EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Documenti analoghi

• FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
  di: Zhang, Zihui, et al.
  Pubblicazione: (2026)
• GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision
  di: Zhang, Zihui, et al.
  Pubblicazione: (2025)
• RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
  di: Wei, Shenxing, et al.
  Pubblicazione: (2025)
• unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
  di: Yang, Yafei, et al.
  Pubblicazione: (2025)
• OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
  di: Song, Ziyang, et al.
  Pubblicazione: (2024)