Abstract Human Pose Estimation (HPE) is widely used in various fields, including motion
analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world …

In this work, we propose a framework for single-view hand mesh reconstruction, which can
simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal …

We present TOCH, a method for refining incorrect 3D hand-object interaction sequences
using a correspondence based prior learnt directly from data. Existing hand trackers …

Abstract Domain adaptation (DA) aims at transferring knowledge from a labeled source
domain to an unlabeled target domain. Though many DA theories and algorithms have been …

3D digital models of the upper limb anatomy represent the starting point for the design
process of bespoke devices, such as orthoses and prostheses, which can be modeled on …

We present a method for reconstructing accurate and consistent 3D hands from a monocular
video. We observe that the detected 2D hand keypoints and the image texture provide …

Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a
labeled source domain to an unlabeled target domain under the distribution shift. Thanks to …

We present SemiHand, a semi-supervised framework for 3D hand pose estimation from
monocular images. We pre-train the model on labelled synthetic data and fine-tune it on …

While pose estimation is an important computer vision task, it requires expensive annotation
and suffers from domain shift. In this paper, we investigate the problem of domain adaptive …

Recent advances in hand pose estimation have shed light on utilizing synthetic data to train
neural networks, which however inevitably hinders generalization to real-world data due to …