ARTE Group

CVPR 2025

Generating Multimodal Driving Scenes via Next-Scene Prediction

UMGen: Next-scene prediction for multimodal driving scene generation

Yanhao Wu Haoyang Zhang Tianwei Lin Lichao Huang Shujie Luo Rui Wu Congpei Qiu Wei Ke Tong Zhang

CVPR ยท 2025

Paper Project Page
Generating Multimodal Driving Scenes via Next-Scene Prediction teaser image

Video Gallery

Teaser Video

Official teaser video of UMGen.

Citation

@InProceedings{Wu_2025_CVPR,
    author    = {Wu, Yanhao and Zhang, Haoyang and Lin, Tianwei and Huang, Lichao and Luo, Shujie and Wu, Rui and Qiu, Congpei and Ke, Wei and Zhang, Tong},
    title     = {Generating Multimodal Driving Scenes via Next-Scene Prediction},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2025},
    pages     = {6844-6853}
}