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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Emerging Metaverse applications demand reliable, accurate, and photorealisticreproductions of human hands to perform sophisticated operations as if in thephysical world. While real human hand represents one of the most intricatecoordination between bones, muscle, tendon, and skin, state-of-the-arttechniques unanimously focus on modeling only the skeleton of the hand. In thispaper, we present NIMBLE, a novel parametric hand model that includes themissing key components, bringing 3D hand model to a new level of realism. Wefirst annotate muscles, bones and skins on the recent Magnetic ResonanceImaging hand (MRI-Hand) dataset and then register a volumetric template handonto individual poses and subjects within the dataset. NIMBLE consists of 20bones as triangular meshes, 7 muscle groups as tetrahedral meshes, and a skinmesh. Via iterative shape registration and parameter learning, it furtherproduces shape blend shapes, pose blend shapes, and a joint regressor. Wedemonstrate applying NIMBLE to modeling, rendering, and visual inference tasks.By enforcing the inner bones and muscles to match anatomic and kinematic rules,NIMBLE can animate 3D hands to new poses at unprecedented realism. To model theappearance of skin, we further construct a photometric HandStage to acquirehigh-quality textures and normal maps to model wrinkles and palm print.Finally, NIMBLE also benefits learning-based hand pose and shape estimation byeither synthesizing rich data or acting directly as a differentiable layer inthe inference network.

NIMBLE: A Non-rigid Hand Model with Bones and Muscles