Estimating human pose and shape from monocular images is a long-standing problem in
computer vision. Since the release of statistical body models, 3D human mesh recovery has …

Graph Neural Networks (GNNs) have gained momentum in graph representation learning
and boosted the state of the art in a variety of areas, such as data mining (eg, social network …

We present PyMAF-X, a regression-based approach to recovering a parametric full-body
model from a single image. This task is very challenging since minor parametric deviation …

Humans intuitively understand that inanimate objects do not move by themselves, but that
state changes are typically caused by human manipulation (eg, the opening of a book). This …

We present an approach that can reconstruct hands in 3D from monocular input. Our
approach for Hand Mesh Recovery HaMeR follows a fully transformer-based architecture …

The two-hand interaction is one of the most challenging signals to analyze due to the self-
similarity, complicated articulations, and occlusions of hands. Although several datasets …

Recovering whole-body mesh by inferring the abstract pose and shape parameters from
visual content can obtain 3D bodies with realistic structures. However, the inferring process …

Signed distance functions (SDFs) is an attractive framework that has recently shown
promising results for 3D shape reconstruction from images. SDFs seamlessly generalize to …

Humans commonly work with multiple objects in daily life and can intuitively transfer
manipulation skills to novel objects by understanding object functional regularities. However …

Reconstructing interacting hands from monocular images is indispensable in AR/VR
applications. Most existing solutions rely on the accurate localization of each skeleton joint …