Sookwan Han
한수관

My endgame is to lead humanity to eternal prosperity, no matter the adversity.  
[Show More]

Hi! I'm an undergraduate student at Seoul National University, majoring in Electrical and Computer Engineering.

I am leading team ROUND.

Contact me if you are interested in my goals! jellyheadandrew@snu.ac.kr




[News]
  • Jun 2025 I'm going to YC AI startup school. See you in San Francisco
[Show More]

Publications

stereo

* equal contribution
project lead

SyncSDE: A Probabilistic Framework for Diffusion Synchronization
Hyunjun Lee*, Hyunsoo Lee*, Sookwan Han
In CVPR 2025
[arXiv] [Project Page]

stereo

* equal contribution

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
Hyeonwoo Kim*, Sookwan Han*, Patric Kwon, Hanbyul Joo
In ECCV 2024 as Oral Presentation
[arXiv] [Project Page] [Code]

stereo

Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images
Sookwan Han, Hanbyul Joo
In ICCV 2023 as Oral Presentation
[arXiv] [Project Page] [Code]

stereo

* equal contribution

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models
Byungjun Kim*, Patric Kwon*, Kwangho Lee, Myunggi Lee, Sookwan Han, Daesik Kim, Hanbyul Joo
In ICCV 2023 as Oral Presentation
[arXiv] [Project Page] [Code]

Affiliation

Seoul National University

Undergraduate

Major: Electrical and Computer Engineering
Student Body President of SNU ECE (2022)

Seoul Science High School

Graduated

Major: Math, Physics

Research/Work Experience

Visual Computing Lab

Intern

2022.03 - 2023.11

Advisor: Hanbyul Joo
Research Area: Human-Object Interaction
Our research focuses on advancing machine perception by developing algorithms and models that enable machines to accurately understand and perceive the interactions between humans and objects.
* I have given a short lecture on diffusion models during internship: you can see the materials here.

VLSI Lab

Intern

2021.09 - 2022.02

Advisor: Jaejoon Kim
Research Area: Quantized/Compressed Neural Networks
Our research focuses on quantizing and compressing neural networks, with a particular emphasis on transformers. The goal is to optimize their performance specifically for embedded devices.

Honors/Awards

Physics Expert Certification

2023.08

Korean Physical Society
Certified as Expert in all fields

SNU FastMRI Challenge

2023.07 - 2023.08

SNU Dept. of Electrical & Computer Engineering
Won 1st place (out of 144 teams, Team Captain)
Kudos to Teammates: Junsung

Heart Disease AI Datathon

2021.11 - 2021.12

Ministry of Science and ICT, National Information Society Agency, SNU College of Medicine, Yonsei Office of Research Affairs
Received Grand Prize (out of 169 teams, Team Captain)
Kudos to Teammates: Sooho, Hoo, Hohun

University Mathematics Competition

2020.11

Korean Mathematical Society
Received Gold Prize

Scholarships

Google Travel Grants

2023, 2024

Google
Support for attending AI conferences (ICCV, ECCV)

Presidential Science Scholarship

2020.03 - Present

Korea Student Aid Foundation (KOSAF)
Full scholarship for undergraduate studies and additional living expenses support