Research Interest

Generative Models. e.g., Image-to-Image Translation, Diffusion Models, Domain Adaptation, etc.
Multimodal Learning. e.g., Text-guided Image Manipulation, Audio-Visual Processing etc.

Also, I’m always trying to study various fields not stated above to facilitate interdisciplinary research.

Education

• Korea University, Seoul, Korea
  • M.S. Student in Computer Science and Engineering
  • Mar. 2021 - Feb. 2023
• Ewha Womans University, Seoul, Korea
  • B.S. in Electrical Engineering
  • Mar. 2016 - Feb. 2021

Experience

• Naver AI Lab, Gyeonggi, Korea
  • Research Intern
  • July. 2022 - Dec. 2022
  • Advisor: Jin-Hwa Kim, Jiyoung Lee
• Korea University CVLAB, Seoul, Korea
  • Undergraduate Researcher
  • July. 2020 - Feb. 2021
  • Advisor: Prof. Seungryong Kim
• Virginia Tech, VA, USA
  • Exchange Student
  • Jan. 2019 - May. 2019
• University of California, Davis (UC Davis), CA, USA
  • Exchange Student
  • Sep. 2018 - Dec. 2018

Publications

International Journal

InstaFormer++: Multi-Domain Instance-aware Image-to-Image Translation with Transformer

Soohyun Kim, Jongbeom Baek, Jihye Park, Eunjae Ha, Homin Jung, Taeyoung Lee, and Seungryong Kim
International Journal of Computer Vision,
To be appeared (Impact Factor: 13.369).

International Conference

Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation

Jihyun Kim, Changjae Oh, Hoseok Do, Soohyun Kim, Kwanghoon Sohn
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2024.

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

Jihye Park*, Sunwoo Kim*, Soohyun Kim*, Seokju Cho, Jaejun Yoo, Youngjung Uh, and Seungryong Kim
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2023.
[Project Page] [arXiv]

Robust Camera Pose Refinement for Multi-Resolution Hash Encoding

Hwan Heo, Taekyung Kim, Jiyoung Lee, Jaewon Lee, Soohyun Kim, Hyunwoo J. Kim, Jin-Hwa Kim
International Conference on Machine Learning (ICML), 2023.
[arXiv]

InstaFormer: Instance-aware Image-to-Image Translation with Transformer

Soohyun Kim, Jongbeom Baek, Jihye Park, Gyeongnyeon Kim, Seungryong Kim
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2022.
[Project Page] [arXiv]

Deep Translation Prior: Test-time Training for Photorealistic Style Transfer

Sunwoo Kim*, Soohyun Kim*, Seungryong Kim
AAAI Conference on Artificial Intelligence (AAAI), 2022.
[arXiv]

Preprints

Panoramic Image-to-Image Translation

Soohyun Kim, Junho Kim, Taekyung Kim, Hwan Heo, Seungryong Kim, Jiyoung Lee, Jin-Hwa Kim
ArXiv Preprint, 2023.
[arXiv]

Honors

• Korean Computer Vision Society, Feb. 2022
  • 34th Workshop on Image Processing and Image Understanding, Best Paper Award (Silver Prize)
• Korea Institute of Science and Technology Information (KISTI), Aug. 2018
  • 2018 AI School, KISTI Director Award

Skills

• Deep Learning, Machine Learning
  • Pytorch, Numpy
• Programming Languages
  • Python, C++