VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera

ACM Transactions on Graphics (SIGGRAPH 2017), Los Angeles, USA

Update: You can see a live demo of VNect at CVPR! (More details)

Download Video: HD (MP4, 1080p, 152 MB)

Abstract

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

Downloads


Citation

BibTeX, 1 KB

@inproceedings{VNect_SIGGRAPH2017,
  author = {Mehta, Dushyant and Sridhar, Srinath and Sotnychenko, Oleksandr and Rhodin, Helge and Shafiei, Mohammad and Seidel, Hans-Peter and Xu, Weipeng and Casas, Dan and Theobalt, Christian},
  title = {VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera},
  journal = {ACM Transactions on Graphics},
  url = {http://gvv.mpi-inf.mpg.de/projects/VNect/},
  numpages = {14},
  volume={36},
  number={4},
  month = July,
  year = {2017}
  doi={10.1145/3072959.3073596}
}
      

Acknowledgments

This work is was funded by the ERC Starting Grant project CapReal (335545). Dan Casas was supported by a Marie Curie Individual Fellow, grant agreement 707326.

Contact

Dushyant Mehta
dmetha@mpi-inf.mpg.de

This page is Zotero translator friendly. Page last updated 23-Jul-2017. Imprint/Impressum.