AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond 文章

ArXiv CS.CV2026-05-26NEWSen作者: Haiming Zhang, Junfei Zhou, Feng Jiang, Jingzhong Li, Zhenglong Guo, Penglin Dai, Jifeng Dai, Yan Xie, Benjin Zhu
大语言模型
查看原文 →
关系图谱

AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond · 相关技术

相关技术

ORMtransformerssafetydivide-and-conquer partitioningautoregressiveUnifiedTokenScalaSPASEMSAFEReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPPONarrative Abstraction BenchmarkNPUNATMITMECIMUICTHISForEffort Metric AttentionENAEFIDiffusionDiffusion TransformerDiTCISANN3D bird's-eye view (BEV) object detectioniOS