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

Depth estimation is usually ill-posed and ambiguous for monocularcamera-based 3D multi-person pose estimation. Since LiDAR can capture accuratedepth information in long-range scenes, it can benefit both the globallocalization of individuals and the 3D pose estimation by providing richgeometry features. Motivated by this, we propose a monocular camera and singleLiDAR-based method for 3D multi-person pose estimation in large-scale scenes,which is easy to deploy and insensitive to light. Specifically, we design aneffective fusion strategy to take advantage of multi-modal input data,including images and point cloud, and make full use of temporal information toguide the network to learn natural and coherent human motions. Without relyingon any 3D pose annotations, our method exploits the inherent geometryconstraints of point cloud for self-supervision and utilizes 2D keypoints onimages for weak supervision. Extensive experiments on public datasets and ournewly collected dataset demonstrate the superiority and generalizationcapability of our proposed method.

Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR