Corpus ID: 236318539

Human Pose Regression with Residual Log-likelihood Estimation

  title={Human Pose Regression with Residual Log-likelihood Estimation},
  author={Jiefeng Li and Siyuan Bian and Ailing Zeng and Can Wang and Bo Pang and Wentao Liu and Cewu Lu},
  • Jiefeng Li, Siyuan Bian, +4 authors Cewu Lu
  • Published 2021
  • Computer Science
  • ArXiv
Heatmap-based methods dominate in the field of human pose estimation by modelling the output distribution through likelihood heatmaps. In contrast, regressionbased methods are more efficient but suffer from inferior performance. In this work, we explore maximum likelihood estimation (MLE) to develop an efficient and effective regression-based methods. From the perspective of MLE, adopting different regression losses is making different assumptions about the output density function. A density… Expand


Human Pose Regression by Combining Indirect Part Detection and Contextual Information
This paper uses the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully differentiable framework that is able to learn heat maps representations indirectly, without additional steps of artificial ground truth generation. Expand
Compositional Human Pose Regression
A structure-aware regression approach that adopts a reparameterized pose representation using bones instead of joints and exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. Expand
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach
The proposed split-and-recombine approach, called SRNet, can be easily adapted to both single-image and temporal models, and it leads to appreciable improvements in the prediction of rare and unseen poses. Expand
LCR-Net: Localization-Classification-Regression for Human Pose
This work proposes an end-to-end architecture for joint 2D and 3D human pose estimation in natural images that significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Expand
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene. Expand
Deep High-Resolution Representation Learning for Human Pose Estimation
This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. Expand
Integral Human Pose Regression
This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues and is differentiable, efficient, and compatible with any heat map based methods. Expand
Towards Accurate Multi-person Pose Estimation in the Wild
This work proposes a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task by using a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and by introducing a novel aggregation procedure to obtain highly localized keypoint predictions. Expand
Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network
  • Chen Li, Gim Hee Lee
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
The experiments show that the 3D poses estimated by the approach from an input of 2D joints are consistent in 2D reprojections, which supports the argument that multiple solutions exist for the 2D-to-3D inverse problem. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
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. Expand