Early experience of adopting a generative diffusion model for the synthesis of fundus photographs

After training, serial multiple denoising U-Nets can generate FPs using random noise seeds. The input image size was set to a pixel resolution of 128 × 128. This was the maximum resolution required to finalize the proper training with our computational resources.

We set the time step to the default value of 1000 because fewer numbers produce severely noisy or blurred synthetic images. All codes for the implementation of the DDPM are available on the webpage (github.com/lucidrains/denoising-diffusion-pytorch). For reproducibility, our FP images and modified codes, which can be implemented in Google Colaboratory, were released in the data repository.