Metraipolis › archive › dc_ebcb6fc9ea87

CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing — arXiv:2610.10264

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10264
License (as archived): CC0-1.0
Archived: 2026-10-08T14:17:32.226Z
SHA-256 of the archived text: b61ba87b4161c83a6a3d2c8f375e2272df655fbdacca08ad3b118c825d35e667
Stable URL of this page: https://metraipolis.com/documento/dc_ebcb6fc9ea87

How to cite

CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing — arXiv:2610.10264 — arXiv (en), https://arxiv.org/abs/2610.10264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebcb6fc9ea87 (Metraipolis archive dc_ebcb6fc9ea87, sha256 b61ba87b4161c83a6a3d2c8f375e2272df655fbdacca08ad3b118c825d35e667)

BibTeX

@misc{dcebcb6fc9ea87,
  title = {CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing — arXiv:2610.10264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebcb6fc9ea87; sha256 b61ba87b4161c83a6a3d2c8f375e2272df655fbdacca08ad3b118c825d35e667},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimedia editing requires generative models to interpret complex, compositional instructions and modify only the desired elements across modalities, a capability largely beyond existing systems. Current approaches are typically limited to simple, single-attribute edits within one modality, since diverse, high-quality editing pairs are hard to obtain, especially for cross-modal tasks where aligned audiovisual (AV) data is scarce. We present CrossEdit, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer. Our key observation is that complex instruction-following, once learned in any modality, generalizes to others. We exploit the additive nature of acoustic signals to procedurally generate large-scale audio editing pairs with compositional instructions, and show that fine-tuning on this synthetic data and self-supervised AV masked reconstruction, alongside a targeted set of curated cross-modal tasks, induces instruction-following that transfers zero-shot to unseen modality and instruction combinations. To evaluate this capability, we release CrossEditBench, a human-annotated benchmark of AV edits on movie scenes, and propose AV-FES, a metric that jointly scores instruction following and consistency. We show that our proposed techniques improve performance on zero-shot AV movie scene editing, while maintaining or improving performance on lip-synced speech editing and standard image, video, and audio editing benchmarks. Demos are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2610.10264 — 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 2026-10-08T13:29:00.779Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).