Self-portraits captured from a short distance might look unnatural or even
unattractive due to heavy distortions making facial features malformed, and
ill-placed head poses. In this paper, we propose SUPER, a novel method of
eliminating distortions and adjusting head pose in a close-up face crop. We
perform 3D GAN inversion for a facial image by optimizing camera parameters and
face latent code, which gives a generated image. Besides, we estimate depth
from the obtained latent code, create a depth-induced 3D mesh, and render it
with updated camera parameters to obtain a warped portrait. Finally, we apply
the visibility-based blending so that visible regions are reprojected, and
occluded parts are restored with a generative model. Experiments on face
undistortion benchmarks and on our self-collected Head Rotation dataset (HeRo),
show that SUPER outperforms previous approaches both qualitatively and
quantitatively, opening new possibilities for photorealistic selfie editing.

本文提出了一种名为 SUPER 的新方法，用于消除自拍照片中的失真和调整头部姿势，实现了更真实的自拍照片编辑。通过 3D GAN 反向传播优化相机参数和面部隐藏编码，生成一张图像。此外，估计获得的隐藏编码的深度，创建深度感应的 3D 网格，并使用更新的相机参数进行渲染，获得一个形变的自画像。最后，通过基于可见性的融合，重新投影可见区域，并使用生成模型恢复被遮挡的部分。对自拍照片失真基准和自行收集的头部旋转数据集（HeRo）的实验表明，SUPER 在定性和定量上均优于以前的方法，为实现逼真的自拍照片编辑开辟了新的可能性。