ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images
This addresses the issue of eyeglasses interfering with face recognition systems, offering a practical pre-processing solution, though it is incremental as it builds on existing image-to-image GAN methods.
The paper tackles the problem of removing eyeglasses from face images while preserving identity, proposing ByeGlassesGAN, a GAN-based framework that automatically detects and removes glasses, resulting in visually appealing outputs and improved face recognition accuracy.
In this paper, we propose a novel image-to-image GAN framework for eyeglasses removal, called ByeGlassesGAN, which is used to automatically detect the position of eyeglasses and then remove them from face images. Our ByeGlassesGAN consists of an encoder, a face decoder, and a segmentation decoder. The encoder is responsible for extracting information from the source face image, and the face decoder utilizes this information to generate glasses-removed images. The segmentation decoder is included to predict the segmentation mask of eyeglasses and completed face region. The feature vectors generated by the segmentation decoder are shared with the face decoder, which facilitates better reconstruction results. Our experiments show that ByeGlassesGAN can provide visually appealing results in the eyeglasses-removed face images even for semi-transparent color eyeglasses or glasses with glare. Furthermore, we demonstrate significant improvement in face recognition accuracy for face images with glasses by applying our method as a pre-processing step in our face recognition experiment.