Personal Information

2023, Dec 12    

I am Ph.D candidate advised by Prof. Kyoung Mu Lee. I am interested in deep learning and computer vision, exploring human 3D reconstruction and image restoration, combining high-level and low-level tasks in my recent research. I am currently dedicated to crafting images that match common visuals and reconstructing 3D human forms from severely degraded images.

Education

  • 2021-present : Integrated Ph.D. program, Electrical & Computer Engineering, Seoul National University.
  • 2015–2021 : Bachelor of Engineering, Electrical and Computer Engineering, Seoul National University.

Publications

  • Joonkyu Park , Cheeun Hong, Sungyong Baik, and Kyoung Mu Lee, “Colanet: Adaptive context and latent information blending for face image inpainting”, SPL, 2023.
  • Joonkyu Park* , Daniel Sungho Jung*, Gyeongsik Moon*, and Kyoung Mu Lee, “Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery”, ICCVW (Oral), 2023. [paper]
  • Joonkyu Park , Sanghyun Son, and Kyoung Mu Lee, “Content-Aware Local GAN for Photo-Realistic Super-Resolution”, ICCV, 2023. [paper]
  • Yeonguk Oh*, Joonkyu Park*, Jaeha Kim*, Gyeongsik Moon, and Kyoung Mu Lee, “Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding”, CVPR, 2023. [paper]
  • Joonkyu Park*, Seungjun Nah, and Kyoung Mu Lee, “Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention”, arXiv:2203.16063, 2022.[paper]
  • Joonkyu Park, Yeonguk Oh*, Gyeongsik Moon*, Hongsuk Choi, and Kyoung Mu Lee, “HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network,” CVPR, 2022.[paper]
  • Hongsuk Choi, Gyeongsik Moon, Joonkyu Park, and Kyoung Mu Lee, “Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes,” CVPR, 2022.[paper]
  • Joonkyu Park, Seungjun Nah, and Kyoung Mu Lee, “Recurrence-in-Recurrence Networks for Video Deblurring”, BMVC, 2021.[paper] [supple]

Research Experience

Reality Labs Research at Meta
  • 3D recovery from specific targets.
Seoul National University
  • Research Project with Samsung Research: Tunable SW ISP Algorithm.
  • Research Project with Samsung Research: Domain Adaptation for Oven Recipes.
  • College TA: Topics in Control and Automation.
  • 9th Creative Design Festival: Untact AR Makeup.
  • Electrical Engineering Design Project: AE (Adversarial Examples) Generation with GAN.

Invited Talks

  • AI Retreat, SNU, Recovering 3d hand mesh sequence from a single blurry image: A new dataset and temporal unfolding, 2024.
  • Qualcomm Korea, Occlusion-Robust 3D Hand Mesh Estimation Network. 2022.
  • Kakao Enterprise Corp, Occlusion-Robust 3D Hand Mesh Estimation Network, 2022.
  • LG AI Center, Occlusion-Robust 3D Hand Mesh Estimation Network, 2022.
  • AI Retreat, SNU, Occlusion-Robust 3D Hand Mesh Estimation Network, 2022.

Academic Services (Reviewer)

  • Conference : CVPR 2022, CVPR 2023, ICCV 2023, ICCVW 2023
  • Journal : TVCJ 2023