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

Image-based virtual try-on is one of the most promising applications ofhuman-centric image generation due to its tremendous real-world potential. Inthis work, we take a step forwards to explore versatile virtual try-onsolutions, which we argue should possess three main properties, namely, theyshould support unsupervised training, arbitrary garment categories, andcontrollable garment editing. To this end, we propose acharacteristic-preserving end-to-end network, the PAtch-routedSpaTially-Adaptive GAN++ (PASTA-GAN++), to achieve a versatile system forhigh-resolution unpaired virtual try-on. Specifically, our PASTA-GAN++ consistsof an innovative patch-routed disentanglement module to decouple the intactgarment into normalized patches, which is capable of retaining garment styleinformation while eliminating the garment spatial information, thus alleviatingthe overfitting issue during unsupervised training. Furthermore, PASTA-GAN++introduces a patch-based garment representation and a patch-guided parsingsynthesis block, allowing it to handle arbitrary garment categories and supportlocal garment editing. Finally, to obtain try-on results with realistic texturedetails, PASTA-GAN++ incorporates a novel spatially-adaptive residual module toinject the coarse warped garment feature into the generator. Extensiveexperiments on our newly collected UnPaired virtual Try-on (UPT) datasetdemonstrate the superiority of PASTA-GAN++ over existing SOTAs and its abilityfor controllable garment editing.

PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on