Metraipolis › archive › dc_55171e784ac4

4Director: Controlling Video World Models with Rigid 3D Geometry — arXiv:2610.02160

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02160
License (as archived)
CC0-1.0
Archived
2026-10-06T19:15:41.879Z
SHA-256 of the archived text
6b24ef0f7e846b9e2fa01071fe81504272c0366d3ab66fe13589a7c40f180f50
Stable URL of this page
https://metraipolis.com/documento/dc_55171e784ac4

How to cite

4Director: Controlling Video World Models with Rigid 3D Geometry — arXiv:2610.02160 — arXiv (en), https://arxiv.org/abs/2610.02160 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55171e784ac4 (Metraipolis archive dc_55171e784ac4, sha256 6b24ef0f7e846b9e2fa01071fe81504272c0366d3ab66fe13589a7c40f180f50)
BibTeX
@misc{dc55171e784ac4,
  title = {4Director: Controlling Video World Models with Rigid 3D Geometry — arXiv:2610.02160},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02160},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55171e784ac4; sha256 6b24ef0f7e846b9e2fa01071fe81504272c0366d3ab66fe13589a7c40f180f50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02160. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We introduce 4Director, a video world model conditioned on an explicit 4D scene representation: each object is reconstructed once from the input image as a canonical mesh and moved by one prescribed rigid transformation per frame. This representation provides an intuitive 3D control interface and prevents unobserved geometry from being regenerated independently in every frame. We render the controlled scene as a depth video and introduce a Motion Adapter that transforms this geometric scaffold into video while synthesizing view-consistent appearance, illumination, and non-rigid dynamics. For training, we construct RealCOD-Rigid, a new dataset of 20,774 clips annotated with rigid 3D scenes by our automatic pipeline. We further introduce Identity-Gated IoU (IG-IoU), which jointly evaluates adherence to prescribed object motion and preservation of object identity. Experiments demonstrate that 4Director consistently outperforms prior methods in visual quality and in camera and object control.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.02160 — 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 2026-10-06T17:37:36.890Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).