A Portrait Dataset
for Face Generators Across Large Poses

ICCV 2023
1State Key Lab of CAD&CG, Zhejiang University, 2City University of Hong Kong

Image and shape samples generated by EG3D models trained with the same training strategy but using different datasets (our new dataset LPFF and FFHQ, and FFHQ alone). The generators are conditioned by the average camera parameters. Shapes are iso-surfaces extracted from the corresponding density fields using marching cubes. Our dataset helps reduce distorted, ''seam'', ''wall-mounted'', and blurry artifacts.


Existing face generators exhibit exceptional performance on faces in small to medium poses (with respect to frontal faces) but struggle to produce realistic results for large poses. The distorted rendering results on large poses in 3D-aware generators further show that the generated 3D face shapes are far from the distribution of 3D faces in reality. We find that the above issues are caused by the training dataset's pose imbalance.

To this end, we present LPFF, a large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images. We utilize our dataset to train a 2D face generator that can process large-pose face images, as well as a 3D-aware generator that can generate realistic human face geometry. To better validate our pose-conditional 3D-aware generators, we develop a new FID measure to evaluate the 3D-level performance.

Through this novel FID measure and other experiments, we show that LPFF can help 2D face generators extend their latent space and better manipulate the large-pose data, and help 3D-aware face generators achieve better view consistency and more realistic 3D reconstruction results.


Dataset samples

The samples from our LPFF dataset.



    author    = {Wu, Yiqian and Zhang, Jing and Fu, Hongbo and Jin, Xiaogang},
    title     = {LPFF: A Portrait Dataset for Face Generators Across Large Poses},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {20327-20337}