3DPortraitGAN :
Learning Canonical Full-Head 3D GANs
from a Single-View Portrait Dataset
with Diverse Body Poses

1State Key Lab of CAD&CG, Zhejiang University, 2City University of Hong Kong

Our 3DPortraitGAN can generate one-quarter headshot 3D avatars and output portrait images (a and d) of a single identity using camera poses and body poses from reference images (c and f). The real reference images (c and f) are sampled from our 360°PHQ dataset. We demonstrate that 3DPortraitGAN can generate canonical portrait images from all camera angles by showcasing the 360° yaw angle exploration results in (g).


3D-aware face generators are typically trained on 2D real-life face image datasets that primarily consist of near-frontal face data, and as such, they are unable to construct one-quarter headshot 3D portraits with complete head, neck, and shoulder geometry. Two reasons account for this issue: First, existing facial recognition methods struggle with extracting facial data captured from large camera angles or back views. Second, it is challenging to learn a distribution of 3D portraits covering the one-quarter headshot region from single-view data due to significant geometric deformation caused by diverse body poses.

To this end, we first create the dataset 360°PHQ-Portrait-HQ (360°PHQ} for short) which consists of high-quality single-view real portraits annotated with a variety of camera parameters (the yaw angles span the entire 360° range) and body poses. We then propose 3DPortraitGAN, 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. Our model can generate view-consistent portrait images from all camera angles with a canonical one-quarter headshot 3D representation.

Our experiments show that the proposed framework can accurately predict portrait body poses and generate view-consistent, realistic portrait images with complete geometry from all camera angles.


Our image generation pipeline.



      title={3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses},
      author={Yiqian Wu and Hao Xu and Xiangjun Tang and Hongbo Fu and Xiaogang Jin},