Blind face images deblurring with enhancement

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Qing Qi
  • Jichang Guo
  • Chongyi Li
  • Lijun Xiao

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)2975–2995
Journal / PublicationMultimedia Tools and Applications
Volume80
Issue number2
Online published18 Sep 2020
Publication statusPublished - Jan 2021

Abstract

Face images deblurring has achieved advanced development; however, existing methods involve high computational cost problems. Furthermore, the recovered face images by current methods have the problems of over-smooth textures, ringing artifacts, and poor details. We consider the problem of face images deblurring as a semantic generation task. In this paper, we propose a generative adversarial network (GAN), which includes a perception-inspired blurry removal generator and a discriminator. The proposed generator reconstructs the latent deblurred image by a U-net based network that contains an enhancement module. Face images are highly structured, and thus can be served as a class-specific prior. Considering this, we propose a perceptual loss function to regularize the recovery of face images, which introduces more clear details and reduces the effects of artifacts. The proposed method has a robust capability of generating realistic face images with pleasant visual effects. Extensive experiments on both synthetic and real-world face images demonstrate that the proposed method is comparable with state-of-the-art methods.

Research Area(s)

  • Deep learning, Enhancement module, Face images deblurring

Citation Format(s)

Blind face images deblurring with enhancement. / Qi, Qing; Guo, Jichang; Li, Chongyi; Xiao, Lijun.

In: Multimedia Tools and Applications, Vol. 80, No. 2, 01.2021, p. 2975–2995.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review