Locality-constrained matrix regression for position-patch based face hallucination
Guangwei Gao, Xiao‐Yuan Jing, Quan Zhou, Songsong Wu, Dong Yue · 2016
Position-patch based face hallucination approaches have been proposed to replace the probabilistic graph-based or manifold learning-based models recently. In this paper, we propose a novel position-based face hallucination method based on locality-constrained matrix regression (LcMR). LcMR uses nuclear norm to characterize the reconstruction error straightforward, thus preserving the essential structural information of the input. On the other hand, LcMR imposes a locality constraint onto the combination coefficients to reach sparsity and locality simultaneously. The locality constraint can derive an analytical solution to the optimization problem. Moreover, LcMR can be solved using alternating direction method of multipliers. Experimental results demonstrate the superiority of the proposed method over some state-of-the-art approaches.