Robust Multi-Image Based Blind Face Hallucination

CVPR 2015

doi:10.1109/CVPR.2015.7299162 /cvpr/2015/jin2015cvpr-robust/

Abstract

This paper proposes a robust multi-image based blind face hallucination framework to super-resolve LR faces. The proposed framework first estimates both blurring kernel and transformations of multiple LR faces by robust deblurring and registration in PCA subspace. A patch-wise mixture of probabilistic PCA prior is then incorporated for face super-resolution. Previous work on face SR using PCA prior can be viewed as special cases of the framework. Experimental results in both simulated and real LR sequences demonstrate very promising performance of the proposed method.

PDF CVPR Semantic Scholar

Cite

Text

Jin and Bouganis. "Robust Multi-Image Based Blind Face Hallucination." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299162

Markdown

[Jin and Bouganis. "Robust Multi-Image Based Blind Face Hallucination." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/jin2015cvpr-robust/) doi:10.1109/CVPR.2015.7299162

BibTeX

@inproceedings{jin2015cvpr-robust,
  title     = {{Robust Multi-Image Based Blind Face Hallucination}},
  author    = {Jin, Yonggang and Bouganis, Christos-Savvas},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299162},
  url       = {https://mlanthology.org/cvpr/2015/jin2015cvpr-robust/}
}