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

Natural images can be regarded as residing in a manifold that is embedded ina higher dimensional Euclidean space. Generative Adversarial Networks (GANs)try to learn the distribution of the real images in the manifold to generatesamples that look real. But the results of existing methods still exhibit manyunpleasant artifacts and distortions even for the cases where the desiredground truth target images are available for supervised learning such as insingle image super resolution (SISR). We probe for ways to alleviate theseproblems for supervised GANs in this paper. We explicitly apply the LipschitzContinuity Condition (LCC) to regularize the GAN. An encoding network that mapsthe image space to a new optimal latent space is derived from the LCC, and itis used to augment the GAN as a coupling component. The LCC is also convertedto new regularization terms in the generator loss function to enforce localinvariance. The GAN is optimized together with the encoding network in anattempt to make the generator converge to a more ideal and disentangled mappingthat can generate samples more faithful to the target images. When the proposedmodels are applied to the single image super resolution problem, the resultsoutperform the state of the art.

Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization