The DOI matches its Crossref record; 39 of the 43 references it cites were found in a registry or an index.
Global Texture Enhancement for Fake Face Detection in the Wild
Open accessAbstract
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. More importantly, our Gram-Net generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detecting fake natural images.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Common visual artifacts include lighting and color mismatches [51], unusual facial textures [52], irregular frequency patterns [56], and inconsistent edge blending [59].”
From Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges (2024) · cites this paper as [52]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Several studies have shown that the frequency spectrum of GAN-generated images often contains distinctive patterns - 'checkerboards', particularly in the middle and high-frequency bands [85-89].”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [88]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Textural Features for Image Classification
Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1973.4309314 · Cited by 22,886
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
(2017) · Cited by 11,625
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Research works printed but not linked: 3
- kodali, 2017, On convergence and stability of gans
- paszke, 2017, On Automatic Differentiation
- arjovsky, 0, Wasser-stein generative adversarial networks, International Conference on Machine Learning, 214
Cited by
Sorted by citations
Items 401–405 of 405
In2CLR: Joint Intra-Inter Curriculum Learning with Review for Degraded Fake Image Detection
Li, Y., Liu, B., Wu, Y., & Li, R. (2026) · doi:10.1109/cvprf71909.2026.00234
A Systematic Review of Facial Data Augmentation for Deepfake Detection
Ahmed, N. U. R., Badshah, A., Tajammul, A., Alghushairy, O., Alharbey, R., & Daud, A. (2026) · Journal of Advances in Information Technology · doi:10.12720/jait.17.10.1842-1866
Chen, L., & Ding, Y. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3744649
Dynamic Mask Guided Synthetic Image Detection via Mid-Frequency Enhanced Diffusion Priors
Wang, Q., Ba, G., Yin, J., & Zou, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729947
Durmuş, M. (2026) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap71869.2026.11728043
Metadata
- Authors
- Liu, Z., Qi, X., & Torr, P. H. S.
- Affiliations
- University of Oxford (GB)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 8057-8066
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3034795015
- Cited by
- 401
- References
- 43
- Citations by year
- 2026: 55 · 2025: 102 · 2024: 71 · 2023: 64 · 2022: 57 · 2021: 42 · 2020: 9
- FWCI
- 13.26
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- The HKU Scholars Hub (University of Hong Kong) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Royal Academy of Engineering
- Multidisciplinary University Research Initiative (EP/N019474/1)
- Engineering and Physical Sciences Research Council (EP/N019474/1, EP/M013774/1, EP/M013774/, ERC-2012-AdG 321162-HELIOS, Seebibyte EP/M013774/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- face forgery detection, deepfake detection, GAN-generated images
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
