Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights

• URL: http://arxiv.org/abs/2009.11924v2
• Date: Mon, 12 Oct 2020 19:28:14 GMT
• Title: Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights
• Authors: Shu Hu, Yuezun Li, and Siwei Lyu
• Abstract summary: We show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models.
• Score: 42.83346543247565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces.

Related papers

• Detecting High-Quality GAN-Generated Face Images using Neural Networks [23.388645531702597]
  We propose a new strategy to differentiate GAN-generated images from authentic images by leveraging spectral band discrepancies. In particular, we enable the digital preservation of face images using the Cross-band co-occurrence matrix and spatial co-occurrence matrix. We show that the performance boost is particularly significant and achieves more than 92% in different post-processing environments.
  arXiv  Detail & Related papers  (2022-03-03T13:53:27Z)
• Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces [40.15016121723183]
  We show that GAN-generated faces can be exposed via irregular pupil shapes. This phenomenon is caused by the lack of physiological constraints in the GAN models.
  arXiv  Detail & Related papers  (2021-09-01T03:25:50Z)
• SynFace: Face Recognition with Synthetic Data [83.15838126703719]
  We devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the performance gap. We also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
  arXiv  Detail & Related papers  (2021-08-18T03:41:54Z)
• Heterogeneous Face Frontalization via Domain Agnostic Learning [74.86585699909459]
  We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations. DAL-GAN consists of a generator with an auxiliary classifier and two discriminators which capture both local and global texture discriminations for better synthesis.
  arXiv  Detail & Related papers  (2021-07-17T20:41:41Z)
• LEGAN: Disentangled Manipulation of Directional Lighting and Facial Expressions by Leveraging Human Perceptual Judgements [7.5603864775031004]
  We propose LEGAN, a novel synthesis framework that leverages perceptual quality judgments for jointly manipulating lighting and expressions in face images. LEGAN disentangles the lighting and expression subspaces and performs transformations in the feature space before upscaling to the desired output image. We also conduct a perceptual study using images synthesized by LEGAN and other GAN models and show the correlation between our quality estimation and visual fidelity.
  arXiv  Detail & Related papers  (2020-10-04T01:56:54Z)
• CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis [34.41021278275805]
  Last-generation GAN models allow to generate synthetic images which are visually indistinguishable from natural ones. We propose a method for distinguishing GAN-generated from natural images by exploiting inconsistencies among spectral bands.
  arXiv  Detail & Related papers  (2020-07-25T10:55:04Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)
• Dual-Attention GAN for Large-Pose Face Frontalization [59.689836951934694]
  We present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization. Specifically, a self-attention-based generator is introduced to integrate local features with their long-range dependencies. A novel face-attention-based discriminator is applied to emphasize local features of face regions.
  arXiv  Detail & Related papers  (2020-02-17T20:00:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.