Hands Deep in Deep Learning for Hand Pose Estimation

Abstract

We introduce and evaluate several architectures for Convolutional Neural Networks to predict the 3D joint locations of a hand given a depth map. We first show that a prior on the 3D pose can be easily introduced and significantly improves the accuracy and reliability of the predictions. We also show how to use context efficiently to deal with ambiguities between fingers. These two contributions allow us to significantly outperform the state-of-the-art on several challenging benchmarks, both in terms of accuracy and computation times.

added link to source https://github.com/moberweger/deep-prior

References in corpus (3)

• Deep Learning in Neural Networks: An Overview
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

Cited by in corpus (51)

• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation
• Modeling Human Motion with Quaternion-based Neural Networks
• Model-based Deep Hand Pose Estimation
• Hand3D: Hand Pose Estimation using 3D Neural Network
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Attention guided global enhancement and local refinement network for semantic segmentation
• Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
• BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis
• A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
• Boundary Guided Context Aggregation for Semantic Segmentation
• Articulated Hand Pose Estimation Review
• Depth-based hand pose estimation: methods, data, and challenges
• Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
• Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations
• Neural Sign Language Translation based on Human Keypoint Estimation
• Training a Feedback Loop for Hand Pose Estimation
• Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
• Disentangling Latent Hands for Image Synthesis and Pose Estimation
• Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning
• DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
• Cardiac fat segmentation using computed tomography and an image-to-image conditional generative adversarial neural network
• 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
• Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
• Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data
• Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization
• Sequential Graph Convolutional Network for Active Learning
• DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
• Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
• JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• Two-hand Global 3D Pose Estimation Using Monocular RGB
• Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer
• Deep Kinematic Pose Regression
• Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints
• Silhouette-Net: 3D Hand Pose Estimation from Silhouettes
• Multimodal Noisy Segmentation based fragmented burn scars identification in Amazon Rainforest
• Enhanced Touchable Projector-depth System with Deep Hand Pose Estimation
• Multi-Anchor Active Domain Adaptation for Semantic Segmentation
• HMTNet:3D Hand Pose Estimation from Single Depth Image Based on Hand Morphological Topology
• An End-to-end Framework for Unconstrained Monocular 3D Hand Pose Estimation
• Hand range of motion evaluation for Rheumatoid Arthritis patients
• Patch-based 3D Human Pose Refinement
• Dense 3D Regression for Hand Pose Estimation
• DISCO Nets: DISsimilarity COefficient Networks
• Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images
• Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation
• Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
• Human-Machine Interface for Remote Training of Robot Tasks
• Bi-stream Pose Guided Region Ensemble Network for Fingertip Localization from Stereo Images
• Active Learning for Bayesian 3D Hand Pose Estimation