Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression

By Zigang Geng, Ke Sun, Bin Xiao, Zhaoxiang Zhang, Jingdong Wang. Computer Vision and Pattern Recognition, 2021

356 citations recorded by the source corpus.

In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions.We present a simple yet effective approach, named disentangled keypoint regression (DEKR). We adopt adaptive convolutions through pixel-wise spatial transformer to activate the pixels in the keypoint regions and accordingly learn representations from them. We use a multi-branch structure for separate regression: each branch learns a representation with dedicated adaptive convolutions and regresses one keypoint. The resulting disentangled representations are able to attend to the keypoint regions, respectively, and thus the keypoint regression is spatially more accurate. We empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods and achieves superior bottom-up pose estimation results on two benchmark datasets, COCO and CrowdPose. The code and models are available at https://github.com/HRNet/DEKR.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d38e1225476f5a035e6661c360365c30506e5804

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tao Jiang
2. Chengqi Lyu
3. Yining Li

In Computer Vision and Pattern Recognition

1. Manu Mathew
2. Tao Jiang
3. Ning Ma
4. Kai Chen
5. Rui Han
6. Li Zhang
7. Chengqi Lyu
8. Peng Lu

Citations in the corpus

• RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose (2023, background): “Bottom-up algorithms [7, 10, 19, 27, 29, 41, 44, 45] detect instance-agnostic keypoints in an image and partition these keypoints to obtain the human pose.”
• YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss (2022, methodology): “[30] uses a scale normalized L1 loss for keypoint regression which is a step towards OKS loss.”