Semantic Facial Expression Editing using Autoencoded Flow
This addresses the challenge of non-linear facial expression changes for image editing applications, though it appears incremental as it builds on existing VAE and flow-based techniques.
The paper tackles the problem of high-level facial expression editing in images, such as changing a smile to neutral, by combining flow-based manipulation with Variational Autoencoders, resulting in higher perceptual quality images than previous methods.
High-level manipulation of facial expressions in images --- such as changing a smile to a neutral expression --- is challenging because facial expression changes are highly non-linear, and vary depending on the appearance of the face. We present a fully automatic approach to editing faces that combines the advantages of flow-based face manipulation with the more recent generative capabilities of Variational Autoencoders (VAEs). During training, our model learns to encode the flow from one expression to another over a low-dimensional latent space. At test time, expression editing can be done simply using latent vector arithmetic. We evaluate our methods on two applications: 1) single-image facial expression editing, and 2) facial expression interpolation between two images. We demonstrate that our method generates images of higher perceptual quality than previous VAE and flow-based methods.