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

Learning 3D shape representation with dense correspondence for deformableobjects is a fundamental problem in computer vision. Existing approaches oftenneed additional annotations of specific semantic domain, e.g., skeleton posesfor human bodies or animals, which require extra annotation effort and sufferfrom error accumulation, and they are limited to specific domain. In thispaper, we propose a novel self-supervised approach to learn neural implicitshape representation for deformable objects, which can represent shapes with atemplate shape and dense correspondence in 3D. Our method does not require thepriors of skeleton and skinning weight, and only requires a collection ofshapes represented in signed distance fields. To handle the large deformation,we constrain the learned template shape in the same latent space with thetraining shapes, design a new formulation of local rigid constraint thatenforces rigid transformation in local region and addresses local reflectionissue, and present a new hierarchical rigid constraint to reduce the ambiguitydue to the joint learning of template shape and correspondences. Extensiveexperiments show that our model can represent shapes with large deformations.We also show that our shape representation can support two typicalapplications, such as texture transfer and shape editing, with competitiveperformance. The code and models are available athttps://iscas3dv.github.io/deformshape

Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects