Metraipolis › archive › dc_efe742ef7b46

Panoptic Scene Program Diffusion Transformer — arXiv:2609.31780

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31780
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:27.916Z
SHA-256 of the archived text
71613ffdcac66a08fa1da84dddb25dc2da1d3a0ccce00c09782e592dd46e39e1
Stable URL of this page
https://metraipolis.com/documento/dc_efe742ef7b46

How to cite

Panoptic Scene Program Diffusion Transformer — arXiv:2609.31780 — arXiv (en), https://arxiv.org/abs/2609.31780 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efe742ef7b46 (Metraipolis archive dc_efe742ef7b46, sha256 71613ffdcac66a08fa1da84dddb25dc2da1d3a0ccce00c09782e592dd46e39e1)
BibTeX
@misc{dcefe742ef7b46,
  title = {Panoptic Scene Program Diffusion Transformer — arXiv:2609.31780},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31780},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efe742ef7b46; sha256 71613ffdcac66a08fa1da84dddb25dc2da1d3a0ccce00c09782e592dd46e39e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31780. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern text-to-image models produce high-fidelity images but still struggle with compositional prompts that require instance identity, attribute ownership, counting, spatial ordering, and role-sensitive relations. We introduce Panoptic Scene Program Diffusion Transformer (PSP-DiT), a diffusion-transformer architecture that treats a panoptic scene program as a first-class latent variable rather than an external control signal or post-hoc parse. PSP-DiT jointly denoises image latents and scene-program latents through coupled transformer streams, while panoptic grounding and cycle-consistency objectives tie object instances, attributes, relations, and counts to visual support in the generated image. Under matched training and inference settings, PSP-DiT improves over a strong flat-text baseline across GenEval 2, SANEval-Simple, PSG-Score, and DetailMaster, with the largest gains on counting, attribute binding, role-sensitive relations, and long structured prompts. The method preserves image quality, adds modest inference overhead, and remains robust to imperfect scene programs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.31780 — 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 2026-10-07T22:14:28.543Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).