CONTROLLING FACIAL ATTRIBUTE SYNTHESIS BY DISENTANGLING ATTRIBUTE FEATURE AXES IN LATENT SPACE

In this study, we propose a novel approach to synthesise high-resolution and hyper-realistic face images with controlled attributes. Firstly, by training an attribute classifier to assign attribute labels to given synthesised face images, we build the links between latent vectors and face attributes. Secondly, we adapt regression method to match the distributions of latent vectors with the corresponding face attributes, in order to control the attribute synthesis in the face images. Finally, we use Gram-Schmidt orthogonalization algorithm to disentangle the attribute feature axes in latent space, such that a change in one attribute will not cause any changes in other attributes. Extensive experiments demonstrate the effectiveness of the proposed approach for high-quality face image synthesis with controlled attributes.