Corpus ID: 9511016

Model-Based Deep Hand Pose Estimation

@article{Zhou2016ModelBasedDH,
  title={Model-Based Deep Hand Pose Estimation},
  author={Xingyi Zhou and Qingfu Wan and W. Zhang and X. Xue and Yichen Wei},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.06854}
}
Previous learning based hand pose estimation methods does not fully exploit the prior information in hand model geometry. Instead, they usually rely a separate model fitting step to generate valid hand poses. Such a post processing is inconvenient and sub-optimal. In this work, we propose a model based deep learning approach that adopts a forward kinematics based layer to ensure the geometric validity of estimated poses. For the first time, we show that embedding such a non-linear generative… Expand
Hand pose estimation on hybrid CNN-AE model
TLDR
A Convolutional Neural Network is introduced as Deep learning regression framework while employing an embedding denoising auto-encoder in the bottom layer of the network to learn latent representation of hand pose and account for joint dependencies. Expand
Deep Conditional Variational Estimation for Depth-Based Hand Poses
TLDR
The proposed network combines the framework of conditional variational autoencoder which learns an encoder and a decoder with standard convolutional network and introduces a pool-convolution module to improve the localization regression of the network. Expand
Model-based Hand Pose Estimation for Generalized Hand Shape with Spatial Transformer Network
TLDR
This work extends the kinematic layer into the deep learning structure to make the hand shape parameters adaptable, and shows that by applying Spatial Transformer Network, the performance of a regression task can be improved. Expand
Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization
Since the emergence of large annotated datasets, state-of-the-art hand pose estimation methods have been mostly based on discriminative learning. Recently, a hybrid approach has embedded a kinematicExpand
Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization
TLDR
This work extends the kinematic layer into the deep learning structure to make the hand shape parameters learnable, and applies a cascade of appearance normalization networks to decrease the variance in the input data. Expand
Deep Kinematic Pose Regression
TLDR
This work proposes to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation and achieves state-of-the-art result on Human3.6M dataset. Expand
Deep Learning-based 3D Hand Pose and Shape Estimation from a Single Depth Image: Methods, Datasets and Application
TLDR
This work introduced a novel structure-aware algorithm which learns to estimate 3D hand pose jointly with new structural constraints and created a million-scale synthetic dataset with accurate joint annotations and mesh files of depth maps. Expand
DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
TLDR
A fully supervised deep network is proposed which learns to jointly estimate a full 3D hand mesh representation and pose from a single depth image to improve model based learning (hybrid) methods' results on two of the public benchmarks. Expand
Top-down model fitting for hand pose recovery in sequences of depth images
TLDR
A two-step pipeline for recovering the hand pose from a sequence of depth images, designed to deal with images taken from any viewpoint and exhibiting a high degree of finger occlusion is proposed. Expand
Context-Aware Deep Spatiotemporal Network for Hand Pose Estimation From Depth Images
TLDR
The proposed context-aware deep spatiotemporal network is able to learn the representations of the spatial information and the temporal structure from the image sequences and is capable of dynamically weighting different predictions to lay emphasis on sufficient context. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 48 REFERENCES
Training a Feedback Loop for Hand Pose Estimation
TLDR
An entirely data-driven approach to estimating the 3D pose of a hand given a depth image is proposed, which outperforms state-of-the-art methods, and is efficient as the implementation runs at over 400 fps on a single GPU. Expand
Hands Deep in Deep Learning for Hand Pose Estimation
TLDR
It is shown that a prior on the 3D pose can be easily introduced and significantly improves the accuracy and reliability of the predictions, and how to use context efficiently to deal with ambiguities between fingers is shown. Expand
Cascaded hand pose regression
TLDR
3D pose-indexed features that generalize the previous 2D parameterized features and achieve better invariance to 3D transformations and a principled hierarchical regression that is adapted to the articulated object structure are introduced. Expand
Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties
TLDR
Quantitative results demonstrate that the proposed hybrid approach for hand pose estimation from a single depth image outperforms state-of-the-art representatives of the model-based, data-driven and hybrid paradigms. Expand
Efficient Hand Pose Estimation from a Single Depth Image
  • Chi Xu, Li Cheng
  • Computer Science
  • 2013 IEEE International Conference on Computer Vision
  • 2013
TLDR
This work tackles the practical problem of hand pose estimation from a single noisy depth image, and proposes a dedicated three-step pipeline that is able to work with Kinect-type noisy depth images, and reliably produces pose estimations of general motions efficiently. Expand
Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture
TLDR
The Latent Regression Forest is presented, a novel framework for real-time, 3D hand pose estimation from a single depth image and shows that the LRF out-performs state-of-the-art methods in both accuracy and efficiency. Expand
Hand Pose Estimation and Hand Shape Classification Using Multi-layered Randomized Decision Forests
TLDR
Two novel types of multi---layered RDFs are introduced: Global Expert Network (GEN) and Local Expert network (LEN), which achieve significantly better hand pose estimates than a single---layering skeleton estimator and generalize better to previously unseen hand poses. Expand
Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks
TLDR
A novel method for real-time continuous pose recovery of markerless complex articulable objects from a single depth image using a randomized decision forest classifier for image segmentation, a robust method for labeled dataset generation, a convolutional network for dense feature extraction, and finally an inverse kinematics stage for stable real- time pose recovery. Expand
Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests
TLDR
The Semi-supervised Transductive Regression (STR) forest is proposed which learns the relationship between a small, sparsely labelled realistic dataset and a large synthetic dataset, and a novel data-driven, pseudo-kinematic technique to refine noisy or occluded joints. Expand
Depth-Based Hand Pose Estimation: Methods, Data, and Challenges
TLDR
An extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame, defines a consistent evaluation criteria, rigorously motivated by human experiments and introduces a simple nearest-neighbor baseline that outperforms most existing systems. Expand
...
1
2
3
4
5
...