4 papers with code • 1 benchmarks • 1 datasets
This task aims to solve root-relative 3D multi-person pose estimation (person-centric coordinate system). No ground truth human bounding box and human root joint coordinates are used during testing stage.
( Image credit: RootNet )
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
Ranked #2 on Root Joint Localization on Human3.6M
To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters.
In multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person.
Ranked #1 on 3D Multi-Person Pose Estimation on MuPoTS-3D
Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose.