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

Real-time 3D human pose estimation is crucial for human-computer interaction.It is cheap and practical to estimate 3D human pose only from monocular video.However, recent bone splicing based 3D human pose estimation method bringsabout the problem of cumulative error. In this paper, the concept of virtualbones is proposed to solve such a challenge. The virtual bones are imaginarybones between non-adjacent joints. They do not exist in reality, but they bringnew loop constraints for the estimation of 3D human joints. The proposednetwork in this paper predicts real bones and virtual bones, simultaneously.The final length of real bones is constrained and learned by the loopconstructed by the predicted real bones and virtual bones. Besides, the motionconstraints of joints in consecutive frames are considered. The consistencybetween the 2D projected position displacement predicted by the network and thecaptured real 2D displacement by the camera is proposed as a new projectionconsistency loss for the learning of 3D human pose. The experiments on theHuman3.6M dataset demonstrate the good performance of the proposed method.Ablation studies demonstrate the effectiveness of the proposed inter-frameprojection consistency constraints and intra-frame loop constraints.

Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos