• Skip to primary navigation
  • Skip to content
  • Skip to footer
전생했더니 인공지능이었던 건에 대하여
  • Tags

    JiYeop Kim

    Diffusion은 신이고 GPT는 무적이다

    • Seoul, Korea
    • GitHub
    • Email
    • 📂 전체 게시글 (751)
    • 📝 논문리뷰 (715)
      • Computer Vision (433)
      • 3D Vision (179)
      • NLP (62)
      • Audio & Speech (48)
      • RL (25)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🎮 GAME (30)

    Recent posts

    [논문리뷰] Depth Anything 3: Recovering the Visual Space from Any Views

    2025년 11월 21일 

    Depth Anything 3 (DA3) 논문 리뷰

    Tags: 3D Reconstruction, 3D Vision, Gaussian Splatting, Monocular Depth Estimation, Novel View Synthesis, Pose Estimation

    [논문리뷰] Scalable Autoregressive Monocular Depth Estimation

    2025년 11월 19일 

    Depth AutoRegressive Model (DAR) 논문 리뷰 (CVPR 2025)

    Tags: Autoregressive, Computer Vision, CVPR, Monocular Depth Estimation

    [논문리뷰] Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction

    2025년 11월 17일 

    Rig3R 논문 리뷰

    Tags: 3D Reconstruction, 3D Vision, DUSt3R, Pose Estimation

    [논문리뷰] D-Attn: Decomposed Attention for Large Vision-and-Language Models

    2025년 11월 15일 

    Decomposed Attention (D-Attn) 논문 리뷰 (ICCV 2025)

    Tags: Computer Vision, ICCV, Large Multimodal Model

    [논문리뷰] Efficient Track Anything

    2025년 11월 13일 

    EfficientTAM 논문 리뷰 (ICCV 2025)

    Tags: Computer Vision, ICCV, Meta, Video Object Segmentation

    • Previous
    • 1
    • 2
    • 3
    • 4
    • 5
    • …
    • 151
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.