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

Although monocular 3D human pose estimation methods have made significantprogress, it is far from being solved due to the inherent depth ambiguity.Instead, exploiting multi-view information is a practical way to achieveabsolute 3D human pose estimation. In this paper, we propose a simple yeteffective pipeline for weakly-supervised cross-view 3D human pose estimation.By only using two camera views, our method can achieve state-of-the-artperformance in a weakly-supervised manner, requiring no 3D ground truth butonly 2D annotations. Specifically, our method contains two steps: triangulationand refinement. First, given the 2D keypoints that can be obtained through anyclassic 2D detection methods, triangulation is performed across two views tolift the 2D keypoints into coarse 3D poses. Then, a novel cross-view U-shapedgraph convolutional network (CV-UGCN), which can explore the spatialconfigurations and cross-view correlations, is designed to refine the coarse 3Dposes. In particular, the refinement progress is achieved throughweakly-supervised learning, in which geometric and structure-aware consistencychecks are performed. We evaluate our method on the standard benchmark dataset,Human3.6M. The Mean Per Joint Position Error on the benchmark dataset is 27.4mm, which outperforms existing state-of-the-art methods remarkably (27.4 mm vs30.2 mm).

Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network