Skip to main content

Research Repository

See what's under the surface

Advanced Search

Face hallucination based on sparse local-pixel structure

Li, Yongchao; Cai, Cheng; Qiu, Guoping; Lam, Kin-Man

Authors

Yongchao Li

Cheng Cai

Guoping Qiu

Kin-Man Lam



Abstract

In this paper, we propose a face-hallucination method, namely face hallucination based on sparse local-pixel structure. In our framework, a high resolution (HR) face is estimated from a single frame low resolution (LR) face with the help of the facial dataset. Unlike many existing face-hallucination methods such as the from local-pixel structure to global image super-resolution method (LPS-GIS) and the super-resolution through neighbor embedding, where the prior models are learned by employing the least-square methods, our framework aims to shape the prior model using sparse representation. Then this learned prior model is employed to guide the reconstruction process. Experiments show that our framework is very flexible, and achieves a competitive or even superior performance in terms of both reconstruction error and visual quality. Our method still exhibits an impressive ability to generate plausible HR facial images based on their sparse local structures.

Journal Article Type Article
Publication Date Mar 1, 2014
Journal Pattern Recognition
Print ISSN 0031-3203
Electronic ISSN 0031-3203
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 47
Issue 3
APA6 Citation Li, Y., Cai, C., Qiu, G., & Lam, K. (2014). Face hallucination based on sparse local-pixel structure. Pattern Recognition, 47(3), https://doi.org/10.1016/j.patcog.2013.09.012
DOI https://doi.org/10.1016/j.patcog.2013.09.012
Keywords Face hallucination; Sparse local-pixel structure; Super-resolution; Sparse representation
Publisher URL https://www.sciencedirect.com/science/article/pii/S0031320313003841
Copyright Statement Copyright information regarding this work can be found at the following address: http://creativecommons.org/licenses/by-nc-nd/4.0

Files

1.pdf (1.4 Mb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://creativecommons.org/licenses/by-nc-nd/4.0





You might also like



Downloadable Citations

;