Abstract
Obtaining a high-quality frontal face image from a low-resolution (LR) non-frontal face image is primarily important for many facial analysis applications. However, mainstreams either focus on super-resolving near-frontal LR faces or frontalizing non-frontal high-resolution (HR) faces. It is desirable to perform both tasks seamlessly for daily-life unconstrained face images. In this paper, we present a novel Vivid Face Hallucination Generative Adversarial Network (VividGAN) devised for simultaneously super-resolving and frontalizing tiny non-frontal face images. VividGAN consists of a Vivid Face Hallucination Network (Vivid-FHnet) and two discriminators, i.e., Coarse-D and Fine-D. The Vivid-FHnet first generates a coarse frontal HR face and then makes use of the structure prior, i.e., fine-grained facial components, to achieve a fine frontal HR face image. Specifically, we propose a facial component-aware module, which adopts the facial geometry guidance as clues to accurately align and merge the coarse frontal HR face and prior information. Meanwhile, the two-level discriminators are designed to capture both the global outline of the face as well as detailed facial characteristics. The Coarse-D enforces the coarse hallucinated faces to be upright and complete; while the Fine-D focuses on the fine hallucinated ones for sharper details. Extensive experiments demonstrate that our VividGAN achieves photo-realistic frontal HR faces, reaching superior performance in downstream tasks, i.e., face recognition and expression classification, compared with other state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2002.03308
