Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
On potentials of regularized Wasserstein generative adversarial networks for realistic hallucination of tiny faces
Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing, Jiangsu, Peoples R China.;Nanjing Univ Posts & Telecommun, Natl Engn Res Ctr Commun & Networking, Nanjing, Jiangsu, Peoples R China..
Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing, Jiangsu, Peoples R China..
Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing, Jiangsu, Peoples R China..
Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing, Jiangsu, Peoples R China..
Show others and affiliations
2019 (English)In: Neurocomputing, ISSN 0925-2312, E-ISSN 1872-8286, Vol. 364, p. 1-15Article in journal (Refereed) Published
Abstract [en]

Super-resolution of facial images, a.k.a. face hallucination, has been intensively studied in the past decades due to the increasingly emerging analysis demands in video surveillance, e.g., face detection, verification, identification. However, the actual performance of most previous hallucination approaches will drop dramatically when a very low-res tiny face is provided, due to the challenging multimodality of the problem as well as lack of an informative prior as a strong semantic guidance. Inspired by the latest progress in deep unsupervised learning, this paper focuses on tiny faces of size 16 x 16 pixels, hallucinating them to their 8 x upsampling versions by exploring the potentials of Wasserstein generative adversarial networks (WGAN). Besides a pixel-wise L2 regularization term imposed to the generative model, it is found that our advocated autoencoding generator with both residual and skip connections is a critical component for WGAN representing the facial contour and semantic content to a reasonable precision. With the additional Lipschitz penalty and architectural considerations for the critic in WGAN, the proposed approach finally achieves state-of-the-art hallucination performance in terms of both visual perception and objective assessment. The cropped CelebA face dataset is primarily used to aid the tuning and analysis of the new method, termed as tfh-WGAN. Experimental results demonstrate that the proposed approach not only achieves realistic hallucination of tiny faces, but also adapts to pose, expression, illuminance and occluded variations to a great degree.

Place, publisher, year, edition, pages
ELSEVIER , 2019. Vol. 364, p. 1-15
Keywords [en]
Super-resolution, Face hallucination, Wasserstein GAN, Autoencoding, ResNet, Skip connections
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-260159DOI: 10.1016/j.neucom.2019.07.046ISI: 000484070700001Scopus ID: 2-s2.0-85071384887OAI: oai:DiVA.org:kth-260159DiVA, id: diva2:1356190
Note

QC 20191001

Available from: 2019-10-01 Created: 2019-10-01 Last updated: 2019-10-01Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Li, Haibo

Search in DiVA

By author/editor
Li, Haibo
By organisation
Media Technology and Interaction Design, MID
In the same journal
Neurocomputing
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf