TY - GEN
T1 - Personalized Image Generation for Color Vision Deficiency Population
AU - Jiang, Shuyi
AU - Liu, Daochang
AU - Li, Dingquan
AU - Xu, Chang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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. Instead, we propose a personalized CVD-friendly image generation algorithm with two key characteristics: (i) generating CVD-oriented images aligned with the needs of CVD populations; (ii) generating continuous personalized images for people with various CVD degrees through disentangling the color representation based on a triple-latent structure. Quantitative and qualitative experiments indicate our proposed image generation model can generate practical and compelling results compared to the normal generation model and combination baselines on several datasets. The code is available at: https://github.com/Jiangshuyi0V0/CVD-GAN.git
AB - 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. Instead, we propose a personalized CVD-friendly image generation algorithm with two key characteristics: (i) generating CVD-oriented images aligned with the needs of CVD populations; (ii) generating continuous personalized images for people with various CVD degrees through disentangling the color representation based on a triple-latent structure. Quantitative and qualitative experiments indicate our proposed image generation model can generate practical and compelling results compared to the normal generation model and combination baselines on several datasets. The code is available at: https://github.com/Jiangshuyi0V0/CVD-GAN.git
UR - http://www.scopus.com/inward/record.url?scp=85182636548&partnerID=8YFLogxK
U2 - 10.1109/ICCV51070.2023.02063
DO - 10.1109/ICCV51070.2023.02063
M3 - Conference paper
AN - SCOPUS:85182636548
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 22514
EP - 22523
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - IEEE, Institute of Electrical and Electronics Engineers
T2 - 2023 IEEE/CVF International Conference on Computer Vision
Y2 - 2 October 2023 through 6 October 2023
ER -