Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

@article{Chen2017AdversarialPA,
  title={Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation},
  author={Y. Chen and Chunhua Shen and Xiu-Shen Wei and Lingqiao Liu and Jingqing Yang},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1221-1230}
}
For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. [] Key Method If the pose generator (G) generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors.,,To better capture the structure dependency of human body joints, the generator G is designed in a stacked multi-task manner to predict poses as well as occlusion heatmaps.

Figures and Tables from this paper

AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
TLDR
The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models.
3D Human Pose Estimation With Generative Adversarial Networks
TLDR
A new evaluation metric distance-based Pose Structure Score (dPSS) for evaluating the structural similarity degree between the predicted 3D pose and its ground-truth and it outperforms state-of-the-art methods.
Improving Human Pose Estimation With Self-Attention Generative Adversarial Networks
TLDR
This paper proposes to apply Self-Attention GAN to further improve the performance of human pose estimation with attention mechanism in the framework of GAN, which outperforms other state-of-the-art methods on two standard benchmark datasets MPII and LSP.
3D Human Pose Estimation in the Wild by Adversarial Learning
TLDR
An adversarial learning framework is proposed, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations and designs a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator.
Learning to Refine Human Pose Estimation
TLDR
A pose refinement network (PoseRefiner) is introduced which takes as input both the image and a given pose estimate and learns to directly predict a refined pose by jointly reasoning about the input-output space.
Learning Joint Structure for Human Pose Estimation
TLDR
This work designs a Structural Pose Network to take full advantage of joint structure for human pose estimation under unconstrained environment and proposes a novel structure-consistency constraint, which can maintain the structural consistency between the joints and body parts via estimating whether the joints are located in their corresponding parts.
Improving Human Pose Estimation with Self-Attention Generative Adversarial Networks
TLDR
Self-Attention GAN is proposed to apply to further improve the performance of human pose estimation with attention mechanism in the discriminator, to enforce the entire body joints structural constrains to make all the body joints to be consistent.
3D Hand Pose Estimation in the Wild via Graph Refinement under Adversarial Learning
TLDR
This paper proposes a hand-model regularized graph refinement paradigm under an adversarial learning framework, aiming to explicitly capture structural inter-dependencies of hand joints for the learning of intrinsic patterns in 3D pose estimation.
Adversarial Semantic Data Augmentation for Human Pose Estimation
TLDR
Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity, is proposed, which exploits a generative network to dynamiclly predict tailored pasting configuration.
...
...

References

SHOWING 1-10 OF 46 REFERENCES
End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
TLDR
This paper proposes a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts, and explicitly incorporate domain prior knowledge into the framework, which greatly regularizes the learning process and enables the flexibility of the framework for loopy models or tree-structured models.
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.
DeepPose: Human Pose Estimation via Deep Neural Networks
TLDR
The pose estimation is formulated as a DNN-based regression problem towards body joints and a cascade of such DNN regres- sors which results in high precision pose estimates.
MODEC: Multimodal Decomposable Models for Human Pose Estimation
TLDR
This paper proposes a multimodal, decomposable model of human pose that explicitly captures a variety of pose modes and outperforms state-of-the-art approaches across the accuracy-speed trade-off curve for several pose datasets.
Human Pose Estimation via Convolutional Part Heatmap Regression
TLDR
A CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions is proposed, and achieves top performance on the MPII and LSP data sets.
An Efficient Convolutional Network for Human Pose Estimation
TLDR
An efficient deep network architecture is proposed that is trained efficiently with a transparent procedure and exploits the best available ingredients from deep learning with low computational budget and achieves impressive performance on popular benchmarks in human pose estimation.
Structured Feature Learning for Pose Estimation
TLDR
A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints, and the proposed framework improves feature learning substantially.
Cascaded Models for Articulated Pose Estimation
TLDR
This work proposes to learn a sequence of structured models at different pose resolutions, where coarse models filter the pose space for the next level via their max-marginals, and trains the cascade to prune as much as possible while preserving true poses for the final level pictorial structure model.
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
TLDR
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models.
...
...