3D Human Pose Estimation in the Wild by Adversarial Learning

@article{Yang20183DHP,
  title={3D Human Pose Estimation in the Wild by Adversarial Learning},
  author={Wei Yang and Wanli Ouyang and X. Wang and Jimmy S. J. Ren and Hongsheng Li and Xiaogang Wang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={5255-5264}
}
Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose… 

Figures and Tables from this paper

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.

3D Human Pose Estimation With Adversarial Learning

TLDR
This paper proposes a method of adversarial learning to estimate the 3D pose of the human body through a framework consisting of two parts, a pose generator and a discriminator that can effectively increase the accuracy and visual effect of3D pose estimation results.

Generalizing Monocular 3D Human Pose Estimation in the Wild

TLDR
This paper proposes a principled approach to generate high quality 3D pose ground truth given any in-the-wild image with a person inside, and builds a large-scale dataset, which enables the training of a high quality neural network model, without specialized training scheme and auxiliary loss function, which performs favorably against the state-of theart3D pose estimation methods.

Lifting 2d Human Pose to 3d : A Weakly Supervised Approach

TLDR
This paper proposes a method which can effectively predict 3d human pose from 2d pose using a deep neural network trained in a weakly-supervised manner on a combination of ground-truth 3d pose andGround-truth 2d posing, and demonstrates the superior generalization ability of this method by cross-dataset validation.

Towards Generalization of 3D Human Pose Estimation In The Wild

TLDR
3DBodyTex.Pose showed promising improvement in the overall performance, and a sensible decrease in the per joint position error when testing on challenging viewpoints, and is expected to offer the research community with new possibilities for generalizing 3D pose estimation from monocular in-the-wild images.

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.

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization

TLDR
This work proposes a novel structure-aware fully convolutional network to implicitly take such priors about the structure of pose components into account during training of the deep network, demonstrating the usefulness of implicit learning of structures using GANs.

Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision

TLDR
A novel deep-learning based framework is proposed to infer 3D human poses from a single image and achieves MPJPE of 58.68mm on the ECCV2018 3D Human Pose Estimation Challenge.

In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations

TLDR
This work proposes a new deep learning based method for monocular 3D human pose estimation that shows high accuracy and generalizes better to in-the-wild scenes.
...

References

SHOWING 1-10 OF 61 REFERENCES

Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision

We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly

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

TLDR
This work proposes a novel structure-aware convolutional network to implicitly take priors about the structure of human bodies into account during training of the deep network and significantly outperforms the state-of-the-art methods and almost always generates plausible human pose predictions.

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization

TLDR
This work proposes a novel structure-aware fully convolutional network to implicitly take such priors about the structure of pose components into account during training of the deep network, demonstrating the usefulness of implicit learning of structures using GANs.

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

TLDR
A weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels.

A Simple Yet Effective Baseline for 3d Human Pose Estimation

TLDR
The results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video

TLDR
This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence with a novel approach that integrates a sparsity-driven 3D geometric prior and temporal smoothness and outperforms a publicly available 2D pose estimation baseline on the challenging PennAction dataset.

Learning Feature Pyramids for Human Pose Estimation

TLDR
This work designs a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs and provides theoretic derivation to extend the current weight initialization scheme to multi-branch network structures.

3D Human Pose Estimation from a Single Image via Distance Matrix Regression

  • F. Moreno-Noguer
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
It is shown that more precise pose estimates can be obtained by representing both the 2D and 3D human poses using NxN distance matrices, and formulating the problem as a 2D-to-3D distance matrix regression.

3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network

TLDR
A deep convolutional neural network for 3D human pose estimation from monocular images is proposed and empirically show that the network has disentangled the dependencies among different body parts, and learned their correlations.

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

TLDR
An integrated approach is taken that fuses probabilistic knowledge of 3D human pose with a multi-stage CNN architecture and uses the knowledge of plausible 3D landmark locations to refine the search for better 2D locations.
...