Wang Zhaorong
Ph.D. Student in Computer Science, University of Tsukuba
I am a Ph.D. student in Computer Science at the University of Tsukuba, advised by Yoshihiro Kanamori and Yuki Endo in the Computational Geometry and Graphics Laboratory (CGG).
My past research has focused on digital humans, including reconstruction from sparse images, 3D avatar editing, and animation. I am broadly interested in 3D vision, reconstruction, generation, and computer graphics.
I am a doctoral research intern at CyberAgent AI Lab from August to September 2026, working on 3D scene generation.
Research
AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization
CVPR 2026 Findings
3D virtual try-on that combines two avatars while preserving the wearer's face and body shape, with diffusion-based repair of seams and appearance artifacts.
EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View
Computational Visual Media, 12(2), 355–379, 2026
Novel human views from three or four images, using a body prior and predicted geometry to reduce sampling, followed by occlusion-aware image refinement.
Selected Projects
Open Adaptive Shells
A reimplementation of Adaptive Shells, from neural-field training and shell extraction to an interactive GPU renderer using OptiX and Dr.Jit.
VolLenia Playground
A playground for 3D artificial life, with a C++/CUDA simulator and volume renderer, plus PyTorch tools for parameter optimization and pattern search.