Disentangled Geometry for Deep Face Generation and Editing
A team of engineers presented a method for SIGGRAPH 2021 that allows users to intuitively edit a face image, manipulate its geometry and appearance with detailed control.
Shu-Yu Chen, Feng-Lin Liu, Yu-Kun Lai, Paul L. Rosin, Chunpeng Li, Hongbo Fu, and Lin Gao from Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Cardiff University, and the City University of Hong Kong presented a novel method to edit a face image.
Given a portrait image, the method disentangles its geometry and appearance, and the resulting representations can faithfully reconstruct the input image.
There is a range of flexible face editing tasks that can be achieved with the framework: changing the appearance according to the given reference images while retaining the geometry, replacing the geometry of the face with a sketch while keeping the appearance, editing the geometry using sketches, and editing both the geometry and appearance.
