From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding

Documenti analoghi

• GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond
  di: Halacheva, Anna-Maria, et al.
  Pubblicazione: (2025)
• Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
  di: Halacheva, Anna-Maria, et al.
  Pubblicazione: (2024)
• ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models
  di: Dey, Sombit, et al.
  Pubblicazione: (2024)
• Occam's LGS: An Efficient Approach for Language Gaussian Splatting
  di: Cheng, Jiahuan, et al.
  Pubblicazione: (2024)
• SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
  di: Nikolov, Nikolay, et al.
  Pubblicazione: (2025)