DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion 事件

DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion arXiv:2510.15264v3 Announce Type: replace Abstract: We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either suffer from prohibitive computational demands for extended temporal generation, focus exclusively on prolonged video synth