Evaluating Model Perception of Color Illusions in Photorealistic Scenes

We study the perception of color illusions by visionlanguage models. Color illusion, where a person's visual system perceives color differently from actual color, is wellstudied in human vision. However, it remains underexplored whether vision-language models (VLMs), trained on largescale human data, exhibit similar perceptual biases when confronted with such color illusions. We propose an automated framework for generating color illusion images, resulting in RCID (Realistic Color Illusion Dataset), a dataset of 19,000 realistic illusion images. Our experiments show that all studied VLMs exhibit perceptual biases similar human vision. Finally, we train a model to distinguish both human perception and actual pixel differences.