mlsanityData to 14 Oct 2026

More Real than Real: A Study on Human Visual Perception of Synthetic Faces

arXiv 2106.07226 ↗First posted 14 Jun 2021cs.CV cs.CYcited by 23

Not on the map. Why?

Abstract (arXiv)

Deep fakes became extremely popular in the last years, also thanks to their increasing realism. Therefore, there is the need to measures human's ability to distinguish between real and synthetic face images when confronted with cutting-edge creation technologies. We describe the design and results of a perceptual experiment we have conducted, where a wide and diverse group of volunteers has been exposed to synthetic face images produced by state-of-the-art Generative Adversarial Networks (namely, PG-GAN, StyleGAN, StyleGAN2). The experiment outcomes reveal how strongly we should call into question our human ability to discriminate real faces from synthetic ones generated through modern AI.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 8 of its 16 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

8 of 16 references.

References · 8

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 632
  5. 2020Media Forensics and DeepFakes: an overviewcited by 209
  6. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 119
  7. 2018Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networkscited by 43
  8. 2021Image-to-Video Generation via 3D Facial Dynamicscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 5; 2024: 4; 2025: 4; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 123
  2. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  3. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  4. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  5. 2021Towards Universal GAN Image Detectioncited by 26
  6. 2023A Representative Study on Human Detection of Artificially Generated Media Across Countriescited by 22
  7. 2021A Study of the Human Perception of Synthetic Facescited by 14
  8. 2024Characteristics and prevalence of fake social media profiles with AI-generated facescited by 14
  9. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 14
  10. 2022Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Facescited by 11
  11. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  12. 2024AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Imagescited by 10
11 more
  1. 2025TrueFake: A Real World Case Dataset of Last Generation Fake Images also Shared on Social Networkscited by 8
  2. 2022PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasetscited by 1
  3. 2023Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instancescited by 1
  4. 2023ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysiscited by 1
  5. 2024Analysis of Human Perception in Distinguishing Real and AI-Generated Faces: An Eye-Tracking Based Studycited by 1
  6. 2025Synthetic Art Generation and DeepFake Detection A Study on Jamini Roy Inspired Datasetcited by 1
  7. 2025Advance Fake Video Detection via Vision Transformerscited by 1
  8. 2026Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensicscited by 0
  9. 2026Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidencecited by 0
  10. 2026Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Imagescited by 0
  11. 2026Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibrationcited by 0