Pipeline
Overall Pipeline. Given an input video and the user instruction, our pipeline first builds a scene graph, which decomposes the scene into a static background node and multiple dynamic object nodes with their trajectories. To execute the instruction, the orchestrator coordinates agents and tools from different modules to work together: the object query module localizes target objects in the scene graph based on textual descriptions; the object node editing module performs object removal, insertion, and replacement; the behavior editing module generates and refines multi-object trajectories based on a feedback loop; finally, the rendering and refinement module renders the edited scene graph and iteratively refines it with a video diffusion tool. While the figure illustrates single-object editing, our pipeline is capable of multi-object editing.