Text2Face: Text-Based Face Generation With Geometry and Appearance Control

Recent years have witnessed the emergence of various techniques proposed for text-based human face generation and manipulation. Such methods, targeting bridging the semantic gap between text and visual contents, provide users with a deft hand to turn ideas into visuals via text interface and enable more diversified multimedia applications. However, due to the flexibility of linguistic expressiveness, the mapping from sentences to desired facial images is clearly many-to-many, causing ambiguities during text-to-face generation. To alleviate these ambiguities, we introduce a local-to-global framework with two graph neural networks (one for geometry and the other for appearance) embedded to model the inter-dependency among facial parts. This is based upon our key observation that the geometry and appearance attributes among different facial components are not mutually independent, i.e., the combinations of part-level facial features are not arbitrary and thus do not conform to a uniform distribution. By learning from the dataset distribution and enabling recommendations given partial descriptions of human faces, these networks are highly suitable for our text-to-face task. Our method is capable of generating high-quality attribute-conditioned facial images from text. Extensive experiments have confirmed the superiority and usability of our method over the prior art.