The field of vision-based human hand three-dimensional (3D) shape and pose estimation
has attracted significant attention recently owing to its key role in various applications, such …

In keypoint estimation tasks such as human pose estimation, heatmap-based regression is
the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer …

Abstract 3D hand-mesh reconstruction from RGB images facilitates many applications,
including augmented reality (AR). However, this requires not only real-time speed and …

State-of-the-art technologies for hand (and finger) motion tracking do not always provide
accurate and robust tracking. For example, severe occlusions can affect tracking with vision …

Depth images and point clouds are the two most commonly used data representations for
depth-based 3D hand pose estimation. Benefiting from the structuring of image data and the …

Reconstructing interacting hands from a single RGB image is a very challenging task. On the
one hand, severe mutual occlusion and similar local appearance between two hands …

Abstract 3D hand pose estimation from single depth is a fundamental problem in computer
vision, and has wide applications. However, the existing methods still can not achieve …

In this work, we study the cross-view information fusion problem in the task of self-
supervised 3D hand pose estimation from the depth image. Previous methods usually adopt …

We study how well different types of approaches generalise in the task of 3D hand pose
estimation under single hand scenarios and hand-object interaction. We show that the …

We aim to improve the performance of regressing hand keypoints and segmenting pixel-
level hand masks under new imaging conditions (eg., outdoors) when we only have labeled …