Learn to synthesize and synthesize to learn
This work addresses the challenge of flexible and high-quality face image manipulation for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles the problem of attribute-guided face image synthesis by proposing a single model that can generate multiple photo-realistic face images conditioned on attributes, overcoming limitations of existing methods that require separate models for each attribute pair and suffer from mode collapse. It demonstrates improved photorealistic quality on face datasets and shows that generated images can enhance facial expression recognition classifier performance through synthetic data augmentation.
Attribute guided face image synthesis aims to manipulate attributes on a face image. Most existing methods for image-to-image translation can either perform a fixed translation between any two image domains using a single attribute or require training data with the attributes of interest for each subject. Therefore, these methods could only train one specific model for each pair of image domains, which limits their ability in dealing with more than two domains. Another disadvantage of these methods is that they often suffer from the common problem of mode collapse that degrades the quality of the generated images. To overcome these shortcomings, we propose attribute guided face image generation method using a single model, which is capable to synthesize multiple photo-realistic face images conditioned on the attributes of interest. In addition, we adopt the proposed model to increase the realism of the simulated face images while preserving the face characteristics. Compared to existing models, synthetic face images generated by our method present a good photorealistic quality on several face datasets. Finally, we demonstrate that generated facial images can be used for synthetic data augmentation, and improve the performance of the classifier used for facial expression recognition.