Existing 3D human pose estimators suffer poor generalization performance to new datasets,
largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this …

Various deep learning techniques have been proposed to solve the single-view 2D-to-3D
pose estimation problem. While the average prediction accuracy has been improved …

In this paper, we propose a novel graph convolutional network architecture, Graph Stacked
Hourglass Networks, for 2D-to-3D human pose estimation tasks. The proposed architecture …

Human pose estimation from single images is a challenging problem in computer vision that
requires large amounts of labeled training data to be solved accurately. Unfortunately, for …

While deep learning reshaped the classical motion capture pipeline with feed-forward
networks, generative models are required to recover fine alignment via iterative refinement …

Estimating 3D human pose from a single image suffers from severe ambiguity since multiple
3D joint configurations may have the same 2D projection. The state-of-the-art methods often …

Vision-based 3D human pose estimation approaches are typically evaluated on datasets
that are limited in diversity regarding many factors, eg, subjects, poses, cameras, and …

We present a self-supervised learning algorithm for 3D human pose estimation of a single
person based on a multiple-view camera system and 2D body pose estimates for each view …

In the task of monocular 3D pose estimation, the estimation errors of limb joints (ie, wrist,
ankle, etc) with a higher degree of freedom (DOF) are larger than that of others (ie, hip …

Local processing is an essential feature of CNNs and other neural network architectures--it
is one of the reasons why they work so well on images where relevant information is, to a …