BulletTime: 分离时间与相机姿态的视频生成控制
BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
AI总结：
BulletTime通过分离时间与相机姿态，实现了视频生成的精细控制与高质量生成。
摘要：
新兴的视频扩散模型能够实现高视觉保真度，但本质上将场景动态与相机运动耦合在一起，限制了其提供精确空间和时间控制的能力。我们提出了一种4D可控的视频扩散框架，该框架明确地将场景动态与相机姿态分离，使能够对两者进行精细操控。我们的框架将连续的世界时间序列和相机轨迹作为条件输入，通过注意力层中的4D位置编码和自适应归一化对特征进行调制，将它们注入视频扩散模型中。为了训练此模型，我们整理了一个独特的数据集，在其中时间变化和相机变化被独立参数化；这个数据集将公开。实验表明，我们的模型在多种时间模式和相机轨迹下实现了稳健的4D控制，同时保持了高质量的生成效果，并在可控性方面优于先前的工作。请查看我们的网站获取视频结果：https://19reborn.github.io/Bullet4D/
英文摘要：
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 codes and video results: https://19reborn.github.io/Bullet4D/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
