AI Research 技术调研

标签: 3d-vision

此标签下有1条笔记。

  • 2026年7月16日

    Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud

    • jepa
    • self-supervised
    • point-cloud
    • 3d-vision
    • latent-prediction
    • non-generative
    • masking
    • representation-learning
    • transformer

  • GitHub