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

The aim of this work is learning to reshape the object in an input image toan arbitrary new shape, by just simply providing a single reference image withan object instance in the desired shape. We propose a new GenerativeAdversarial Network (GAN) architecture for such an object reshaping problem,named ReshapeGAN. The network can be tailored for handling all kinds of problemsettings, including both within-domain (or single-dataset) reshaping andcross-domain (typically across mutiple datasets) reshaping, with paired orunpaired training data. The appearance of the input object is preserved in allcases, and thus it is still identifiable after reshaping, which has never beenachieved as far as we are aware. We present the tailored models of the proposedReshapeGAN for all the problem settings, and have them tested on 8 kinds ofreshaping tasks with 13 different datasets, demonstrating the ability ofReshapeGAN on generating convincing and superior results for object reshaping.To the best of our knowledge, we are the first to be able to make one GANframework work on all such object reshaping tasks, especially the cross-domaintasks on handling multiple diverse datasets. We present here both ablationstudies on our proposed ReshapeGAN models and comparisons with thestate-of-the-art models when they are made comparable, using all kinds ofapplicable metrics that we are aware of.

ReshapeGAN: Object Reshaping by Providing A Single Reference Image