PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

  title={PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation},
  author={Abdallah Benzine and Florian Chabot and Bertrand Luvison and Quoc-Cuong Pham and C. Achard},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications such as autonomous driving or crowd analysis require pose estimation of a large number of people possibly at low-resolution. In this work, we present PandaNet (Pose estimAtioN and Dectection Anchor-based Network), a new single-shot, anchor-based… Expand
5 Citations

Figures and Tables from this paper

PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
  • PDF
CenterHMR: Multi-Person Center-based Human Mesh Recovery.
Deep Learning-Based Human Pose Estimation: A Survey
  • 27
  • PDF
Reconstructing 3D Human Pose by Watching Humans in the Mirror
  • PDF
CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image
  • 1


Deep, robust and single shot 3D multi-person human pose estimation in complex images
  • 2
  • PDF
Deep, Robust and Single Shot 3D Multi-Person Human Pose Estimation from Monocular Images
  • 7
  • PDF
LCR-Net: Localization-Classification-Regression for Human Pose
  • 177
  • PDF
Towards Accurate Multi-person Pose Estimation in the Wild
  • 379
  • PDF
Single-Shot Multi-Person 3D Body Pose Estimation From Monocular RGB Input
  • 11
  • Highly Influential
  • PDF
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images
  • 122
  • PDF
Cascaded Pyramid Network for Multi-person Pose Estimation
  • 431
  • PDF
XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera
  • 32
  • Highly Influential
  • PDF
MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
  • 101
  • PDF
PifPaf: Composite Fields for Human Pose Estimation
  • 81
  • PDF