Face generation is the task of generating (or interpolating) new faces from an existing dataset.
The state-of-the-art results for this task are located in the Image Generation parent.
The necessary attributes of having a realistic face animation are 1) audio-visual synchronization (2) identity preservation of the target individual (3) plausible mouth movements (4) presence of natural eye blinks.
Finally, we apply our approach to real face editing by involving GAN inversion approaches as well as explicitly training additional feed-forward models based on the synthetic data established by InterFaceGAN.
Most of the existing methods train models for one-versus-one kin relation, which only consider one parent face and one child face by directly using an auto-encoder without any explicit control over the resemblance of the synthesized face to the parent face.
Although many methods focus on fake detection, only a few put emphasis on the localization of the fake regions.
Generative adversarial networks (GANs) nowadays are capable of producing im-ages of incredible realism.
The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake content with its corresponding implications towards society in this era of fake news.
Generating a pose-invariant representation capable of synthesizing multiple face pose views from a single pose is still a difficult problem.
In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.
Specifically, we propose a two-stage kin-face generation model to predict the appearance of a child given a pair of parents.