Metraipolis › archive › dc_463bc3a5462d
Generative Cinematographer: Composing Camera and Object Motion in 3D — arXiv:2610.02180
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02180
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:16:21.405Z
- SHA-256 of the archived text
7cbcb723fcc07bc24eda99051b8b0533c4d13d25b2543606fcc196169c16f2b9- Stable URL of this page
https://metraipolis.com/documento/dc_463bc3a5462d
How to cite
Generative Cinematographer: Composing Camera and Object Motion in 3D — arXiv:2610.02180 — arXiv (en), https://arxiv.org/abs/2610.02180 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_463bc3a5462d (Metraipolis archive dc_463bc3a5462d, sha256 7cbcb723fcc07bc24eda99051b8b0533c4d13d25b2543606fcc196169c16f2b9)
BibTeX
@misc{dc463bc3a5462d,
title = {Generative Cinematographer: Composing Camera and Object Motion in 3D — arXiv:2610.02180},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02180},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_463bc3a5462d; sha256 7cbcb723fcc07bc24eda99051b8b0533c4d13d25b2543606fcc196169c16f2b9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02180. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D motions, especially when the camera and objects move simultaneously. We present Generative Cinematographer (GenCine), a system that lifts a single image into an editable 3D scene scaffold where artists jointly author camera and foreground motion. Artists specify a camera path and move selected foreground regions using local 3D motion handles. Several handles can move different parts of a subject independently, providing a piecewise-rigid approximation to non-rigid motion without a physics simulator or category-specific prior. To communicate these controls to a pretrained video model, we project them into guidance maps. These maps record where the controlled regions appear in each frame, assign each handle a fixed color across frames and encode the current 3D positions of its controlled points in the same world coordinate system as the background. This lets us describe object motion relative to the scene even as the camera moves. For training, we recover controls from the motion observed in real videos and use ground-truth geometry and trajectories from synthetic videos. We train a lightweight guidance branch and LoRA adapters on a pretrained Wan model to follow these controls. Our experiments show consistent camera-relative motion, improved geometric consistency under viewpoint changes, and strong controllability across diverse real-world scenes. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.02180 — 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 2026-10-06T10:21:28.253Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).