Face Hallucination Using Manifold-Regularized Group Locality-Constrained Representation

Tao Lu, Kangli Zeng, Junjun Jiang, Yanduo Zhang, Wei He, Zhongyuan Wang, Huabing Zhou

Abstract

Sparsity and locality regularizations are successfully applied to face hallucination algorithms to ameliorate their ill-posed nature. However, most of patch-based face hallucination approaches only consider the manifold structure of single patch, thus resulting in unstable solution for image reconstruction. In this paper, we propose a novel face hallucination, termed manifold-regularized group locality-constrained representation (MGLR), in order to exploit the multiple manifold structures rooted in grouped self-similarly patches. Specifically, we first group similar patches to form a matrix which contains the recurrent non-local patches. Then graph regularization term is formulated to represent the group manifolds for better reconstruction quality. Taking advantages of grouped self-similar patches, MGLR can offer stable sparse solution to take advantage of the the accurate prior for super-resolution reconstruction. Experimental results on LFW database and CMU real-world images demonstrate the superiority of the proposed method over some state-of-the-art face methods both in terms of subjective and objective qualities.
BibTeX
@inproceedings{lu2018face,
  author = {Tao Lu and Kangli Zeng and Junjun Jiang and Yanduo Zhang and Wei He and Zhongyuan Wang and Huabing Zhou},
  title = {{Face Hallucination Using Manifold-Regularized Group Locality-Constrained Representation}},
  booktitle = {ICIP},
  year = {2018},
  doi = {10.1109/icip.2018.8451499},
}

Loading related content...

Figure