media creative tools
Video Motion Controls Moved Into Three Dimensions
Artists compose camera paths and local object handles in a shared scene scaffold.
Summary
Artists compose camera paths and local object handles in a shared scene scaffold.
Generative Cinematographer lifts one image into an editable 3D scaffold, where camera paths and local handles describe foreground motion relative to the scene. Guidance maps project those controls into a pretrained video model while retaining consistent handle identities and world coordinates as the camera moves. The authors train lightweight guidance and LoRA components and report more consistent camera-relative motion and geometry across diverse scenes. The system approximates non-rigid motion without a physics simulator and is an authoring tool, not a physical-motion model.
Why it matters
Artists compose camera paths and local object handles in a shared scene scaffold.
Limits and context
- The system approximates non-rigid motion without a physics simulator and is an authoring tool, not a physical-motion model.
Key claims
Artists compose camera paths and local object handles in a shared scene scaffold.
Qualification: The system approximates non-rigid motion without a physics simulator and is an authoring tool, not a physical-motion model.
Evidence: source-2026-10-02-012
Sources
- arXiv preprint 2610.02180arXiv · primary research
Corrections
No corrections have been recorded for this story.