I am Yiqian Wu (吴奕谦), now serving as an academic guest at ETH Zurich (May 2024 - May 2025), working with Prof. Siyu Tang. Concurrently, I am a CS Ph.D. candidate (since 2021) at the State Key Lab of CAD&CG, Zhejiang University, under the supervision of Prof. Xiaogang Jin. Prior to this, I accomplished my Bachelor’s degree in Computer Science and Technology, graduating from the Chu Kochen College at Zhejiang University in 2021.
Address: Mengminwei Bldg, Zijingang Campus of Zhejiang University, 866 Yuhangtang Rd, Hangzhou 310058, China.
ORCID: 0000-0002-2432-809X
Contact: onethousand@zju.edu.cn / onethousand1250@gmail.com
I love painting! I have posted some of my paintings on my website’s art gallery, and also shared some videos on Bilibili. I hope you will enjoy them too :)
My Journey: Advancing 2D to 3D Avatar Generation
My current research focuses on portrait editing and generation. I have proposed two portrait image editing methods based on 2D GAN models, developed a dataset and designed a new architecture for 3D-aware face GANs. Currently, I am utilizing diffusion models for text-guided 3D avatar generation and extending this approach to enable animatability.
Below is an overview that showcases all of my papers through a single identity!
Publications
Explore the complete list of publications 👉️ here .
Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2024), 2024
Yiqian Wu, Hao Xu, Xiangjun Tang, Xien Chen, Siyu Tang, Zhebin Zhang, Chen Li, Xiaogang Jin*
LPFF: A Portrait Dataset for Face Generators Across Large Poses
2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Yiqian Wu, Jing Zhang, Hongbo Fu, Xiaogang Jin
3DPortraitGAN: Learning Canonical Full-Head 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses
Preprints, 2023
Yiqian Wu, Hao Xu, Xiangjun Tang, Hongbo Fu, Xiaogang Jin*
HairMapper: Removing Hair from Portraits Using GANs
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Yiqian Wu, Yongliang Yang, Xiaogang Jin
Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2021), 2021
Yiqian Wu, Yongliang Yang, Qinjie Xiao, Xiaogang Jin
Experience
Academic Guest
Computer Vision and Learning Group (VLG), ETH Zürich.
Zürich, Switzerland. May. 2024 - May. 2025
Ph.D.
State Key Lab of CAD&CG, Zhejiang University.
Hangzhou, China. Sep. 2021 - Exp. Jun. 2026
Bachelor
Chu Kochen Honors College, Zhejiang University.
Hangzhou, China. Sep. 2017 - Jun. 2021