Eight images used in the study; four of them are synthetic. Can you tell which ones? (Answers at bottom of the article.)
A study published [sagepub.com] in the peer-reviewed journal Psychological Science [sagepub.com] on Monday found that AI-generated faces generated with three year-old technology, particularly those representing white individuals, were perceived as more real than actual face photographs, reports The Guardian [theguardian.com]. The finding did not extend to images of people of color, likely due to AI models being trained predominantly on images of white individuals—a common bias [nytimes.com] that is well-known in machine learning research.
Researchers used real and synthetic images sourced from an earlier study [osf.io], with the synthetic ones generated by Nvidia's StyleGAN2 [github.com] image generator, which can create realistic faces using image synthesis. It's worth noting that StyleGAN2 was released in 2020, and AI image synthesis has progressed rapidly since then—but newer AI models were not involved in the study.