No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learning

Documenti analoghi

• FP3: A 3D Foundation Policy for Robotic Manipulation
  di: Yang, Rujia, et al.
  Pubblicazione: (2025)
• EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation
  di: Dong, Zibin, et al.
  Pubblicazione: (2025)
• CL3R: 3D Reconstruction and Contrastive Learning for Enhanced Robotic Manipulation Representations
  di: Cui, Wenbo, et al.
  Pubblicazione: (2025)
• ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
  di: Lu, Guanxing, et al.
  Pubblicazione: (2024)
• BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
  di: Li, Peiyan, et al.
  Pubblicazione: (2025)