Copy and Paste GAN: Face Hallucination from Shaded Thumbnails
This addresses the challenge of generating high-quality face images from shaded thumbnails, which is important for applications like surveillance or photo enhancement, though it is an incremental improvement over existing CNN-based methods.
The paper tackles the problem of face hallucination from low-resolution images under poor illumination by proposing a Copy and Paste GAN (CPGAN) that recovers high-resolution faces with uniform illumination, outperforming state-of-the-art methods in experiments.
Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternately in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.