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 aims to transfer an in-shop garment onto aspecific person. Existing methods employ a global warping module to model theanisotropic deformation for different garment parts, which fails to preservethe semantic information of different parts when receiving challenging inputs(e.g, intricate human poses, difficult garments). Moreover, most of themdirectly warp the input garment to align with the boundary of the preservedregion, which usually requires texture squeezing to meet the boundary shapeconstraint and thus leads to texture distortion. The above inferior performancehinders existing methods from real-world applications. To address theseproblems and take a step towards real-world virtual try-on, we propose aGeneral-Purpose Virtual Try-ON framework, named GP-VTON, by developing aninnovative Local-Flow Global-Parsing (LFGP) warping module and a DynamicGradient Truncation (DGT) training strategy. Specifically, compared with theprevious global warping mechanism, LFGP employs local flows to warp garmentsparts individually, and assembles the local warped results via the globalgarment parsing, resulting in reasonable warped parts and a semantic-correctintact garment even with challenging inputs.On the other hand, our DGT trainingstrategy dynamically truncates the gradient in the overlap area and the warpedgarment is no more required to meet the boundary constraint, which effectivelyavoids the texture squeezing problem. Furthermore, our GP-VTON can be easilyextended to multi-category scenario and jointly trained by using data fromdifferent garment categories. Extensive experiments on two high-resolutionbenchmarks demonstrate our superiority over the existing state-of-the-artmethods.

GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning