Abstract 3D human pose estimation from monocular images is a highly ill-posed problem
due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these …

The rise of deep learning technology has broadly promoted the practical application of
artificial intelligence in production and daily life. In computer vision, many human-centered …

This paper addresses the problem of cross-dataset generalization of 3D human pose
estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a …

When applying a pre-trained 2D-to-3D Human Pose lifting model to a target unseen dataset,
a large performance degradation is commonly encountered due to domain shift issues. We …

This paper addresses the problem of 3D human pose estimation from single images. While
for a long time human skeletons were parameterized and fitted to the observation by …

The existing pose estimation approaches often require a large number of annotated images
to attain good estimation performance, which are laborious to acquire. To reduce the human …

The limited number of actors and actions in existing datasets make 3D pose estimators tend
to overfit, which can be seen from the performance degradation of the algorithm on cross …

3D human pose estimation describes estimating 3D articulation structure of a person from
an image or a video. The technology has massive potential because it can enable tracking …

Graph convolution networks (GCNs) based methods for 3D human pose estimation usually
aggregate immediate features of single-hop nodes, which are unaware of the correlation of …

Abstract We propose Structural Triangulation, a closed-form solution for optimal 3D human
pose considering multi-view 2D pose estimations, calibrated camera parameters, and bone …