LG-Hand: Advancing 3D Hand Pose Estimation with Locally and Globally Kinematic Knowledge
This work addresses the problem of estimating 3D hand poses from 2D joints for applications like human-computer interaction, but it is incremental as it builds on existing graph-based methods with new loss functions.
The paper tackles 3D hand pose estimation from RGB images by proposing LG-Hand, a method that uses spatial-temporal Graph Convolutional Neural Networks and introduces Angle and Direction loss functions to incorporate kinematic knowledge, achieving promising results on the FPHAB dataset.
3D hand pose estimation from RGB images suffers from the difficulty of obtaining the depth information. Therefore, a great deal of attention has been spent on estimating 3D hand pose from 2D hand joints. In this paper, we leverage the advantage of spatial-temporal Graph Convolutional Neural Networks and propose LG-Hand, a powerful method for 3D hand pose estimation. Our method incorporates both spatial and temporal dependencies into a single process. We argue that kinematic information plays an important role, contributing to the performance of 3D hand pose estimation. We thereby introduce two new objective functions, Angle and Direction loss, to take the hand structure into account. While Angle loss covers locally kinematic information, Direction loss handles globally kinematic one. Our LG-Hand achieves promising results on the First-Person Hand Action Benchmark (FPHAB) dataset. We also perform an ablation study to show the efficacy of the two proposed objective functions.