Global Texture Enhancement for Fake Face Detection in the Wild

Zhengzhe LIU, Xiaojuan QI, Philip H.S. TORR

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

213 Citations (Scopus)

Abstract

Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings. On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than99.9%accuracyin discerning fake/real images. In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets. Motivated by the above observations, we propose a new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection. Experimental results on several datasets demonstrate that our Gram-Netoutperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEGcompression, blur, and noise.

Original languageEnglish
Title of host publication2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 : Proceedings
Pages8057-8066
Number of pages10
ISBN (Electronic)9781728171685
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
ISSN (Print)1063-6919

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Country/TerritoryUnited States
CityVirtual, Online
Period14/06/2019/06/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

This work was supported by the ERC grant ERC-2012-AdG 321162-HELIOS, EPSRC grant Seebibyte EP/M013774/1 and EPSRC/MURI grant EP/N019474/1.

Fingerprint

Dive into the research topics of 'Global Texture Enhancement for Fake Face Detection in the Wild'. Together they form a unique fingerprint.

Cite this