Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering
This addresses the critical barrier of real-time video generation for applications like embodied AI and VR/AR, though it is an incremental improvement focused on static scenes.
The paper tackles the computational inefficiency of diffusion-based video generation by proposing a method that generates sparse keyframes with diffusion, lifts them to 3D, and renders intermediate frames, achieving over 40x faster generation of 20-second videos while maintaining high visual quality.
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical barrier to deploying generative video in applications that require real-time interactions, such as embodied AI and VR/AR. This paper explores a new strategy for camera-conditioned video generation of static scenes: using diffusion-based generative models to generate a sparse set of keyframes, and then synthesizing the full video through 3D reconstruction and rendering. By lifting keyframes into a 3D representation and rendering intermediate views, our approach amortizes the generation cost across hundreds of frames while enforcing geometric consistency. We further introduce a model that predicts the optimal number of keyframes for a given camera trajectory, allowing the system to adaptively allocate computation. Our final method, SRENDER, uses very sparse keyframes for simple trajectories and denser ones for complex camera motion. This results in video generation that is more than 40 times faster than the diffusion-based baseline in generating 20 seconds of video, while maintaining high visual fidelity and temporal stability, offering a practical path toward efficient and controllable video synthesis.