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

Most existing monocular 3D pose estimation approaches only focus on a singlebody part, neglecting the fact that the essential nuance of human motion isconveyed through a concert of subtle movements of face, hands, and body. Inthis paper, we present FrankMocap, a fast and accurate whole-body 3D poseestimation system that can produce 3D face, hands, and body simultaneously fromin-the-wild monocular images. The core idea of FrankMocap is its modulardesign: We first run 3D pose regression methods for face, hands, and bodyindependently, followed by composing the regression outputs via an integrationmodule. The separate regression modules allow us to take full advantage oftheir state-of-the-art performances without compromising the original accuracyand reliability in practice. We develop three different integration modulesthat trade off between latency and accuracy. All of them are capable ofproviding simple yet effective solutions to unify the separate outputs intoseamless whole-body pose estimation results. We quantitatively andqualitatively demonstrate that our modularized system outperforms both theoptimization-based and end-to-end methods of estimating whole-body pose.

FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration