| CARVIEW |
I am Yiqian Wu (吴奕谦), a final-year CS Ph.D. candidate at the State Key Laboratory of CAD&CG, Zhejiang University, where I have been conducting research under the supervision of Prof. Xiaogang Jin since 2021.
From Jun. 2025 to Dec. 2025, I did my internship at the Codec Avatars Lab, Meta, working with Junxuan Li. From May 2024 to Apr. 2025, I was an academic guest at ETH Zurich, collaborating with Prof. Siyu Tang. I received my B.S. degree in Computer Science and Technology from the Chu Kochen College at Zhejiang University in 2021.
I am also a lazy and amateur painter.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
https://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "👩🎓Education
-
Zhejiang University
State Key Lab of CAD&CG
Ph.D. StudentSep. 2021 - Present -
Zhejiang University
B.S. in Computer ScienceSep. 2017 - Jun. 2021
👩💻 Experience
-
Codec Avatars Lab, Meta
Research Scientist InternJun. 2025 - Dec. 2025 -
ETH Zürich
Computer Vision and Learning Group
Academic GuestMay. 2024 - April. 2025
Research Overview
A central theme of my doctoral research is the generation and editing of high-quality, realistic digital humans. My work spans from 2D portrait representations to 3D avatar creation, progresses from static to dynamic digital humans, and scales from zero-shot generation to large-scale, multi-modal model training.
Below is an overview that showcases all of my papers through a single identity!
Selected Publications
(view all )
Text-based Animatable 3D Avatars with Morphable Model Alignment
Yiqian Wu; Malte Prinzler; Xiaogang Jin; Siyu Tang.
ACM SIGGRAPH (Conference Track) 2025 Work done while visiting ETH Zurich
A novel framework, AnimPortrait3D, for text-based realistic animatable 3DGS avatar generation with morphable model alignment.
Text-based Animatable 3D Avatars with Morphable Model Alignment
Yiqian Wu; Malte Prinzler; Xiaogang Jin; Siyu Tang.
Work done while visiting ETH Zurich
A novel framework, AnimPortrait3D, for text-based realistic animatable 3DGS avatar generation with morphable model alignment.
3DPortraitGAN: Learning Canonical Full-Head 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses
Yiqian Wu; Hao Xu; Xiangjun Tang; Yue Shangguan; Hongbo Fu; Xiaogang Jin.
IEEE Transactions on Circuits and Systems for Video Technology 2025
The first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360°PHQ dataset with body pose self-learning.
3DPortraitGAN: Learning Canonical Full-Head 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses
Yiqian Wu; Hao Xu; Xiangjun Tang; Yue Shangguan; Hongbo Fu; Xiaogang Jin.
The first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360°PHQ dataset with body pose self-learning.
Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
Yiqian Wu; Hao Xu; Xiangjun Tang; Xien Chen; Siyu Tang; Zhebin Zhang; Chen Li; Xiaogang Jin.
ACM Transactions on Graphics (Proceedings of SIGGRAPH) 2024
A novel neural rendering-based framework with a novel joint geometry-appearance prior to achieve text-to-3D-portrait generation.
Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
Yiqian Wu; Hao Xu; Xiangjun Tang; Xien Chen; Siyu Tang; Zhebin Zhang; Chen Li; Xiaogang Jin.
A novel neural rendering-based framework with a novel joint geometry-appearance prior to achieve text-to-3D-portrait generation.
LPFF: A Portrait Dataset for Face Generators Across Large Poses
Yiqian Wu; Jing Zhang; Hongbo Fu; Xiaogang Jin.
IEEE/CVF International Conference on Computer Vision (ICCV) 2023
A large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images.
LPFF: A Portrait Dataset for Face Generators Across Large Poses
Yiqian Wu; Jing Zhang; Hongbo Fu; Xiaogang Jin.
A large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images.
HairMapper: Removing Hair from Portraits Using GANs
Yiqian Wu; Yongliang Yang; Xiaogang Jin.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
A dataset and a baseline method for removing hair from portrait images using generative adversarial networks (GANs).
HairMapper: Removing Hair from Portraits Using GANs
Yiqian Wu; Yongliang Yang; Xiaogang Jin.
A dataset and a baseline method for removing hair from portrait images using generative adversarial networks (GANs).
Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications
Yiqian Wu; Yongliang Yang; Qinjie Xiao; Xiaogang Jin.
ACM Transactions on Graphics (Proceedings of SIGGRAPH) 2021
A novel method that can automatically remove the double chin effect in portrait images.
Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications
Yiqian Wu; Yongliang Yang; Qinjie Xiao; Xiaogang Jin.
A novel method that can automatically remove the double chin effect in portrait images.