Learning-based face hallucination in DCT domain

In this paper, we propose a novel learning-based face hallucination framework built in DCT domain, which can recover the high-resolution face image from a single low-resolution one. Unlike most previous learning-based work, our approach addresses the face hallucination problem from a different angle. In details, the problem is formulated as inferring DCT coefficients in frequency domain instead of estimating pixel intensities in spatial domain. Experimental results show that DC coefficients can be estimated fairly accurately by simple interpolation-based methods. AC coefficients, which contain the information of local features of face image, cannot be estimated well using interpolation. We propose a method to infer AC coefficients by introducing an efficient learning-based inference model. Moreover, the proposed framework can lead to significant savings in memory and computation cost since the redundancy of the training set is reduced a lot by clustering. Experimental results demonstrate that our approach is very effective to produce hallucinated face images with high quality.