PERSONAL RESEARCH PROFILE

Joonkyu Park

Computer Vision Researcher

Seoul National University · CV Lab Seoul, Republic of Korea

jkpark0825@snu.ac.kr GitHub Google Scholar

CURRICULUM VITAE Download CV PDF Document ↓

Personal Information

Please click for the details

I am a computer vision researcher at Seoul National University, working under the supervision of Prof. Kyoung Mu Lee. My research focuses on generative image restoration, 3D vision, and human-centric visual intelligence.

Research Interests

Image Restoration & Diffusion Models
3D Vision & Gaussian Splatting
Human-Object Interaction

Get in touch

jkpark0825@snu.ac.kr

Open to research collaboration and academic discussion.

Selected Publications

ECCV, 2026.

Learning to Corrupt for Better Restoration

Joonkyu Park, Wooseok Lee, Jaeha Kim, Sehoon Kim, Bokyeung Lee, and Kyoung Mu Lee

ICLR, 2026.

Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution

Joonkyu Park, and Kyoung Mu Lee

ICCVW, 2025.

Mars2 2025 challenge on multimodal reasoning

Peng Xu, Shengwu Xiong, Jiajun Zhang, Yaxiong Chen, Bowen Zhou, Chen Change Loy, ..., Joonkyu Park (121 additional authors)

NeurIPS, 2024.

A 3D Scene-Based Dataset for Realistic Image Deblurring

Dongwoo Lee, Joonkyu Park, and Kyoung Mu Lee.

ECCV, 2024.

3D Hand Sequence Recovery from Real Blurry Images and Event Stream

Joonkyu Park, Gyeongsik Moon, Weipeng Xu, Evan Kaseman, Takaaki Shiratori, and Kyoung Mu Lee

ArXiv, 2024.

Rethinking RGB Color Representation for Image Restoration Models

Jaerin Lee, Joonkyu Park, Sungyong Baik, Kyoung Mu Lee

SPL, 2023.

Adaptive Context and Latent Information Blending for Face Image Inpainting

Joonkyu Park, Cheeun Hong, Sungyong Baik, and Kyoung Mu Lee

ICCVW (Oral), 2023.

Extract-and-Adaptation Network for 3d Interacting Hand Mesh Recovery

Joonkyu Park*, Daniel Sungho Jung*, Gyeongsik Moon*, and Kyoung Mu Lee.

ICCV, 2023.

Content-Aware Local Gan for Photo-Realistic Super-Resolution

Joonkyu Park, Sanghyun Son, and Kyoung Mu Lee.

CVPR, 2023.

Recovering 3d Hand Mesh Sequence from a Single Blurry Image. A new dataset and temporal unfolding

Yeonguk Oh*, Joonkyu Park*, Jaeha Kim*, Gyeongsik Moon, and Kyoung Mu Lee.

arXiv 2022.

Pay Attention to Hidden States for Video Deblurring, Ping-pong Recurrent Neural Networks and Selective Non-Local Attention

Joonkyu Park, Seungjun Nah, and Kyoung Mu Lee.

CVPR, 2022.

Occlusion-Robust 3d Hand Mesh Estimation Network

Joonkyu Park, Yeonguk Oh, Gyeongsik Moon, Hongsuk Choi, and Kyoung Mu Lee

CVPR, 2022.

Learning to Estimate Robust 3d Human Mesh from in-the-wild Crowded Scenes

Hongsuk Choi, Gyeongsik Moon, Joonkyu Park, and Kyoung Mu Lee.

BMVC, 2021.

Recurrence-in-Recurrence Networks for Video Deblurring

Joonkyu Park, Seungjun Nah, and Kyoung Mu Lee.

Selected Projects

IAC-IR

with Samsung MX

DM-SR

EBH Dataset

with Meta Reality Lab

Controllable ISP

with Samsung AI Center