GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation
This work addresses a domain-specific challenge in biological imaging by generating realistic EM images, which is incremental as it builds on existing GAN frameworks.
The paper tackled the problem of generating realistic electron microscopy (EM) images by proposing a new GAN discriminator architecture with skip patches to handle complex structures, resulting in improved image generation compared to existing methods like pix2pix.
Generating realistic electron microscopy (EM) images has been a challenging problem due to their complex global and local structures. Isola et al. proposed pix2pix, a conditional Generative Adversarial Network (GAN), for the general purpose of image-to-image translation; which fails to generate realistic EM images. We propose a new architecture for the discriminator in the GAN providing access to multiple patch sizes using skip patches and generating realistic EM images.