Abstract
This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically consistent keyframes, serving as reliable anchors for the scene's appearance and geometry. To maintain long-range geometric consistency, the model 1) jointly handles image and depth in a shared latent space, 2) explicitly conditions on the existing scene geometry (i.e., rendered point clouds) from previously generated keyframes, and 3) steers the sampling process with a warp-consistent guidance. Given high-quality RGB-D keyframes, a video diffusion model then interpolates between them to produce dense and coherent video frames. AutoScape generates realistic and geometrically consistent driving videos of over 20 seconds, improving the long-horizon FID and FVD scores over the prior state-of-the-art by 48.6\% and 43.0\%, respectively.
Abstract (translated)
本文提出了AutoScape，这是一种长时域驾驶场景生成框架。其核心是一个新颖的RGB-D扩散模型，该模型通过迭代生成稀疏、几何一致的关键帧，这些关键帧作为场景外观和几何结构的可靠锚点。为了维持长距离几何一致性，模型采用了以下策略：1）在共享潜在空间中同时处理图像和深度信息；2）明确地以先前生成的关键帧中存在的场景几何（即渲染后的点云）为条件；3）使用一致变形引导来指导采样过程。基于高质量的RGB-D关键帧，随后的视频扩散模型会在这之间进行插值运算，从而产生密集且连贯的视频帧。AutoScape能够生成超过20秒的真实感和几何一致性良好的驾驶视频，在长时域FID（Fréchet Inception Distance）和FVD（Feature Voxel Distance）评分上分别比之前的最佳方法提高了48.6% 和 43.0%。
URL
https://arxiv.org/abs/2510.20726
