Pixel Sampling for Style Preserving Face Pose Editing
This addresses the style preservation issue in face pose editing for applications like image manipulation, but it is incremental as it builds on existing auto-encoder methods.
The paper tackles the problem of preserving image style (color, brightness, saturation) in face pose editing, which existing auto-encoder methods often fail to do, by proposing a two-stage approach that casts pose manipulation as face inpainting with pixel sampling and 3D landmark guidance, resulting in flexible editing across yaw, pitch, and roll angles and validated by qualitative and quantitative evaluations.
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 high-dimensional 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-of-the-art. Both the qualitative and quantitative evaluations validate the superiority of the proposed approach.