BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
This work addresses the need for more precise spatial and temporal control in video generation for applications like filmmaking or simulation, representing a novel method rather than an incremental improvement.
The paper tackles the problem of video diffusion models coupling scene dynamics with camera motion, limiting precise control, by introducing a 4D-controllable framework that decouples these elements, enabling fine-grained manipulation of both scene dynamics and camera viewpoint while preserving high generation quality and outperforming prior work in controllability.
Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion framework that explicitly decouples scene dynamics from camera pose, enabling fine-grained manipulation of both scene dynamics and camera viewpoint. Our framework takes continuous world-time sequences and camera trajectories as conditioning inputs, injecting them into the video diffusion model through a 4D positional encoding in the attention layer and adaptive normalizations for feature modulation. To train this model, we curate a unique dataset in which temporal and camera variations are independently parameterized; this dataset will be made public. Experiments show that our model achieves robust real-world 4D control across diverse timing patterns and camera trajectories, while preserving high generation quality and outperforming prior work in controllability. See our website for video results: https://19reborn.github.io/Bullet4D/