Patrick Kwon (권용재)

Deep learning researcher, Naver Webtoon.
[CV]

profile_pic.jpg

I am a deep learning researcher at Naver Webtoon. My main research goal is to solve 2D/3D generation problems with semantic control, based on deep learning techniques. My prior research areas include 3D human digitalization, generative models, Deepfake detection, and VR/AR programming.

news

Aug 12, 2023 I’m proud to share that my recent paper Chupa, co-authored with Byungjun Kim, has been accepted as an Oral Presentation to #ICCV2023!

latest posts

Mar 17, 2022 Towards Controllable and Photorealistic Region-wise Image Manipulation
Mar 7, 2022 Swapping Autoencoder for Deep Image Manipulation
Feb 20, 2022 E4E - Encoder for StyleGAN Image Manipulation

selected publications

2023

  1. rp_christopher_posed_001_boy_long_sleeves_jeans.gif
    Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models
    Byungjun Kim*, Patrick Kwon*, Kwangho Lee, and 4 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  2. teaser_v3_wocolor.png
    LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model
    Kwangho Lee, Patrick Kwon, Myung Ki Lee, and 2 more authors
    2023

2021

  1. 5-Figure2-1.png
    Kodf: A large-scale korean deepfake detection dataset
    Patrick Kwon, Jaeseong You, Gyuhyeon Nam, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021