Zhaorong Wang

Ph.D. Student
Department of Computer Science
University of Tsukuba
Tsukuba, Japan

I am a Ph.D. student in Computer Science at the University of Tsukuba. My research lies at the intersection of computer graphics, digital humans, and learning-based 3D representation, with a current focus on 3D Gaussian Splatting, avatar editing, and animatable human avatars.

My recent work spans two main directions. In my master’s research, I studied sparse-view digital human reconstruction and rendering, focusing on generalizable human NeRF models that balance rendering quality and inference efficiency. In my doctoral research, I work on digital human editing with 3D Gaussian Splatting, including outfit personalization, cross-avatar editing, and animatable avatar control.

I enjoy building practical research systems in PyTorch, especially pipelines that combine geometry, rendering, and generative modeling. I also build supporting tooling for large-scale experimentation and reproducible workflows on Linux GPU servers.

I hold JLPT N1 in Japanese and am comfortable communicating in both English and Japanese in research settings.

Please see my publications, projects, and CV for more details.

selected publications

CVM

EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View

Zhaorong Wang, Yoshihiro Kanamori, and Yuki Endo

Computational Visual Media, 2026

DOI Bib HTML

@article{wang2026eghumannerf,
  title = {EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View},
  author = {Wang, Zhaorong and Kanamori, Yoshihiro and Endo, Yuki},
  journal = {Computational Visual Media},
  year = {2026},
  volume = {12},
  number = {2},
  pages = {355--379},
  doi = {10.26599/CVM.2025.9450508},
}

CVPR

AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization

Zhaorong Wang, Yoshihiro Kanamori, and Yuki Endo

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

CVPR 2026 Findings

Bib

@inproceedings{wang2026avatarmix,
  title = {AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization},
  author = {Wang, Zhaorong and Kanamori, Yoshihiro and Endo, Yuki},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  note = {CVPR 2026 Findings}
}