Hansol Lee
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 2D image generation. I currently work as a Machine Learning Engineer at CLO Virtual Fashion. 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, 3D scene reconstruction and generation, and generative models.
Researches
DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation
European Conference on Computer Vision (ECCV) 2026 [Link]
European Conference on Computer Vision (ECCV) 2026 [Link]
ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
Conference on Neural Information Processing Systems (NeurIPS) 2024 [Link]
Conference on Neural Information Processing Systems (NeurIPS) 2024 [Link]
PIDiffu: Pixel-aligned Diffusion Model for High-Fidelity Clothed Human Reconstruction
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 [Link]
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 [Link]
3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 [Link]
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 [Link]
IFaceUV: Intuitive Motion Facial Image Generation by Identity Preservation via UV map
arXiv 2023 [Link]
arXiv 2023 [Link]
