Deformable Generator Network: Unsupervised Disentanglement of Appearance and Geometry

We propose a deformable generator model to disentangle the appearance and geometric information from images into two independent latent vectors. The appearance generator produces the appearance information, including color, illumination, identity or category, of an image. The geometric generator produces displacement of the coordinates of each pixel and performs geometric warping, such as stretching and rotation, on the appearance generator to obtain the final synthesized image. The proposed model can learn both representations from image data in an unsupervised manner. The learned geometric generator can be conveniently transferred to the other image datasets to facilitate downstream AI tasks.