Sookwan (Andrew) Han
한수관

Hi! I was a student going to Carnegie Mellon University Robotics PhD. I am currently leading Affordance and AER.

Essays

See all essays →

Current Bet

  • Robot forms diverge, but Robot chips will standardize.
  • Robot chips will be in the form factor of Continual Learning Unit (CLU).
  • Robot chips (and robots enabled by them to learn and preserve physical knowledge) will be the Source of Sovereignty.

Progress

Affordance

* equal contribution; † corresponding author

SyncSDE teaser

SyncSDE: A Probabilistic Framework for Diffusion Synchronization

Hyunjun Lee*, Hyunsoo Lee*, Sookwan Han†

In CVPR 2025

[arXiv] [Project Page]

Probabilistic framework unifying diffusion synchronization.

Beyond the Contact teaser

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]

Novel representation that jointly models contact, orientation, and spatial affordances.

CHORUS teaser

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]

Scalable method for inferring how humans spatially interact with tools and objects.

Chupa teaser

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]

3D clothed human reconstruction from single images using diffusion-based carving on SMPL priors.

AER

1st place, AMD FPL'26 Agentic FPGA Backend Optimization Contest

1st of 91 teams · announced Sep 9, 2026

[Contest site] [AER →]

Misc

Browse Misc →