• 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 (626)
    • 📝 논문리뷰 (616)
      • Computer Vision (401)
      • 3D Vision (126)
      • Audio & Speech (48)
      • NLP (49)
      • RL (15)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🔥 AI소식 (4)

    Recent posts

    [논문리뷰] REDUCIO! Generating 1024×1024 Video within 16 Seconds using Extremely Compressed Motion Latents

    2024년 12월 08일 

    Reducio 논문 리뷰

    Tags: Computer Vision, Diffusion, DiT, Microsoft, Text-to-Video

    [논문리뷰] MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

    2024년 12월 06일 

    MonST3R 논문 리뷰 (ICLR 2025 Spotlight)

    Tags: 3D Vision, DUSt3R, Google, ICLR, Monocular Depth Estimation, Pose Estimation

    [논문리뷰] Video Depth without Video Models

    2024년 12월 04일 

    RollingDepth 논문 리뷰

    Tags: Computer Vision, Diffusion, Monocular Depth Estimation

    [논문리뷰] CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

    2024년 12월 02일 

    CAT4D 논문 리뷰

    Tags: 3D Vision, Diffusion, Gaussian Splatting, Google, Novel View Synthesis

    [논문리뷰] CAT3D: Create Anything in 3D with Multi-View Diffusion Models

    2024년 11월 30일 

    CAT3D 논문 리뷰 (NeurIPS 2024 Oral)

    Tags: 3D Vision, Diffusion, Google, NeurIPS, Novel View Synthesis

    • Previous
    • 1
    • …
    • 14
    • 15
    • 16
    • 17
    • 18
    • 19
    • 20
    • …
    • 126
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.