DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving

Documenti analoghi

• VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
  di: Zhang, Haiming, et al.
  Pubblicazione: (2024)
• SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
  di: Zhang, Haiming, et al.
  Pubblicazione: (2025)
• Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities
  di: Yan, Xu, et al.
  Pubblicazione: (2024)
• D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow
  di: Zhang, Haiming, et al.
  Pubblicazione: (2024)
• DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
  di: Min, Chen, et al.
  Pubblicazione: (2024)