Object and intent
Identify the target and desired state change.
A unified framework for object-level geometric video editing with compact, video-aligned pre/post geometry instructions.
GIVE represents an edit as a transition between pre-edit and post-edit 3D object states. The trajectory case below is one example of the shared interface used across editing operators.
Identify the target and desired state change.
Encode the object's current placement, extent, and orientation.
Specify the intended object state across viewpoint and time.
Execute the specified state transition while preserving the scene.
A graphics engine executes sampled edit programs and renders controlled before/after training pairs.
Compare the same input and edit intent across applicable methods.
These examples complement the side-by-side comparisons by highlighting targeted capabilities: edit-consistent secondary effects, flexible 3D trajectory control, and controllable rotation angles.