|
I am currently a MS/PhD student at Seoul National University(SNU), advised by Hanbyul Joo. I'm interested in 3D human modeling in generative model perspective. |
|
News
- Jun. 2025: Our work HairCUP was accepted to ICCV 2025.
- Mar. 2024: I will start my intership in Codec Avatars Lab, Meta (Pittsburgh) this summer!
- Feb. 2024: GALA, PEGASUS, and Guess The Unseen were accepted to CVPR 2024.
- Jul. 2023: Our work Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models was accepted to ICCV 2023.
- Jul. 2022: Our work SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty was accepted to ECCV 2022.
- Jul. 2022: Joined SNU's Visual Computing Lab!
- Jun. 2022: Completed my military service in Agency for Defense Development(ADD) as a Research Officer for National Defense(ROND).
- Feb. 2019: Got my Bachelor's degree in Electrical Engineering at KAIST.
Research
|
Byungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon, Jason Saragih, Hanbyul Joo, Junxuan Li ICCV, 2025 [ Paper - Coming Soon ] We present HairCUP, a universal prior model for 3D head avatars with hair compositionality, which enables hairstyle swapping and efficient personalization. |
|
Taeksoo Kim*, Byungjun Kim*, Shunsuke Saito, Hanbyul Joo CVPR, 2024 [ Project Page / Code / arXiv ] We present GALA, a framework that takes as input a single-layer clothed 3D human mesh and decomposes it into complete multi-layered 3D assets. |
|
Hyunsoo Cha, Byungjun Kim, Hanbyul Joo CVPR, 2024 [ Project Page / Code / arXiv ] We present, PEGASUS, a method for constructing personalized generative 3D face avatars from monocular video sources. |
|
Inhee Lee, Byungjun Kim, Hanbyul Joo CVPR, 2024 [ Project Page / Code / arXiv ] We present Guess The Unseen, a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. |
|
Byungjun Kim*, Patrick Kwon*, Kwangho Lee, Myunggi Lee, Sookwan Han, Daesik Kim, Hanbyul Joo ICCV, 2023 (Oral Presentation) [ Project Page / Code / arXiv ] We propose Chupa, a 3D human generation pipeline that combines the generative power of diffusion models and neural rendering techniques to create diverse, realistic 3D humans. |
|
Gwangtak Bae, Byungjun Kim, Seongyong Ahn, Jihong Min, Inwook Shim ECCV, 2022 [ arXiv ] We propose a novel self-supervised learning framework for snow points removal in LiDAR point clouds. |