Sanghyeon Lee

Publications

(C: Conferences, W: Workshops, *: Equal contribution)

[C3]: iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer

• Jooyeol Yun*, Sanghyeon Lee*, Minho Park*,  and Jaegul Choo

• IEEE Winter Conference on Applications of Computer Vision(WACV), 2023, Round 1 Accept (22% acceptance rate).

[C2]: Deep Edge-Aware Interactive Colorization against Color Bleeding Effects 

• Eungyeup Kim*, Sanghyeon Lee*, Jeonghoon Park*,  Somi Choi, Choonghyun Seo, and Jaegul Choo

• IEEE International Conference on Computer Vision(ICCV), 2021,  Accepted as Oral Presentation (3% acceptance rate). 

[C1]: Efficient Adversarial Audio Synthesis via Progressive Upsampling 

• Youngwoo Cho*, MinwookChang*, Sanghyeon Lee, Hyoungwoo Lee, Gerard Jounghyun Kim and Jaegul Choo

• IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2020 (48.0% acceptance rate). 

Under Review

Recalibrating Color-Collapse in Point-Interactive Colorization by Localizing Hint Regions

• Sanghyeon Lee, Jooyeol Yun,  and Jaegul Choo

Learning How One Edits: Multi-style Photo Enhancement via 3D Lookup Tables

• Jooyeol Yun*, Sanghyeon Lee*,  Minho Park*,  and Jaegul Choo

Education

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, Sep. 2021- Present

 Ph.D. in Artificial Intelligence

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, Sep. 2019 - Oct. 2021

 M.S. in Artificial Intelligence

Seoul National University, Seoul, Korea, Mar. 2011 - Feb. 2018 

B.A. in Economics

Award

Best Poster Award, KAIST AI Workshop, 2022  

Silver medalist at Korean Chemistry Olympiad (KCHO), 2006 & 2007

Research Interest 

• Personalized deep learning

• Computational photography 

• Human in the loop AI  

• Image & Sketch colorization