Corpus ID: 210921129

FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles

@article{Huang2020FakeLocatorRL,
  title={FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles},
  author={Yihao Huang and Felix Juefei-Xu and Run Wang and Xiaofei Xie and Lei Ma and Jianwen Li and Weikai Miao and Yang Liu and Geguang Pu},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.09598}
}
  • Yihao Huang, Felix Juefei-Xu, +6 authors Geguang Pu
  • Published in ArXiv 2020
  • Computer Science
  • Nowadays, full face synthesis and partial face manipulation by virtue of the generative adversarial networks (GANs) have raised wide public concern. In the digital media forensics area, detecting and ultimately locating the image forgery have become imperative. Although many methods focus on fake detection, only a few put emphasis on the localization of the fake regions. Through analyzing the imperfection in the upsampling procedures of the GAN-based methods and recasting the fake localization… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    Detecting and Simulating Artifacts in GAN Fake Images

    VIEW 1 EXCERPT

    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

    • Tero Karras, Samuli Laine, Timo Aila. A style-based generator architecture for gen networks
    • pages 4401–4410,
    • 2019
    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    On the Detection of Digital Face Manipulation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    stability

    • Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. Progressive growing of gans for improved quality
    • and variation. arXiv preprint arXiv:1710.10196,
    • 2017
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints

    • Ning Yu, Larry Davis, Mario Fritz
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    • 2019
    VIEW 1 EXCERPT

    Analyzing and Improving the Image Quality of StyleGAN

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    FakeSpotter: A Simple Baseline for Spotting AI-Synthesized Fake Faces

    VIEW 1 EXCERPT