Currently, 3D pose estimation methods are not compatible with a variety of low
computational power devices because of efficiency and accuracy. In this paper, we revisit a …

Abstract 3D human pose estimation has been researched for decades with promising fruits.
3D human pose lifting is one of the promising research directions toward the task where …

We present MoVNect, a lightweight deep neural network to capture 3D human pose using a
single RGB camera. To improve the overall performance of the model, we apply the teacher …

Pose estimation plays a critical role in human-centered vision applications. However, it is
difficult to deploy state-of-the-art HRNet-based pose estimation models on resource …

Estimating 3D humans from images often produces implausible bodies that lean, float, or
penetrate the floor. Such methods ignore the fact that bodies are typically supported by the …

Monocular 3D human pose estimation is challenging due to depth ambiguity. Convolution-
based and Graph-Convolution-based methods have been developed to extract 3D …

Even though most existing monocular 3D pose estimation approaches achieve very
competitive results, they ignore the heterogeneity among human body parts by estimating …

Regression-based methods for 3D human pose estimation directly predict the 3D pose
parameters from a 2D image using deep networks. While achieving state-of-the-art …

To improve the generalization of 3D human pose estimators, many existing deep learning
based models focus on adding different augmentations to training poses. However, data …

In this paper, we propose a fully convolutional network for 3D human pose estimation from
monocular images. We use limb orientations as a new way to represent 3D poses and bind …