Robust super-resolution of face images by iterative compensating neighborhood relationships

In this paper, we propose a novel method for performing robust super-resolution of face images. Face super-resolution is to recover a high-resolution face image from a given low-resolution face image by modeling a face image space in view of multiple resolutions. The proposed method is based on the assumption that a low-resolution image space and a high-resolution image space have similar local geometries but also have partial distortions of neighborhood relationships between facial images. In this paper, local geometry is analyzed by an idea inspired by Locally Linear Embedding (LLE), the state-of-the art manifold learning method. Using the analyzed neighborhood relationships, two sets of neighborhoods in the low- and high-resolution image spaces become more similar in an iterative way. In this paper, we show that changing resolution causes the partial distortions of neighborhood embeddings obtained by a manifold learning method. Experimental results show that the proposed method produces more reliable results of face super-resolution than the traditional way using neighbor embedding.