Prompt-Driven Color Accessibility Evaluation in Diffusion-based Image Generation Models
This addresses color accessibility issues in generative AI for users with CVD, but it is incremental as it focuses on evaluation rather than solving the problem directly.
The study tackled the problem of color accessibility for users with Color Vision Deficiencies (CVD) in images generated by diffusion models, finding that existing models struggle to reliably respond to accessibility-focused prompts and introducing CVDLoss as a new metric to evaluate this.
Generative models are increasingly integrated into creative workflows. While text-to-image generation excels in visual quality and diversity, color accessibility for users with Color Vision Deficiencies (CVD) remains largely unexplored. Our work systematically evaluates color accessibility in images generated by a common pretrained diffusion model, prompted to improve accessibility across diverse categories. We quantify performance using established, off-the-shelf CVD simulation methods and introduce "CVDLoss", a new metric measuring differences in image gradients indicative of structural detail. We validate CVDLoss against a commonly used daltonization method, demonstrating its sensitivity to color accessibility modifications. Applying CVDLoss to model outputs reveals that existing diffusion models struggle to reliably respond to accessibility-focused prompts. Consequently, our study establishes CVDLoss as a valuable evaluation tool for accessibility-aware image generation and post-processing, offering insights into current generative models' limitations in addressing color accessibility.