Super-resolution restoration of facial images in video

Reconstruction-based super-resolution has been widely treated in computer vision. However, super-resolution of facial images has received very little attention. Since dif-ferent parts of a face may have different motions in normal videos, this paper proposes a new method for enhancing the resolution of low-resolution facial image by handling the facial image non-uniformly. We divide low-resolution face image into different regions based on facial features and estimate motions of each of these regions using differ-ent motion models. Our experimental results show we can achieve better results than applying super-resolution on the whole face image uniformly. 1