Learning to Hallucinate Face Images via Component Generation and Enhancement
This work addresses face hallucination for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles face hallucination by proposing a two-stage method that generates facial components using CNNs and enhances them with fine-grained details from high-resolution images, achieving favorable performance compared to state-of-the-art methods.
We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods