Do vision models perceive illusory motion in static images like humans?

TL;DR

This study evaluates whether current optical flow models can perceive illusory motion in static images like humans, revealing significant gaps and insights for future human-centric AI development.

Contribution

It demonstrates that most models fail to perceive static illusory motion, while a human-inspired model shows promising perception under specific conditions.

Findings

Most models do not perceive illusory motion in static images.

The Dual-Channel model perceives rotation during saccade simulation.

Both luminance and color signals, plus attention mechanisms, influence perception.

Abstract

Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategies. Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge. While recent DNN-based motion models can reproduce dynamic illusions such as reverse-phi, it remains unclear whether they can perceive illusory motion in static images, exemplified by the Rotating Snakes illusion. We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception. Under simulated conditions mimicking saccadic eye movements, only the human-inspired Dual-Channel model exhibits the expected rotational motion, with the closest correspondence emerging during the saccade simulation. Ablation analyses further reveal that both luminance-based and higher-order color--feature--based motion signals contribute to this behavior and that a recurrent attention mechanism is critical for integrating local cues. Our results highlight a substantial gap between current optical-flow models and human visual motion processing, and offer insights for developing future motion-estimation systems with improved correspondence to human perception and human-centric AI.