Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding

Documenti analoghi

• SA3DIP: Segment Any 3D Instance with Potential 3D Priors
  di: Yang, Xi, et al.
  Pubblicazione: (2024)
• SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
  di: Xu, Mutian, et al.
  Pubblicazione: (2023)
• DAG: Unleash the Potential of Diffusion Model for Open-Vocabulary 3D Affordance Grounding
  di: Wang, Hanqing, et al.
  Pubblicazione: (2025)
• Open-Vocabulary Octree-Graph for 3D Scene Understanding
  di: Wang, Zhigang, et al.
  Pubblicazione: (2024)
• Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding
  di: Tai, Hanchen, et al.
  Pubblicazione: (2024)