The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

Inferring human pose from a monocular RGB image remains an interesting field of research
in computer vision. It serves as a fundamental key for many real-world applications …

Top-down methods dominate the field of 3D human pose and shape estimation, because
they are decoupled from human detection and allow researchers to focus on the core …

Estimating 3D human poses from monocular videos is a challenging task due to depth
ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting …

Recent transformer-based solutions have been introduced to estimate 3D human pose from
2D keypoint sequence by considering body joints among all frames globally to learn spatio …

Human pose is typically represented by a coordinate vector of body joints or their heatmap
embeddings. While easy for data processing, unrealistic pose estimates are admitted due to …

Despite the great progress in 3D human pose estimation from videos, it is still an open
problem to take full advantage of a redundant 2D pose sequence to learn representative …

Abstract 3D human pose data collected in controlled laboratory settings present challenges
for pose estimators that generalize across diverse scenarios. To address this domain …

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 …

As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh
reconstruction (3DHMR) methods either use a constant large focal length or estimate one …