Metraipolis › archive › dc_e1f2bf4e4451

Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing — arXiv:2611.02330

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02330
License (as archived): CC0-1.0
Archived: 2026-11-03T18:19:50.054Z
SHA-256 of the archived text: ce9461f82fcddb013cbbc7823a97e529203db5e33c438f5234f8d78000ce6695
Stable URL of this page: https://metraipolis.com/documento/dc_e1f2bf4e4451

How to cite

Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing — arXiv:2611.02330 — arXiv (en), https://arxiv.org/abs/2611.02330 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1f2bf4e4451 (Metraipolis archive dc_e1f2bf4e4451, sha256 ce9461f82fcddb013cbbc7823a97e529203db5e33c438f5234f8d78000ce6695)

BibTeX

@misc{dce1f2bf4e4451,
  title = {Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing — arXiv:2611.02330},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02330},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1f2bf4e4451; sha256 ce9461f82fcddb013cbbc7823a97e529203db5e33c438f5234f8d78000ce6695},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02330. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial audio conveys not only what sounds are present, but where they originate and how they interact with the environment. Recent audio-language models increasingly understand and reason about such scenes, yet spatial audio understanding, generation, and editing remain largely separate. We present Spatial Transfusion, a unified first-order ambisonics (FOA) framework that extends a pretrained spatial audio understanding model to generation and editing through flow matching over VAE latents. We formulate editing as a structured scene transformation over a taxonomy of atomic edits. Keeping the pretrained backbone frozen, we introduce modality-based LoRA routing and a curriculum that progressively adds generation, editing, and natural-language interaction. Experiments show that Spatial Transfusion largely preserves spatial understanding while outperforming full fine-tuning in generation and editing. The resulting model supports controllable FOA generation and editing through both structured and natural-language interfaces. Audio samples are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.02330 — 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 2026-11-03T18:09:53.672Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).