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

In the domain of 3D Human Pose Estimation, which finds widespread dailyapplications, the requirement for convenient acquisition equipment continues togrow. To satisfy this demand, we set our sights on a short-baseline binocularsetting that offers both portability and a geometric measurement property thatradically mitigates depth ambiguity. However, as the binocular baselineshortens, two serious challenges emerge: first, the robustness of 3Dreconstruction against 2D errors deteriorates; and second, occlusion reoccursdue to the limited visual differences between two views. To address the firstchallenge, we propose the Stereo Co-Keypoints Estimation module to improve theview consistency of 2D keypoints and enhance the 3D robustness. In this module,the disparity is utilized to represent the correspondence of binocular 2Dpoints and the Stereo Volume Feature is introduced to contain binocularfeatures across different disparities. Through the regression of SVF, two-view2D keypoints are simultaneously estimated in a collaborative way whichrestricts their view consistency. Furthermore, to deal with occlusions, aPre-trained Pose Transformer module is introduced. Through this module, 3Dposes are refined by perceiving pose coherence, a representation of jointcorrelations. This perception is injected by the Pose Transformer network andlearned through a pre-training task that recovers iterative masked joints.Comprehensive experiments carried out on H36M and MHAD datasets, complementedby visualizations, validate the effectiveness of our approach in theshort-baseline binocular 3D Human Pose Estimation and occlusion handling.

RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling