StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
This work addresses the challenge of generating realistic street views for autonomous driving applications, representing an incremental improvement by integrating generative priors into dynamic scene representations.
The paper tackles the problem of photorealistic view synthesis from vehicle sensor data, where performance degrades with viewpoint deviations, by introducing StreetCrafter, a controllable video diffusion model that uses LiDAR point cloud renderings as pixel-level conditions, enabling flexible viewpoint control and outperforming existing methods on datasets like Waymo Open Dataset and PandaSet.
This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the performance significantly degrades as the viewpoint deviates from the training trajectory. To mitigate this problem, we introduce StreetCrafter, a novel controllable video diffusion model that utilizes LiDAR point cloud renderings as pixel-level conditions, which fully exploits the generative prior for novel view synthesis, while preserving precise camera control. Moreover, the utilization of pixel-level LiDAR conditions allows us to make accurate pixel-level edits to target scenes. In addition, the generative prior of StreetCrafter can be effectively incorporated into dynamic scene representations to achieve real-time rendering. Experiments on Waymo Open Dataset and PandaSet demonstrate that our model enables flexible control over viewpoint changes, enlarging the view synthesis regions for satisfying rendering, which outperforms existing methods.