Illusions in Humans and AI: How Visual Perception Aligns and Diverges

TL;DR

This paper compares human and AI visual perception through illusions, revealing similarities and differences that inform the development of more aligned and robust AI vision systems.

Contribution

It systematically analyzes how AI perceives visual illusions, identifying both shared effects and unique AI-specific illusions, to improve understanding of perception alignment.

Findings

AI exhibits some illusion-like effects through training or pattern recognition

AI has unique illusions such as pixel sensitivity and hallucinations

Comparison reveals gaps and vulnerabilities in AI perception

Abstract

By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust, interpretable, and human-aligned artificial intelligence (AI) vision systems. In particular, visual illusions expose how human perception is based on contextual assumptions rather than raw sensory data. As artificial vision systems increasingly perform human-like tasks, it is important to ask: does AI experience illusions, too? Does it have unique illusions? This article explores how AI responds to classic visual illusions that involve color, size, shape, and motion. We find that some illusion-like effects can emerge in these models, either through targeted training or as by-products of pattern recognition. In contrast, we also identify illusions unique to AI, such as pixel-level sensitivity and hallucinations, that lack human counterparts. By systematically comparing human and AI responses to visual illusions, we uncover alignment gaps and AI-specific perceptual vulnerabilities invisible to human perception. These findings provide insights for future research on vision systems that preserve human-beneficial perceptual biases while avoiding distortions that undermine trust and safety.