• Corpus ID: 202660969

Adaptive Graphical Model Network for 2D Handpose Estimation

@inproceedings{Kong2019AdaptiveGM,
  title={Adaptive Graphical Model Network for 2D Handpose Estimation},
  author={Deying Kong and Yifei Chen and Haoyu Ma and Xiangyi Yan and Xiaohui Xie},
  booktitle={BMVC},
  year={2019}
}
In this paper, we propose a new architecture called Adaptive Graphical Model Network (AGMN) to tackle the task of 2D hand pose estimation from a monocular RGB image. The AGMN consists of two branches of deep convolutional neural networks for calculating unary and pairwise potential functions, followed by a graphical model inference module for integrating unary and pairwise potentials. Unlike existing architectures proposed to combine DCNNs with graphical models, our AGMN is novel in that the… 

Figures and Tables from this paper

Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation
TLDR
Experimental results show the R-MGMN model outperforms the state-of-the-art algorithm which is widely used in 2D hand pose estimation by a noticeable margin.
Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation
TLDR
This work proposes a new deep learning-based framework that consists of two main modules that presents a segmentationbased approach to detect the hand skeleton and localize the hand bounding box and regresses the 2D joint locations through a multi-scale heatmap regression approach.
Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation
TLDR
A novel Nonparametric Structure Regularization Machine (NSRM) is proposed for 2D hand pose estimation, adopting a cascade multi-task architecture to learn hand structure and keypoint representations jointly.
Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos
TLDR
A new framework of training 3D pose estimation models from RGB images without using explicit 3D annotations, i.e., trained with only 2D information is proposed, which achieves surprisingly good results, with 3D estimation accuracy on par with the state-of-the-art models trained with3D annotations.
FastHand: Fast Hand Pose Estimation From A Monocular Camera
TLDR
A fast and accurate framework for hand pose estimation, dubbed as “FastHand”, using a lightweight encoder-decoder network architecture to fulfil the requirements of practical applications running on embedded devices.
MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation
TLDR
A spin match algorithm is designed that enables a rigid mesh model matching with any target mesh ground truth and an efficient pipeline is proposed to generate a large-scale multi-view hand mesh (MVHM) dataset with accurate 3D hand mesh and joint labels.
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
TLDR
A transformer framework for multi-view 3D pose estimation, aiming at directly improving individual 2D predictors by integrating information from different views is introduced, and the concept of epipolar field to encode 3D positional information into the transformer model is proposed.
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking
TLDR
This work proposes a probabilistic graphical model built on top of deep neural networks, Deep Graph Pose (DGP), to leverage the rich spatiotemporal structures pervasive in behavioral video, and develops an efficient structured variational approach to perform inference in this model.
SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation
TLDR
The proposed SIA-GCN can efficiently extract spatial information from 2D maps at each node and propagate them through graph convolution and can achieve state-of-the-art performance on the task of hand pose estimation.
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
TLDR
This work specifies a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations).
Learning to Estimate 3D Hand Pose from Single RGB Images
TLDR
A deep network is proposed that learns a network-implicit 3D articulation prior that yields good estimates of the 3D pose from regular RGB images, and a large scale 3D hand pose dataset based on synthetic hand models is introduced.
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
This paper proposes a new hybrid architecture that consists of a deep Convolu-tional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging
Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos
TLDR
The proposed end-to-end architecture is evaluated on two widely used benchmarks for video-based pose estimation (Penn Action and JHMDB datasets) and outperforms several state-of-the-art methods.
Large-scale Multiview 3D Hand Pose Dataset
Stacked Hourglass Networks for Human Pose Estimation
TLDR
This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.
Dense 3D Regression for Hand Pose Estimation
TLDR
A simple and effective method for 3D hand pose estimation from a single depth frame based on dense pixel-wise estimation that outperforms all previous state-of-the-art approaches by a large margin and outperforms various other proposed methods.
Using a Single RGB Frame for Real Time 3D Hand Pose Estimation in the Wild
TLDR
This work capitalize on the latest advancements of deep learning, combining them with the power of generative hand pose estimation techniques to achieve real-time monocular 3D hand Pose estimation in unrestricted scenarios.
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
TLDR
An approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other is proposed.
Convolutional Pose Machines
TLDR
This work designs a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference in structured prediction tasks such as articulated pose estimation.
...
1
2
3
...