English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generative adversarial networks (GANs) have drawn enormous attention due tothe simple yet effective training mechanism and superior image generationquality. With the ability to generate photo-realistic high-resolution (e.g.,$1024\times1024$) images, recent GAN models have greatly narrowed the gapsbetween the generated images and the real ones. Therefore, many recent worksshow emerging interest to take advantage of pre-trained GAN models byexploiting the well-disentangled latent space and the learned GAN priors. Inthis paper, we briefly review recent progress on leveraging pre-trainedlarge-scale GAN models from three aspects, i.e., 1) the training of large-scalegenerative adversarial networks, 2) exploring and understanding the pre-trainedGAN models, and 3) leveraging these models for subsequent tasks like imagerestoration and editing. More information about relevant methods andrepositories can be found at https://github.com/csmliu/pretrained-GANs.

A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration