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 …

In this study, we introduce a methodology for human image animation by leveraging a 3D
human parametric model within a latent diffusion framework to enhance shape alignment …

Recent advances in neural rendering have improved both training and rendering times by
orders of magnitude. While these methods demonstrate state-of-the-art quality and speed …

Abstract We introduce Gaussian Articulated Template Model (GART) an explicit efficient and
expressive representation for non-rigid articulated subject capturing and rendering from …

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 …

We introduce ChatPose a framework employing Large Language Models (LLMs) to
understand and reason about 3D human poses from images or textual descriptions. Our …

In this work we study the benefits of using tracking and 3D poses for action recognition. To
achieve this, we take the Lagrangian view on analysing actions over a trajectory of human …

We present Paint-it a text-driven high-fidelity texture map synthesis method for 3D meshes
via neural re-parameterized texture optimization. Paint-it synthesizes texture maps from a …

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 …

The estimation of 3D human motion from video has progressed rapidly but current methods
still have several key limitations. First most methods estimate the human in camera …