English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

State-of-the-art single depth image-based 3D hand pose estimation methods arebased on dense predictions, including voxel-to-voxel predictions,point-to-point regression, and pixel-wise estimations. Despite the goodperformance, those methods have a few issues in nature, such as the poortrade-off between accuracy and efficiency, and plain feature representationlearning with local convolutions. In this paper, a novel pixel-wiseprediction-based method is proposed to address the above issues. The key ideasare two-fold: a) explicitly modeling the dependencies among joints and therelations between the pixels and the joints for better local featurerepresentation learning; b) unifying the dense pixel-wise offset predictionsand direct joint regression for end-to-end training. Specifically, we firstpropose a graph convolutional network (GCN) based joint graph reasoning moduleto model the complex dependencies among joints and augment the representationcapability of each pixel. Then we densely estimate all pixels' offsets tojoints in both image plane and depth space and calculate the joints' positionsby a weighted average over all pixels' predictions, totally discarding thecomplex postprocessing operations. The proposed model is implemented with anefficient 2D fully convolutional network (FCN) backbone and has only about 1.4Mparameters. Extensive experiments on multiple 3D hand pose estimationbenchmarks demonstrate that the proposed method achieves new state-of-the-artaccuracy while running very efficiently with around a speed of 110fps on asingle NVIDIA 1080Ti GPU.

JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image