Crafting Synthetic Realities: Examining Visual Realism and Misinformation Potential of Photorealistic AI-Generated Images

TL;DR

This study analyzes the realism and misinformation potential of AI-generated images, revealing their high quality and risks, especially in depicting humans, and offers guidelines for responsible use.

Contribution

First empirical investigation of photorealistic AI-generated images across platforms using mixed methods, highlighting their realism and misinformation risks.

Findings

AIGIs often depict humans with high realism and surrealism.

Low overt signals of AI production in photorealistic images.

Implications for visual misinformation and risk mitigation.

Abstract

Advances in generative models have created Artificial Intelligence-Generated Images (AIGIs) nearly indistinguishable from real photographs. Leveraging a large corpus of 30,824 AIGIs collected from Instagram and Twitter, and combining quantitative content analysis with qualitative analysis, this study unpacks AI photorealism of AIGIs from four key dimensions, content, human, aesthetic, and production features. We find that photorealistic AIGIs often depict human figures, especially celebrities and politicians, with a high degree of surrealism and aesthetic professionalism, alongside a low degree of overt signals of AI production. This study is the first to empirically investigate photorealistic AIGIs across multiple platforms using a mixed-methods approach. Our findings provide important implications and insights for understanding visual misinformation and mitigating potential risks associated with photorealistic AIGIs. We also propose design recommendations to enhance the responsible use of AIGIs.