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 present a self-trainable method, Mask2Hand, which learns to solve thechallenging task of predicting 3D hand pose and shape from a 2D binary mask ofhand silhouette/shadow without additional manually-annotated data. Given theintrinsic camera parameters and the parametric hand model in the camera space,we adopt the differentiable rendering technique to project 3D estimations ontothe 2D binary silhouette space. By applying a tailored combination of lossesbetween the rendered silhouette and the input binary mask, we are able tointegrate the self-guidance mechanism into our end-to-end optimization processfor constraining global mesh registration and hand pose estimation. Theexperiments show that our method, which takes a single binary mask as theinput, can achieve comparable prediction accuracy on both unaligned and alignedsettings as state-of-the-art methods that require RGB or depth inputs. Our codeis available at https://github.com/lijenchang/Mask2Hand.

Mask2Hand: Learning to Predict the 3D Hand Pose and Shape from Shadow