Saved in:
Bibliographic Details
Main Authors: Roy, Nishith Ranjon, Rawnaq, Nailah, Kaman, Tulin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.00558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910392933941248
author Roy, Nishith Ranjon
Rawnaq, Nailah
Kaman, Tulin
author_facet Roy, Nishith Ranjon
Rawnaq, Nailah
Kaman, Tulin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00558
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation
Roy, Nishith Ranjon
Rawnaq, Nailah
Kaman, Tulin
Image and Video Processing
Computer Vision and Pattern Recognition
92B20
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.
title GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation
topic Image and Video Processing
Computer Vision and Pattern Recognition
92B20
url https://arxiv.org/abs/2404.00558