Personalized Color Vision Deficiency Friendly Image Generation

Abstract

Approximately, 350 million people, a proportion of 8%, suffer from color vision deficiency (CVD). While image generation algorithms have been highly successful in synthesizing high-quality images, CVD populations are unintentionally excluded from target users and have difficulties understanding the generated images as normal viewers do. Although a straightforward baseline can be formed by combining generation models and recolor compensation methods as the post-processing, the CVD friendliness of the result images is still limited since the input image content of recolor methods is not CVD-oriented and will be fixed during the recolor compensation process. Besides, the CVD populations can not be fully served since the varying degrees of CVD are often neglected in recoloring methods.

To address these issues, we introduce a personalized CVD-friendly image generation algorithm distinguished by two key features: (i) the ability to produce CVD-oriented images that align with the needs of CVD populations, and (ii) the capacity to generate continuous personalized images for people with various CVD degrees through disentangling the color representation based on a triple-latent structure. Quantitative and qualitative experiments affirm the effectiveness of our proposed image generation model, demonstrating its practicality and superior performance compared to standard generation models and combination baselines across multiple datasets.