ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN
This work addresses the challenge of obtaining large-scale child facial datasets for computer vision applications, offering a domain-specific solution that is incremental in nature.
The authors tackled the problem of generating synthetic child facial data by proposing ChildGAN, a pair of GAN networks based on StyleGAN2, which produced over 300k high-quality samples with various transformations, demonstrating that synthetic data can serve as a cost-effective alternative to real-world collection.
In this research work, we proposed a novel ChildGAN, a pair of GAN networks for generating synthetic boys and girls facial data derived from StyleGAN2. ChildGAN is built by performing smooth domain transfer using transfer learning. It provides photo-realistic, high-quality data samples. A large-scale dataset is rendered with a variety of smart facial transformations: facial expressions, age progression, eye blink effects, head pose, skin and hair color variations, and variable lighting conditions. The dataset comprises more than 300k distinct data samples. Further, the uniqueness and characteristics of the rendered facial features are validated by running different computer vision application tests which include CNN-based child gender classifier, face localization and facial landmarks detection test, identity similarity evaluation using ArcFace, and lastly running eye detection and eye aspect ratio tests. The results demonstrate that synthetic child facial data of high quality offers an alternative to the cost and complexity of collecting a large-scale dataset from real children.