publications

* Equal contribution or co-last authors, as noted on each entry.

2026

  1. CVPR
    OpenFS.png
    OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis
    Junuk Cha, Jihyeon Kim, and Han-Mu Park
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    PDF Code Website

2025

  1. ICCVW
    CoTPose.png
    CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts
    Junuk Cha* and Jihyeon Kim*
    In IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025
    PDF Code
  2. CVPR
    BIGS.png
    BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
    Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, and 4 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    PDF Supp Code
  3. arXiv
    EmoTalkingGaussian.png
    EmoTalkingGaussian: Continuous Emotion-conditioned Talking Head Synthesis
    Junuk Cha, Seongro Yoon, Valeriya Strizhkova, and 2 more authors
    arXiv preprint, 2025
    PDF
  4. AAAI
    AAAI2025.png
    Text2Relight: Creative Portrait Relighting with Text Guidance
    Junuk Cha, Mengwei Ren, Krishna Kumar Singh, and 6 more authors
    In AAAI Conference on Artificial Intelligence (AAAI), 2025
    PDF Website

2024

  1. Challenge
    eccv2024_challenge.png
    3DGS-based Bimanual Category-agnostic Interaction Reconstruction
    Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, and 5 more authors
    In Technical Report, HANDS Workshop Challenge at European Conference on Computer Vision (ECCV), 2024
    1st Place PDF
  2. CVPR
    text2hoi.png
    Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction
    Junuk Cha, Jihyeon Kim, Jae Shin Yoon*, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    arXiv PDF Supp Code Website
  3. CVPRW
    vlm_pl.png
    VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model
    Junsu Kim, Yunhoe Ku*, Jihyeon Kim*, and 2 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024
    arXiv PDF
  4. WACV
    MultiRecon.png
    3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image
    Junuk Cha, Hansol Lee, Jaewon Kim, and 3 more authors
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
    PDF

2023

  1. arXiv
    DynamicAppearance.gif
    Dynamic Appearance Modeling of Clothed 3D Human Avatars using a Single Camera
    Hansol Lee, Junuk Cha, Yunhoe Ku, and 2 more authors
    arXiv preprint, 2023
    PDF

2022

  1. arXiv
    HOImage.png
    HOReeNet: 3D-aware Hand-Object Grasping Reenactment
    Changhwa Lee, Junuk Cha, Hansol Lee, and 3 more authors
    arXiv preprint, 2022
    PDF
  2. ECCV
    MultiMesh.png
    Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
    Junuk Cha, Muhammad Saqlain, GeonU Kim, and 2 more authors
    In European Conference on Computer Vision (ECCV), 2022
    PDF Code
  3. Journal
    ActionRecog.png
    Learning 3D Skeletal Representation From Transformer for Action Recognition
    Junuk Cha, Muhammad Saqlain, Donguk Kim, and 3 more authors
    IEEE Access, 2022
    PDF
  4. Journal
    GroupActionRecog.png
    3DMesh-GAR: 3D Human Body Mesh-based Method for Group Activity Recognition
    Muhammad Saqlain, Donguk Kim, Junuk Cha, and 3 more authors
    Sensors, 2022
    HTML

2021

  1. Journal
    SelfSuperMesh.png
    Towards Single 2D Image-level Self-supervision for 3D Human Pose and Shape Estimation
    Junuk Cha, Muhammad Saqlain, Changhwa Lee, and 5 more authors
    Applied Sciences, 2021
    HTML Code