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

In this paper, we tackle the problem of static 3D cloth draping on virtualhuman bodies. We introduce a two-stream deep network model that produces avisually plausible draping of a template cloth on virtual 3D bodies byextracting features from both the body and garment shapes. Our network learnsto mimic a Physics-Based Simulation (PBS) method while requiring two orders ofmagnitude less computation time. To train the network, we introduce loss termsinspired by PBS to produce plausible results and make the modelcollision-aware. To increase the details of the draped garment, we introducetwo loss functions that penalize the difference between the curvature of thepredicted cloth and PBS. Particularly, we study the impact of mean curvaturenormal and a novel detail-preserving loss both qualitatively andquantitatively. Our new curvature loss computes the local covariance matricesof the 3D points, and compares the Rayleigh quotients of the prediction andPBS. This leads to more details while performing favorably or comparablyagainst the loss that considers mean curvature normal vectors in the 3Dtriangulated meshes. We validate our framework on four garment types forvarious body shapes and poses. Finally, we achieve superior performance againsta recently proposed data-driven method.

GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss