HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton

TL;DR

HandFoldingNet introduces a novel folding-based 3D hand pose estimation model that efficiently regresses joint locations from point clouds, guided by multi-scale features, outperforming existing methods with fewer parameters.

Contribution

The paper presents a new folding-based decoder guided by multi-scale features for accurate and efficient 3D hand pose estimation from point clouds.

Findings

Outperforms existing methods on three benchmark datasets.

Requires fewer model parameters than comparable approaches.

Achieves higher accuracy in hand joint localization.

Abstract

With increasing applications of 3D hand pose estimation in various human-computer interaction applications, convolution neural networks (CNNs) based estimation models have been actively explored. However, the existing models require complex architectures or redundant computational resources to trade with the acceptable accuracy. To tackle this limitation, this paper proposes HandFoldingNet, an accurate and efficient hand pose estimator that regresses the hand joint locations from the normalized 3D hand point cloud input. The proposed model utilizes a folding-based decoder that folds a given 2D hand skeleton into the corresponding joint coordinates. For higher estimation accuracy, folding is guided by multi-scale features, which include both global and joint-wise local features. Experimental results show that the proposed model outperforms the existing methods on three hand pose benchmark datasets with the lowest model parameter requirement. Code is available at https://github.com/cwc1260/HandFold.