About Me

Hello, I’m Hansol Lee, a Computer Vision and Deep Learning Research Engineer with specialized research interests in 3D avatar reconstruction, 3D scene reconstruction, and generation. I’m currently an intern researcher at xrHuman Lab, Korea Institute of Science and Technology(KIST), where I focus on 3D scene reconstruction, including people and objects, from multiple views. I received a dual bachelor’s degree in economics and computer science from Sookmyung Women’s University in Seoul, South Korea, and a master’s degree in computer engineering from Ulsan National Institute of Science and Technology(UNIST) in Ulsan, South Korea.

Research Interests. Deep learning-driven computer vision with a focus on 3D human modeling, avatar reconstruction, and 3D scene reconstruction and generation.

Researches

ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
Hansol Lee, Tackgeun You, Hansoo Park, Woohyeon Shim, Sanghyeon Kim, Hwasup Lim, [NeurIPS'24 Under Review] [Link]

Dynamic Appearance Modeling of Clothed 3D Human Avatars using a Single Camera
Hansol Lee, Junuk Cha, Yunhoe Ku, Jaeshin Yoon* and Seungryul Baek*, arXiv 2024 [Link]

PIDiffu: Pixel-aligned Diffusion Model for High-Fidelity Clothed Human Reconstruction
Jungeun Lee, Sanghun Kim, Hansol Lee, Tserendorj Adiya, Hwasup Lim*, WACV 2024 [Link]

3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image
Junuk Cha, Hansol Lee, Jaewon Kim, Bao, Jaeshin Yoon* and Seungryul Baek*, WACV 2024 [Link]

IFaceUV: Intuitive Motion Facial Image Generation by Identity Preservation via UV map
Hansol Lee, Yunhoe Ku, Eunseo Kim, Seungryul Baek*, arXiv 2023 [Link]

Data

Synthetic dataset of multi-person interaction geometry

View Example Sequential Video Dataset