Patrick Kwon (권용재)

[CV] [Twitter] [Linkedin] [Google Scholar] [Github]

profile_pic.jpg

I am a first-year research assistant at the Center for Research in Computer Vision, UCF, working with Dr. Chen Chen. Previously, I worked as a full-time research scientist at Naver Webtoon Corp. studying computer vision, graphics, and AI. I have also worked with Professor Hanbyul Joo and SNU VCLab in solving 3D reconstruction and affordance problems. I received my Master’s degree at Columbia University studying machine learning and human-computer interaction within augmented reality.

My main research goal is in embedding human prior knowledge within generative AI systems. Specifically, I aspire to create AI systems that has a human level understanding towards visual context, which in turn will pave way for novel solutions in the field of computer vision. For instance, how can we aid video generation models to better understand human-object interaction? And how can we utilize such models in helping content creators and improving robotics systems? These are just few of the questions I hope to discover answers for.

news

Sep 26, 2026 Our paper FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery has been accepted as a poster at NeurIPS 2026! :tada:

selected publications

  1. Use of Computer Vision with Conventional Video Recordings of Gait in Older Adults: A Scoping Review
    Chitra Banarjee, Anthony Bilic, Yong Jae Kwon, and 5 more authors
    Healthcare, Aug 2026
    A scoping review of computer-vision methods that use conventional video recordings to analyze gait in older adults.
  2. Fig3-1.png
    FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
    Patrick Kwon, and Chen Chen
    In Advances in Neural Information Processing Systems, Aug 2026
    A two-stage human mesh recovery (HMR) framework that uses a factorized representation and processing of human body poses. Accepted as a poster at NeurIPS 2026.
  3. example-pipeline.png
    Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery
    Chitra Banarjee, Patrick Kwon, Ania Lipat, and 3 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): Computer Vision for Biomechanics Workshop (CVBW), Jun 2026
    Case Study for utilizing 3D Human Mesh Recovery (HMR) research for analyzing gait for the elderly population
  4. Figure1_v5-2.png
    DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models
    Patrick Kwon, and Chen Chen
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Dec 2025
    A story visualization pipeline that repurposes video generative models and LLMs to produce identity-consistent, multi-panel comics with spatial layout control.
  5. GraspDiff.png
    GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction
    Patrick Kwon, Chen Chen, and Hanbyul Joo
    In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Oct 2025
    Generates realistic full-bodied HOI poses and images controlled by a given 3D object via a two-stage synthesis pipeline.
  6. ComA.png
    Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
    Hyeonwoo Kim*, Sookwan Han*, Patrick Kwon, and 1 more author
    In Computer Vision – ECCV 2024, Sep 2024
    Discovers rich 3D affordance relationships based on image generative models and their prior knowledge. Oral presentation at ECCV 2024.
  7. ARIOS.jpg
    Augmented-reality-assisted intraoral scanning: A proof-of-concept study
    Seung Jun Song, Madison Tang, Brynn Gwartzman, and 6 more authors
    Journal of Prosthodontics, Jul 2024
    An AR application to guide intraoral scanning for dental applications, and its connected study for efficiency evaluation.
  8. 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 (ICCV), Jul 2023
    Realistic 3D clothed human reconstruction method leveraging image diffusion models and skinned shape priors. Oral presentation at ICCV 2023.
  9. interactivecartoonization.jfif
    Interactive Cartoonization with Controllable Perceptual Factors
    Namhyuk Ahn, Patrick Kwon, Jihye Back, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2023
    A novel cartoonization method that allows users to interactively control various perceptual factors of images.
  10. 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
    Jul 2023
    Provides intuitive, semantic control of talking-head models using facial landmarks and a morphable parameter model.
  11. 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 (ICCV), Jul 2021
    A large-scale deepfake detection dataset focusing on Korean faces to address demographic bias in deepfake detection models.