can limit editing strength and leave semantic changes incomplete. Inversion-based approaches recover a latent trajectory before regeneration, where approximation errors can accumulate and cause source-content drift and temporal inconsistency. We introduce Edit-VAR, the first training-free and inversion-free framework for text-guided video editing with a pretrained visual autoregressive video model. Edit-VAR directly encodes the source video into multi-scale discrete tokens and performs probability-guided conditional token replacement for source preservation. Attention-guided token-wise and scale-aware modulation selectively relaxes source constraints over edit-relevant positions and generation stages. Scale-Decoupled Generation, implemented as late-scale constraint release, regenerates motion-consistent details and reduces texture fragmentation. Residual-guided token pruning further exploits redundancy at the final two high-resolution scales to reduce inference cost. Extensive experiments and a blind user study demonstrate that Edit-VAR outperforms existing training-free video editing methods overall in editing fidelity, source preservation, temporal coherence, and inference efficiency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21268 — 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 2026-10-10T02:07:36.025Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).