Pixel Sampling for Style Preserving Face Pose Editing

Xiangnan Yin (1, 2) , Liming Chen (1, 2) , Di Huang (3) , Hongyu Yang , Zehua Fu (1) , Yunhong Wang (3)

1 ECL - École Centrale de Lyon
2 imagine - Extraction de Caractéristiques et Identification
3 School of Computer Science and Engineering [Beijing]

The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc. In this paper, we take advantage of the well-known frontal/profile optical illusion and present a novel two-stage approach to solve the aforementioned dilemma, where the task of face pose manipulation is cast into face inpainting. By selectively sampling pixels from the input face and slightly adjust their relative locations with the proposed "Pixel Attention Sampling" module, the face editing result faithfully keeps the identity information as well as the image style unchanged. By leveraging highdimensional embedding at the inpainting stage, finer details are generated. Further, with the 3D facial landmarks as guidance, our method is able to manipulate face pose in three degrees of freedom, i.e., yaw, pitch, and roll, resulting in more flexible face pose editing than merely controlling the yaw angle as usually achieved by the current state-ofthe-art. Both the qualitative and quantitative evaluations validate the superiority of the proposed approach.

Domaines: Informatique [cs]

Xiangnan Yin, Liming Chen, Di Huang, Hongyu Yang, Zehua Fu, et al.. Pixel Sampling for Style Preserving Face Pose Editing. 2020 IEEE International Joint Conference on Biometrics (IJCB), Sep 2020, Houston, United States. pp.1-10, ⟨10.1109/IJCB48548.2020.9304867⟩. ⟨hal-03381113⟩