Metraipolis › archive › dc_a01113035ea0

Text-Driven Artistic Staging: 3D Posing, Lighting, and Camera References from Paintings — arXiv:2608.28823

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28823
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:17.172Z
SHA-256 of the archived text
906b421f038838a1c9a24ec18e3f75e1cef0575e1f1ad13a21e18b50569111f1
Stable URL of this page
https://metraipolis.com/documento/dc_a01113035ea0

How to cite

Text-Driven Artistic Staging: 3D Posing, Lighting, and Camera References from Paintings — arXiv:2608.28823 — arXiv (en), https://arxiv.org/abs/2608.28823 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a01113035ea0 (Metraipolis archive dc_a01113035ea0, sha256 906b421f038838a1c9a24ec18e3f75e1cef0575e1f1ad13a21e18b50569111f1)
BibTeX
@misc{dca01113035ea0,
  title = {Text-Driven Artistic Staging: 3D Posing, Lighting, and Camera References from Paintings — arXiv:2608.28823},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28823},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a01113035ea0; sha256 906b421f038838a1c9a24ec18e3f75e1cef0575e1f1ad13a21e18b50569111f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28823. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artists coordinate human pose, illumination, and camera placement to convey narrative and emotion, but existing generative methods typically model these elements independently. We introduce text-to-editable 3D staging, a task that jointly generates human poses, a dominant light, and a camera configuration from an affective description. We construct 11,911 text--staging pairs from 2,328 figurative paintings by reconstructing SMPL bodies, estimating low-frequency illumination, recovering camera parameters, and pairing each scene with ArtEmis descriptions. We train a flow-matching transformer that supports variable numbers of figures and produces multiple staging alternatives for each prompt. On held-out descriptions, the model achieves 32.2\% retrieval R@1, compared with 16.6\% for CLIP-based nearest-neighbor retrieval, while approximately preserving corpus-level diversity. These results demonstrate the feasibility of generating editable, emotionally conditioned 3D staging references from text.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28823 — 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 2026-10-17T07:28:26.686Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).