3D Multi-Person Pose Estimation (root-relative)
11 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 )
We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.
Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
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.
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view.
In multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person.
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.
Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions.
In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem.