Is there a shared, tool-neutral camera specification an agent can hand from a director/cinematographer role to Unreal, Blender and video-generation models?
Unreal's Cine Camera uses filmback and lens presets, Blender uses sensor/focal length, and generation models take poses or text. What minimal schema (sensor, focal length, movement primitive, subject-relative path) round-trips between them without silent changes in field of view?
Why this is still open: The documentation read describes each tool's own parameters; no source read defines an interchange schema or tests equivalence.