About Me

I am a Ph.D. student at KAIST AI under the supervision of Professor Seungryong Kim. My research interests are broadly in the fields of machine learning and computer vision.
I have been interested in image matching, semi/self-supervised learning, and lately, I have been focusing on large-scale generative models like diffusion models for video, 3D, and 4D representations. If you have any questions or are interested in collaborating, please feel free to contact me!

Experience

  • Research Scientist Intern (Meta, Reality Lab, London)
    • Mar. 2025 - Sep. 2025
  • Research Scientist Intern (Sony AI, Remote)
    • Mar. 2024 - May 2024
  • Research Scientist Intern (Sony AI, Tokyo)
    • Dec. 2023 - Mar. 2024
  • Visiting Researcher (Queen Mary University of London)
    • Jun. 2023 - Aug. 2023

News

  • Jun 2025 / Vid-CamEdit and D^2USt3R are out on arXiv!
  • Mar 2025 / Started as a Research Scientist Intern at Meta Reality Labs!

Featured Publications

For all publications, please refer here.

International Conferences / Journals

D2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

Jisang Han, Honggyu An, Jaewoo Jung, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim
Neural Information Processing Systems (NeurIPS), 2025.
[Project] [Link]

DiffFace: Diffusion-based Face Swapping with Facial Guidance

Kihong Kim, Yunho Kim, Seokju Cho, Junyoung Seo, Jisu Nam, Kychul Lee, Seungryong Kim, Kwanghee Lee
Pattern Recognition (PR), 2025.
[Link]

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

Junyoung Seo, Kazumi Fukuda, Takashi Shibuya, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim, and Yuki Mitsufuji
Neural Information Processing Systems (NeurIPS), 2024.
[Project] [Link]

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Junyoung Seo*, Susung Hong*, Wooseok Jang*, Hyeonsu Kim, Minseop Kwak, Doyup Lee, and Seungryong Kim
International Conference on Machine Learning (ICML), 2024.
[Project] [Link]

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Junyoung Seo*, Wooseok Jang*, Min-Seop Kwak*, Jaehoon Ko, Hyeonsu Kim, Junho Kim, Jin-Hwa Kim, Jiyoung Lee, and Seungryong Kim
International Conference on Learning Representations (ICLR), 2024.
[Project] [Link]

Depth-Aware Guidance with Self-Estimated Depth Representations of Diffusion Models

Gyeongnyeon Kim, Wooseok Jang, Gyuseong Lee*, Susung Hong, Junyoung Seo, and Seungryong Kim
Pattern Recognition (PR), 2023.

MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation

Junyoung Seo*, Gyuseong Lee*, Seokju Cho, Jiyoung Lee, Seungryong Kim
AAAI Conference on Artificial Intelligence (AAAI), 2023.
[Project] [Link]

ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization

Jiwon Kim*, Yeongjo Min*, Daehwan Kim*, Kwangrok Ryoo, Gyuseong Lee, Junyoung Seo, and Seungryong Kim
European Conference on Computer Vision (ECCV), 2022.
[Link]

Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels

Jiwon Kim*, Kwangrok Ryoo*, Junyoung Seo*, Gyuseong Lee* , Daehwan Kim, Hansang Cho, and Seungryong Kim
IEEE Conf. Computer Vision Pattern Recognition (CVPR), 2022
[Link]

Academic Services

Reviewer

  • NeurIPS, ICLR, TPAMI, CVPR, ICCV, ECCV and AAAI

Honors

  • Award for Academic Excellence
    • 1st Semester of 2021, 2st Semester of 2020, and 1st Semester of 2020
    • Korea University, Korea
  • KEPCO Scholarship
    • Korea Electric Power Corporation, Korea (Mar. 2021)
  • 3rd Prize, Barrier-free App Development Contest
    • Incorporated Association GreenLight and HYUNDAI AutoEver, Korea (Feb. 2021)
  • Special Award in Self-driving RC Car Development. Korea Embedded Software Contest
    • HYUNDAI MOBIS, Korea (Jan. 2021)
  • Professor’s Association(Seokrimhoe) Scholarship
    • Korea University, Korea (Sep. 2020)
  • Grand Prize in App Development, SK Smarteen App Challenge
    • SK, Korea (Dec. 2013)

Projects

  • Automation of Deep Learning Model Update Using Unlabeled Data
    • Samsung Electro-Mechanics (2021-2022)

Skills

  • Deep Learning, Machine Learning
    • Pytorch, Numpy
  • Programming Languages
    • Python, JavaScript, C/C++
  • Framework and Tool
    • Flutter, MATLAB