Corpus ID: 208139223

DirectPose: Direct End-to-End Multi-Person Pose Estimation

@article{Tian2019DirectPoseDE,
  title={DirectPose: Direct End-to-End Multi-Person Pose Estimation},
  author={Zeyong Tian and Hao Chen and Chunhua Shen},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.07451}
}
  • Zeyong Tian, Hao Chen, Chunhua Shen
  • Published 2019
  • Computer Science
  • ArXiv
  • We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two corners of target bounding-boxes, the proposed framework directly predicts instance-aware keypoints for all the instances from a raw input image, eliminating the need for heuristic grouping in bottom-up methods or bounding-box detection and RoI operations in top-down ones. We also propose a novel Keypoint Alignment… CONTINUE READING
    3 Citations
    Multi-Person Pose Regression via Pose Filtering and Scoring
    FCOS: A simple and strong anchor-free object detector
    Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
    • 2
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Towards Accurate Multi-person Pose Estimation in the Wild
    • 332
    • PDF
    Cascaded Pyramid Network for Multi-person Pose Estimation
    • 352
    • PDF
    DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model
    • 565
    • PDF
    DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
    • 495
    • PDF
    RMPE: Regional Multi-person Pose Estimation
    • 383
    • PDF
    DenseBox: Unifying Landmark Localization with End to End Object Detection
    • 196
    • PDF
    Single-Stage Multi-Person Pose Machines
    • 13
    • PDF
    Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation
    • 166
    • PDF
    FCOS: Fully Convolutional One-Stage Object Detection
    • 343
    • Highly Influential
    • PDF