Authors: Adéla Šubrtová, Jan Čech, Akihiro Sugimoto
Abstract: We propose a method for detecting and automatically correcting perceptual artifacts on synthetic face images. Recent generative models, such as diffusion models, can produce photorealistic images. However, these models often generate visual defects on the faces of people, especially at low resolutions, which impairs the quality of the images. We use a face detector and a binary classifier to identify perceptual artifacts. The classifier was trained on our dataset of manually annotated synthetic face images generated by a diffusion model, half of which contain perceptual artifacts. We compare our method with several baselines and show that it achieves superior accuracy of 93\% on an independent test set. In addition, we propose a simple mechanism for automatically correcting the distorted faces using inpainting. For each face with artifact response, we generate several replacement candidates by inpainting and choose the best one by the lowest artifact score. The best candidate is then back-projected into to the image. Inpainting ensures a seamless connection between the corrected face and the original image. Our method improves the realism and quality of synthetic images.
[PDF]