Toward extreme face super-resolution in the wild: A self-supervised learning approach

Extreme face super-resolution (FSR), that is, improving the resolution of face images by an extreme scaling factor (often greater than x8) has remained underexplored in the literature of low-level vision. Extreme FSR in the wild must address the challenges of both unpaired training data and unknown degradation factors. Inspired by the latest advances in image super-resolution (SR) and self-supervised learning (SSL), we propose a novel two-step approach to FSR by introducing a mid-resolution (MR) image as the stepping stone. In the first step, we leverage ideas from SSL-based SR reconstruction of medical images (e.g., MRI and ultrasound) to modeling the realistic degradation process of face images in the real world; in the second step, we extract the latent codes from MR images and interpolate them in a self-supervised manner to facilitate artifact-suppressed image reconstruction. Our two-step extreme FSR can be interpreted as the combination of existing self-supervised CycleGAN (step 1) and StyleGAN (step 2) that overcomes the barrier of critical resolution in face recognition. Extensive experimental results have shown that our two-step approach can significantly outperform existing state-of-the-art FSR techniques, including FSRGAN, Bulat's method, and PULSE, especially for large scaling factors such as 64.