COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation

Documenti analoghi

• OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation
  di: Che, Yuchen, et al.
  Pubblicazione: (2024)
• Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection
  di: Takeda, Koji, et al.
  Pubblicazione: (2024)
• Embodied Navigation with Auxiliary Task of Action Description Prediction
  di: Kondoh, Haru, et al.
  Pubblicazione: (2025)
• Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models
  di: Yajima, Masaru, et al.
  Pubblicazione: (2025)
• FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models
  di: Wu, Kuanting, et al.
  Pubblicazione: (2025)