LAUSR

Face hallucination refers an application-specific super-resolution (SR) which predicts high-resolution images from one or multiple low-resolution inputs. Learning-based SR algorithms infer latent HR images by the guidance of coexisted priors from training samples. Various regularization methods have been successfully applied in face hallucination to ameliorate its ill-posed nature. But most of them only consider the local manifold geometry of a single patch which results in an unstable solution for SR reconstruction. In this paper, we propose a novel face hallucination algorithm to embed group patches for accurate prior representation and reconstruction. First, we select multiple recurrent self-similar patches to form a group embedding matrix. Then, a graph regularization term and another multiple-manifold regularization term are used to exploit accurate representation for SR performance. Our resulting ADMM algorithm gives a stable solution in an iterative manner. Furthermore, we use a two-step searching strategy for accelerated patch matching. Experimental results on the LFW database, FEI database, and some real-world images demonstrate the superiority of the proposed method when compared with state-of-the-art face hallucination results both on subjective and objective qualities.