Jihun Park

Hi, I'm Jihun Park, a M.S.-Ph.D. integrated course student at the Department of Artificial Intelligence at DGIST, South Korea. I am conducting my research under the supervision of Prof. Sunghoon Im at the DGIST Computer Vision Lab.

Previously, I earned a B.S. degree from the Department of Mechanical engineering, Zhejiang University, in 2022, and My research interest is computer vision and deep learning, with a particular emphasis on solving Autoregressive Image/Video Generation, Style Transfer, and Vision-Language Task.


Email  /  Linkedin  /  Google Scholar  /  Github  /  OpenReview  /  📄Curriculum Vitae

profile photo profile photo hover
News

2025

  • 2025-12: Started a Generative Model Research Intern position at the Global Business Unit of Baidu Inc. (3 months).
  • 2025-11: AI-driven artworks by our research team exhibited at DGIST Gallery (Nov. 2025 - Feb. 2026). View the curation
  • 2025-11: One paper accepted to AAAI 2026 as an oral paper.
  • 2025-10: I will serve as a Generative Model Research Intern at the Global Business Unit of Baidu Inc. for three months.
  • 2025-10: I received the Best Oral Presentation Award from the DGIST EECS/AI.
    • 2025-07: One paper accepted to ICCV 2025 workshop.
  • 2025-07: I attended ICVSS 2025 in Sicily, Italy.
  • 2025-02: One paper accepted to CVPR 2025 as a highlight paper.

    • 2024

  • 2024-10: One paper accepted to ACCV 2024.
  • 2024-02: Our team received the Encouragement Prize from the 30th Samsung Human-Tech Paper Award.

    • Publications

    * indicates equal contribution.
    † indicates the corresponding author.
    Some papers are highlighted.



    A Training-Free Style-Personalization via SVD-Based Feature Decomposition
    Kyoungmin Lee*, Jihun Park*, Jongmin Gim*, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Sunghoon Im†
    (arXiv 2025)
    [Paper]
    ICCV25 A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model
    Jihun Park*, Jongmin Gim*, Kyoungmin Lee*, Minseok Oh, Minwoo Choi, Jaeyeul Kim, Woo Chool Park, Sunghoon Im†
    (arXiv 2025)
    [Paper]
    bmvc25 Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation
    Sanggyun Ma*, Wonjoon Choi*, Jihun Park*, Jaeyeul Kim, Seunghun Lee, Jiwan Seo, Sunghoon Im†
    (arXiv 2025)
    [Paper]
    ICCV25 Infinite-Story: A Training-Free Consistent Text-to-Image Generation (Oral paper)
    Jihun Park*, Kyoungmin Lee*, Jongmin Gim*, Hyeonseo Jo, Minseok Oh, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Minwoo Choi, Sunghoon Im†
    The 40th Annual AAAI Conference on Artificial Intelligence,(AAAI), 2026
    [Paper]
    bmvc25 Semantic-Enhanced Monocular Depth Estimation via Fusion and Distillation of Foundation Models
    Sanggyun Ma*, Wonjoon Choi*, Jihun Park, Jaeyeul Kim, Sunghoon Im†
    International Conference on Computer Vision workshop (ICCVw), 2025
    CVPR teaser Style-Editor: Text-driven object-centric style editing (Highlight paper, Top 3.7%)
    (Encouragement Prize in 30th HumanTech Paper Award)
    Jihun Park*, Jongmin Gim*, Kyoungmin Lee*, Seunghun Lee, Sunghoon Im†
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    [Paper] [Project Page] [Code]
    ACCV teaser Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders
    Jongmin Gim*, Jihun Park*,Kyoungmin Lee*, Sunghoon Im†
    17th Asian Conference on Computer Vision (ACCV), 2024
    [Paper]
    Education & Work Experience


    dise Generative Model Research Intern (Advisor: Yan Zhang)
    Baidu Global Business Unit , Shenzhen, China
    (Dec. 2025 - Present)
    dise M.S.-Ph.D. Integrated Course (Advisor: Sunghoon Im)
    Department of Artificial Intelligence, DGIST, South Korea
    (Mar. 2023 - Present)
    dise Bachelor's Degree
    Department of Mechanical Engineering, Zhejiang University, China
    (Sep. 2018 - Jul. 2022)
    dise Chungnam Samsung Academy, South Korea
    (Mar. 2015 - Feb. 2018)
    Academic Activities

    Honors & Awards

  • Best Oral Presentation Award, DGIST EECS/AI student conference, Oct. 2025
  • Encouragement Prize, 30th HumanTech Paper Award, Samsung Electronics Co., Ltd, Feb. 2024

    • Reviewer

  • The Association for the Advancement of Artificial Intelligence (AAAI), 2026
  • The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

    • Teaching

  • Invited speaker of DGIST Generative AI Integrated Seminar,Oct. 2024
  • Teaching Assistant (TA), Advanced Deep Learning, Mar-Jun 2024

    • Other Experiences

  • Exhibition of our team's research on AI-driven art at DGIST, Nov. 2025 - Feb. 2026
  • Attended to International Computer Vision Summer School (ICVSS 2025) in Sicily, Italy, Jul. 2025
  • Selected to represent DGIST at the official institutional booth during the 2025 Korea Science Festival, Apr. 2025


    • Website Template


    ©Jihun Park | Last updated: Jul 15, 2025