AutoScape: Geometry-Consistent Long-Horizon Scene Generation
Jiacheng Chen, Ziyu Jiang, Mingfu Liang, Bingbing Zhuang, Jong-Chyi Su, Sparsh Garg, Ying Wu, Manmohan Chandraker
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.
BibTeX
@InProceedings{Chen_2025_ICCV,
author = {Chen, Jiacheng and Jiang, Ziyu and Liang, Mingfu and Zhuang, Bingbing and Su, Jong-Chyi and Garg, Sparsh and Wu, Ying and Chandraker, Manmohan},
title = {AutoScape: Geometry-Consistent Long-Horizon Scene Generation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2025},
pages = {25700-25711}
}