
The author introduces a novel population model for retinal fundus images that effectively disentangles patient attributes from technical factors, enabling controllable and realistic image generation through a novel disentanglement loss based on distance correlation.


coremsg

Disentangling-Retinal-Fundus-Images-with-Generative-Models


Disentangling Retinal Fundus Images with Generative Models


title_rewrite


Retinal fundus image disentanglement enables controllable and realistic image generation by effectively separating patient attributes from technical factors.


retinal-image-disentanglement-with-generative-models


Retinal Image Disentanglement with Generative Models
