Hallucinating Compressed Face Images

Chih Yuan Yang, Sifei Liu, Ming Hsuan Yang*

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

18 Scopus citations


A face hallucination algorithm is proposed to generate high-resolution images from JPEG compressed low-resolution inputs by decomposing a deblocked face image into structural regions such as facial components and non-structural regions like the background. For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition. For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts. Two sets of gradient maps extracted from these two regions are combined to guide an optimization process of generating the hallucination image. Numerous experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art hallucination methods on JPEG compressed face images with different poses, expressions, and illumination conditions.

Original languageEnglish
Pages (from-to)597-614
Number of pages18
JournalInternational Journal of Computer Vision
Issue number6
StatePublished - 01 06 2018
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2017, Springer Science+Business Media, LLC.


  • Face hallucination
  • Image denoising
  • JPEG compression
  • Landmark points
  • Super resolution


Dive into the research topics of 'Hallucinating Compressed Face Images'. Together they form a unique fingerprint.

Cite this