Kernel-Based Face Hallucination via Dual Regularization Priors

  title={Kernel-Based Face Hallucination via Dual Regularization Priors},
  author={Jingang Shi and Chun Qi},
  journal={IEEE Signal Processing Letters},
Recently, patch-based face hallucination methods have shown the ability for achieving high-quality face images. The high-resolution (HR) patches can be reconstructed by a linear combination of training patches, while the combination coefficients are learned according to the corresponding low-resolution (LR) patches. In order to reflect the local features, face images are usually divided into very small patches, e.g. 3 × 3 for LR case. Though we assume the linear relationship between training… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 22 references

Similar Papers

Loading similar papers…