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

We propose DeepMetaHandles, a 3D conditional generative model based on meshdeformation. Given a collection of 3D meshes of a category and theirdeformation handles (control points), our method learns a set of meta-handlesfor each shape, which are represented as combinations of the given handles. Thedisentangled meta-handles factorize all the plausible deformations of theshape, while each of them corresponds to an intuitive deformation. A newdeformation can then be generated by sampling the coefficients of themeta-handles in a specific range. We employ biharmonic coordinates as thedeformation function, which can smoothly propagate the control points'translations to the entire mesh. To avoid learning zero deformation asmeta-handles, we incorporate a target-fitting module which deforms the inputmesh to match a random target. To enhance deformations' plausibility, we employa soft-rasterizer-based discriminator that projects the meshes to a 2D space.Our experiments demonstrate the superiority of the generated deformations aswell as the interpretability and consistency of the learned meta-handles.

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates