当前位置: X-MOL 学术arXiv.cs.CY › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
More Real than Real: A Study on Human Visual Perception of Synthetic Faces
arXiv - CS - Computers and Society Pub Date : 2021-06-14 , DOI: arxiv-2106.07226
Federica Lago, Cecilia Pasquini, Rainer Böhme, Hélène Dumont, Valérie Goffaux, Giulia Boato

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.

中文翻译:

比真实更真实:人类对合成面孔的视觉感知研究

深度假货在过去几年变得非常流行,这也归功于它们越来越逼真。因此,需要衡量人类在面对尖端创作技术时区分真实和合成人脸图像的能力。我们描述了我们进行的感知实验的设计和结果,其中广泛多样的志愿者群体已经接触到由最先进的生成对抗网络(即 PG-GAN、StyleGAN、样式GAN2)。实验结果揭示了我们应该多么强烈地质疑我们人类区分真实面孔和现代人工智能生成的合成面孔的能力。
更新日期:2021-06-15
down
wechat
bug