Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
This addresses the problem of bridging video generation and robotic control for open-world manipulation, representing an incremental advance by adapting existing video models to robotics.
The paper tackles the challenge of translating human-led motions from generative video models into low-level robotic actions by introducing Dream2Flow, a framework that uses 3D object flow as an intermediate representation to enable zero-shot manipulation of diverse object categories without task-specific demonstrations.
Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions demanded by robotic systems. We observe that given an initial image and task instruction, these models excel at synthesizing sensible object motions. Thus, we introduce Dream2Flow, a framework that bridges video generation and robotic control through 3D object flow as an intermediate representation. Our method reconstructs 3D object motions from generated videos and formulates manipulation as object trajectory tracking. By separating the state changes from the actuators that realize those changes, Dream2Flow overcomes the embodiment gap and enables zero-shot guidance from pre-trained video models to manipulate objects of diverse categories-including rigid, articulated, deformable, and granular. Through trajectory optimization or reinforcement learning, Dream2Flow converts reconstructed 3D object flow into executable low-level commands without task-specific demonstrations. Simulation and real-world experiments highlight 3D object flow as a general and scalable interface for adapting video generation models to open-world robotic manipulation. Videos and visualizations are available at https://dream2flow.github.io/.