CVPR 2025 / 神经仿真

Generating Multimodal Driving Scenes via Next-Scene Prediction

作者：Yanhao Wu, Haoyang Zhang, Tianwei Lin, Lichao Huang, Shujie Luo, Rui Wu, Congpei Qiu, Wei Ke, Tong Zhang · 单位：School of Software Engineering, XJTU, School of Computer and Communication Sciences, EPFL, University of Chinese Academy of Sciences · 会议/期刊：CVPR 2025 · 方向：神经仿真 · 发布日期：2025

世界模型3D/4D建模视频生成自动驾驶仿真
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
Generating Multimodal Driving Scenes via Next-Scene Prediction figure
AlphaXiv 中文概览（可滚动查看）