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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We propose to leverage recent advances in reliable 2D pose estimation withConvolutional Neural Networks (CNN) to estimate the 3D pose of people fromdepth images in multi-person Human-Robot Interaction (HRI) scenarios. Ourmethod is based on the observation that using the depth information to obtain3D lifted points from 2D body landmark detections provides a rough estimate ofthe true 3D human pose, thus requiring only a refinement step. In that line ourcontributions are threefold. (i) we propose to perform 3D pose estimation fromdepth images by decoupling 2D pose estimation and 3D pose refinement; (ii) wepropose a deep-learning approach that regresses the residual pose between thelifted 3D pose and the true 3D pose; (iii) we show that despite its simplicity,our approach achieves very competitive results both in accuracy and speed ontwo public datasets and is therefore appealing for multi-person HRI compared torecent state-of-the-art methods.

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation