A novel correspondence-based face-hallucination method

Zhuo Hui, Wenbo Liu, Kin Man Lam

Research output: Journal article publicationJournal articleAcademic researchpeer-review

8 Citations (Scopus)


We assume that the input LR and estimated HR images are under the same view-point and illumination condition, i.e. the setting of image super-resolution. At the core of our techniques is that the facial images can be decomposed as a texture vector, characterized in terms of the appearance, and a shape vector, characterized in terms of the geometry variations. This enables a two-stage successive estimation framework that is geometry aware and obviates the needs in sophisticated optimizations. In particular, the proposed technique first solves for appearance of the HR faces form the correspondence derived between an interpolated LR face and its corresponding HR face. Given the texture of the HR faces, we incorporate optical flow to solve the local structure at sub-pixel level for the HR faces; here, we use additional geometry inspired priors to further regularize the solution. Experimental results show that our method outperforms other state-of-the-art methods in terms of retaining the facial-feature shape and the estimation of novel features.
Original languageEnglish
Pages (from-to)171-184
Number of pages14
JournalImage and Vision Computing
Publication statusPublished - 1 Apr 2017


  • Corresponding-based method
  • Face hallucination
  • Face super-resolution
  • Local kernel

ASJC Scopus subject areas

  • Signal Processing
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'A novel correspondence-based face-hallucination method'. Together they form a unique fingerprint.

Cite this