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/

Zendy Plus

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

Zendy Tools

Zendy Open

Current unsupervised 2D-3D human pose estimation (HPE) methods do not work inmulti-person scenarios due to perspective ambiguity in monocular images.Therefore, we present one of the first studies investigating the feasibility ofunsupervised multi-person 2D-3D HPE from just 2D poses alone, focusing onreconstructing human interactions. To address the issue of perspectiveambiguity, we expand upon prior work by predicting the cameras' elevation anglerelative to the subjects' pelvis. This allows us to rotate the predicted posesto be level with the ground plane, while obtaining an estimate for the verticaloffset in 3D between individuals. Our method involves independently liftingeach subject's 2D pose to 3D, before combining them in a shared 3D coordinatesystem. The poses are then rotated and offset by the predicted elevation anglebefore being scaled. This by itself enables us to retrieve an accurate 3Dreconstruction of their poses. We present our results on the CHI3D dataset,introducing its use for unsupervised 2D-3D pose estimation with three newquantitative metrics, and establishing a benchmark for future research.

Unsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone