Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

Documenti analoghi

• Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
  di: Wang, Song, et al.
  Pubblicazione: (2024)
• A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
  di: Shi, Zhan, et al.
  Pubblicazione: (2025)
• DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
  di: Liu, Xiaolu, et al.
  Pubblicazione: (2026)
• Label-efficient Semantic Scene Completion with Scribble Annotations
  di: Wang, Song, et al.
  Pubblicazione: (2024)
• Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
  di: Kong, Lingdong, et al.
  Pubblicazione: (2024)