Single-Shot Multi-person 3D Pose Estimation from Monocular RGB

@article{Mehta2017SingleShotM3,
  title={Single-Shot Multi-person 3D Pose Estimation from Monocular RGB},
  author={Dushyant Mehta and Oleksandr Sotnychenko and Franziska Mueller and Weipeng Xu and Srinath Sridhar and Gerard Pons-Moll and Christian Theobalt},
  journal={2018 International Conference on 3D Vision (3DV)},
  year={2017},
  pages={120-130}
}
We propose a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene. ORPM outputs a fixed number of maps which encode the 3D joint locations of all people in the scene. Body part associations [8] allow us to infer 3D pose for an arbitrary number of people without explicit… CONTINUE READING
4
Twitter Mentions

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

XNect : Real-time Multi-person 3 D Human Pose Estimation with a Single RGB

Camera, DUSHYANTMEHTA, +5 authors Christian Theobalt
  • 2019
VIEW 25 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera

VIEW 25 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

  • ArXiv
  • 2019
VIEW 9 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images

  • IEEE transactions on pattern analysis and machine intelligence
  • 2018
VIEW 6 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

DHP19: Dynamic Vision Sensor 3D Human Pose Dataset

Enrico Calabrese, Gemma Taverni, +5 authors Tobi Delbruck
  • CVPR 2019
  • 2019
VIEW 1 EXCERPT
CITES METHODS

Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

Weilin Wan, Aaron Walsman, Dieter Fox
  • 2019 International Conference on Robotics and Automation (ICRA)
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 68 REFERENCES

Video Based Reconstruction of 3D People Models

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

LCR-Net: Localization-Classification-Regression for Human Pose

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

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

  • 2017 International Conference on 3D Vision (3DV)
  • 2016
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Pose-conditioned joint angle limits for 3D human pose reconstruction

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Panoptic Studio: A Massively Multiview System for Social Motion Capture

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL