Generative Cinematographer: Composing Camera and Object Motion in 3D
arXiv cs.AI · 2 Oct 2026, 03:58 AEST
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.
Key facts
- 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.
Read aloud
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. 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.
Sources in this cluster
- Generative Cinematographer: Composing Camera and Object Motion in 3D
arXiv cs.AI · 2 Oct 2026, 03:58 AEST