Evaluating Model Perception of Color Illusions in Photorealistic Scenes
Abstract
We study the perception of color illusions by vision-language models. Color illusion, where a person's visual system perceives color differently from actual color, is well-studied in human vision. However, it remains underexplored whether vision-language models (VLMs), trained on large-scale 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.
Cite
Text
Mao et al. "Evaluating Model Perception of Color Illusions in Photorealistic Scenes." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00731Markdown
[Mao et al. "Evaluating Model Perception of Color Illusions in Photorealistic Scenes." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/mao2025cvpr-evaluating/) doi:10.1109/CVPR52734.2025.00731BibTeX
@inproceedings{mao2025cvpr-evaluating,
title = {{Evaluating Model Perception of Color Illusions in Photorealistic Scenes}},
author = {Mao, Lingjun and Tang, Zineng and Suhr, Alane},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {7805-7814},
doi = {10.1109/CVPR52734.2025.00731},
url = {https://mlanthology.org/cvpr/2025/mao2025cvpr-evaluating/}
}