arXiv:2605.18553v2 Announce Type: replace-cross Abstract: Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy lear...
Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions.
arXiv:2607. 11221v1 Announce Type: cross Abstract: Accurate monocular 4D hand reconstruction remains challenging.
arXiv:2610.29936v1 Announce Type: new Abstract: Recovering metric world-space hand motion from egocentric video supports understanding human interactions and transferring them to embodied agents. Thr...
arXiv:2609.13269v1 Announce Type: cross Abstract: Gesture recognition on video is normally posed as classification: label each frame, then act on the label. That is adequate for control, where a comm...
arXiv:2605. 05367v2 Announce Type: replace-cross Abstract: Existing 3D sign language avatar reconstruction methods are developed and evaluated exclusively on Western sign languages, and no 3D parametric annotations exist for any Arabic Sign Language dataset, a gap that blocks the development of avatar-based accessibility applications for the Arab Deaf community.
arXiv:2609.24424v1 Announce Type: new Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict...
KAD-Net introduces a Kinematics-Aware Decoupled Learning Network for 3D hand pose estimation from a single depth image. It employs a Finger Topology Constraint module that uses local kinematic representations of three consecutive finger joints to better model distal joint relationships and handle occlusion. The architecture also decouples 2D joint localization from depth estimation in a hierarchical multitask framework, reducing feature interference and improving accuracy on benchmark datasets such as ICVL, NYU, and MSRA.
arXiv:2610.09455v1 Announce Type: new Abstract: Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand track...
arXiv:2605. 01720v3 Announce Type: replace-cross Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings.
arXiv:2608. 20093v1 Announce Type: new Abstract: In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images.
arXiv:2609.14122v1 Announce Type: new Abstract: We study the challenge of sign language video mimicking: given a driving video and a single reference frame, synthesize a video where the target signer...