Prompt-Driven Color Accessibility Evaluation in Diffusion-based Image Generation Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914383041396736 |
|---|---|
| author | Zhuang, Xinyao Echevarria, Jose Akşit, Kaan |
| author_facet | Zhuang, Xinyao Echevarria, Jose Akşit, Kaan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09832 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prompt-Driven Color Accessibility Evaluation in Diffusion-based Image Generation Models Zhuang, Xinyao Echevarria, Jose Akşit, Kaan Graphics Human-Computer Interaction 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. |
| title | Prompt-Driven Color Accessibility Evaluation in Diffusion-based Image Generation Models |
| topic | Graphics Human-Computer Interaction |
| url | https://arxiv.org/abs/2603.09832 |