Introduction

I am a PhD student at KAIST, advised by Prof. Seungryong Kim. My main research interest is general perception in video, especially Track Any Point (or point tracking), and its application to the 3D/4D video understanding and reconstruction. I am closely working with Joon-Young Lee and Gabriel Huang at Adobe through a couple of internships, and before that, I collaborated with Google Research and Microsoft Research Asia (MSRA).

Before joining KAIST, I was a PhD student at Korea University and transferred to KAIST with my advisor. Prior to that, I received a B.S. degree from Yonsei University.

Education

• Korea Advanced Institute of Science and Technology (KAIST), Seoul, Korea
  • MS/PhD Integrated Student in Artificial Intelligence
  • Sep. 2024 - Present
• Korea University, Seoul, Korea
  • MS/PhD Integrated Student in Computer Science and Engineering
  • Mar. 2022 - Aug. 2024 (Transferred to KAIST with supervisor)
• Yonsei University, Seoul, Korea
  • BS in Computer Science
  • Mar. 2018 - Feb. 2022

Work Experience

• NVIDIA, Santa Clara, CA
  • Incoming Research Intern
• Adobe, San Jose, CA
  • Research Intern, June 2024 - Sep. 2024
  • Worked on 3D point tracking, aiming to understand 3D structure from 2D trajectory; submitted to CVPR 2025.
  • Mentor: Gabriel Huang, Joon-Young Lee
• Adobe, San Jose, CA
  • Research Intern, June 2023 - Sep. 2023
  • Conducted research on long-range dense tracking, leading to the publication of ‘Revisiting Optical Flow for Long-Range Dense Tracking’ at CVPR 2024.
  • Mentor: Joon-Young Lee, Gabriel Huang

Publications

Seurat: From Moving Points to Depth

Seokju Cho, Jiahui Huang, Seungryong Kim, Joon-Young Lee
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2025.

Exploring Temporally-Aware Features for Point Tracking

Inès Hyeonsu Kim*, Seokju Cho*, Jiahui Huang, Jung Yi, Joon-Young Lee, Seungryong Kim
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2025.
[Project Page] [arXiv]

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.
[Project Page] [arXiv]

Multi-Granularity Video Object Segmentation

Sangbeom Lim*, Seongchan Kim*, Seungjun An*, Seokju Cho, Paul Hongsuck Seo, Seungryong Kim
AAAI Conference on Artificial Intelligence (AAAI), 2025.
[Project Page] [arXiv]

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
Neural Information Processing Systems (NeurIPS), 2024.
[Project Page] [arXiv]

Local All-Pair Correspondence for Point Tracking

Seokju Cho, Jiahui Huang, Jisu Nam, Honggyu An, Seungryong Kim, and Joon-Young Lee
European Conference on Computer Vision (ECCV), 2024.
[Project Page] [arXiv]

FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

Seokju Cho, Jiahui Huang, Seungryong Kim, and Joon-Young Lee
IEEE Conference Computer Vision Pattern Recognition (CVPR), 2024.
[arXiv]

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

Seokju Cho*, Heeseong Shin*, Sunghwan Hong, Anurag Arnab, Paul Hongsuck Seo, and Seungryong Kim
IEEE Conference Computer Vision Pattern Recognition (CVPR), Highlight (2.8% Acceptance Rate), 2024.
[Project Page] [arXiv]

Unifying Feature and Cost Aggregation with Transformers for Dense Correspondence

Sunghwan Hong*, Seokju Cho*, Seungryong Kim, and Stephen Lin
International Conference on Learning Representations (ICLR), 2024.

DäRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation

Jiuhn Song*, Seonghoon Park*, Honggyu An*, Seokju Cho, Min-Seop Kwak, Sungjin Cho, and Seungryong Kim
Neural Information Processing Systems (NeurIPS), 2023.
[Project Page] [arXiv]

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]

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 Page] [arXiv]

CATs++: Boosting Cost Aggregation with Convolutions and Transformers

Seokju Cho*, Sunghwan Hong*, and Seungryong Kim
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2023 (Impact Factor: 24.314).
[Project Page] [arXiv]

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, and Seungryong Kim
Neural Information Processing Systems (NeurIPS), 2022.
[Project Page] [arXiv]

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Sunghwan Hong*, Seokju Cho*, Jisu Nam, Stephen Lin, and Seungryong Kim
European Conference on Computer Vision (ECCV), 2022.
[Project Page] [arXiv]

CATs: Cost Aggregation Transformers for Visual Correspondence

Seokju Cho*, Sunghwan Hong*, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn, and Seungryong Kim
Neural Information Processing Systems (NeurIPS), 2021.
[Project Page] [arXiv] [Github]

Preprints

Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification

Inès Hyeonsu Kim, JoungBin Lee, Soowon Son, Woojeong Jin, Kyusun Cho, Junyoung Seo, Min-Seop Kwak, Seokju Cho, JeongYeol Baek, Byeongwon Lee, Seungryong Kim
ArXiv Preprint, 2024.
[arXiv]

Academic Services

Reviewer

• 2024 - CVPR
• 2023 - CVPR, NeurIPS

Honors

• Google, June, 2024
  • Google East Asia Student Travel Grants for CVPR
• Ministry of Science and ICT & National IT Industry Promotion Agency, Sep. 2021
  • AI Online Competition, 3rd Place Award, Won 300M KRW