Which Visual Features Influence Perceived Authenticity in AI-Generated Portrait Photography? A Mixed-Methods Study

As AI-generated portrait images become increasingly photorealistic, understanding how viewers assess their authenticity is critical for applications in digital media, content verification, and generative system design. This study investigates which visual cues most significantly affect perceived authenticity in AI-generated portrait photography (AIGPP). Employing a mixed-methods approach, we first identified eight candidate visual features—skin texture (ST), spatial consistency (SC), facial proportion (FP), pose naturalness (PN), expression naturalness (EN), limb realism (LR), styling (STY), and composition (CP)—through a systematic literature review (SLR) and expert interviews. A subsequent survey involving 508 participants was conducted using AI-generated portraits as stimuli. Statistical analyses, including correlation and multiple regression, revealed that facial-related features, particularly EN, FP, and ST, were the strongest predictors of authenticity perception. These findings provide empirical insights into how micro-level visual cues influence realism judgment and may inform the optimization of AI image generation systems and visual evaluation protocols.