Papers for

gesture control system engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Kinematics-aware model improves 3D hand pose estimation from depth images

KAD-Net: Kinematics-Aware Decoupled Learning for Robust 3D Hand Pose Estimation from a Single Depth Image

Abstract: Due to the complexity of hand kinematics and self-occlusion, existing 3D hand pose estimation methods based on single depth images struggle to comprehensively model the topological dependencies among hand joints. Furthermore, traditional hierarchical multitask architectures enforce a shared feature space for both 2D joint localization and depth estimation, which can induce mutual interference. To address these challenges, we propose a Kinematics-Aware Decoupled Learning Network (KAD-Net) for robust 3D hand pose estimation. Specifically, we first design a Finger Topology Constraint (FTC) module to enhance the representation of distal joints. This module utilizes three consecutive finger joints to construct a local kinematic representation to impose topological constraints, which supplements the kinematic features of the distal joints. The FTC module leverages the structural context from visible joints to assist in locating occluded distal joints, thereby improving robustness to occlusion. Additionally, we propose a task-decoupled hierarchical multitask framework. This framework separates 2D joint localization from depth estimation and incorporates a dedicated multitask learning strategy for depth regression, effectively isolating the UV and depth features to mitigate mutual interference and negative transfer. Extensive experiments demonstrate that KAD-Net outperforms existing methods on several benchmark datasets (ICVL, NYU, and MSRA), achieving state-of-the-art accuracy in 3D hand pose estimation. Potential applications of KAD-Net include human-computer interaction, virtual reality and gesture-based control systems.

Fri 11 SeptComputer Vision and Pattern RecognitionHuman-Computer Interaction
The gist
Estimating the exact positions of hand joints from a single depth image is hard because hands are complex and fingers often block each other. The authors developed a method called KAD-Net that better understands how finger joints move together and splits the task of finding 2D joint locations from estimating their depth to avoid confusion. Their method also uses information from visible joints to predict hidden ones, making it more accurate when fingers are overlapping. Tests show KAD-Net does better than older methods on popular hand pose datasets.
Open 2609.12559v1