[C31] HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton

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 the proposed model outperforms the existing methods on the two hand pose benchmarks with the lowest model parameter requirement.

Publication
International Conference on Computer Vision (ICCV) 2021
Cheng Wencan (정문찬)
Cheng Wencan (정문찬)
Post Doc. @ NUS (National University of Singapore)
Jaehyun Park (박재현)
Jaehyun Park (박재현)
NC Soft (엔씨소프트)