3D Multi-Person Pose Estimation (absolute)
9 papers with code • 1 benchmarks • 2 datasets
This task aims to solve absolute 3D multi-person pose Estimation (camera-centric coordinates). No ground truth human bounding box and human root joint coordinates are used during testing stage.
( Image credit: RootNet )
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.
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.
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
First, problem complexity is reduced to the use of a single parameter (choice of k nearest neighbors), and second, an improved ability for handling large variations in cluster density (heterogeneous density).
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.
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.
Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i. e., the coordinates based on the center of the target person.