BulletTime：视频生成中时间与相机位姿的解耦控制
BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
把世界时间与相机轨迹作为独立条件，通过注意力层中的 4D 位置嵌入和自适应归一化注入视频扩散模型，为需要精确相机运镜与慢动作/时间重映射的可控视频生成提供了可复用的条件注入方案。
原文依据 injecting them into the video diffusion model through a 4D positional embedding in the attention layer and adaptive normalizations for feature modulation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论新兴的视频扩散模型能够达到很高的视觉保真度，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与时间控制的能力。我们提出一个 4D 可控的视频扩散框架，显式地将场景动态与相机位姿解耦，从而能够对场景动态和相机视角进行细粒度操控。该框架以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 位置嵌入以及用于特征调制的自适应归一化，将它们注入视频扩散模型。为训练该模型，我们构建了一个独特的数据集，其中时间变化与相机变化被独立参数化。实验表明，我们的模型在多样的时间模式与相机轨迹下实现了稳健的真实世界 4D 控制，同时保持高生成质量，并在可控性上优于先前工作。
英文原文摘要 980 字符
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 embedding 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. 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.