A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Dense Human Pose Estimation In The Wild
Rıza Alp Güler, Natalia Neverova, Iasonas Kokkinos
densepose.org] [
arXiv] [
BibTeX]
Dense human pose estimation aims at mapping all human pixels of an RGB image to the 3D surface of the human body. DensePose-RCNN is implemented in the Detectron framework and is powered by Caffe2.
In this repository, we provide the code to train and evaluate DensePose-RCNN. We also provide notebooks to visualize the collected DensePose-COCO dataset and show the correspondences to the SMPL model.
Please find installation instructions for Caffe2 and DensePose in
INSTALL.md, a document based on the Detectron installation instructions.
After installation, please see
GETTING_STARTED.mdfor examples of inference and training and testing.
notebooks/DensePose-COCO-Visualize.ipynbto visualize the DensePose-COCO annotations on the images:
notebooks/DensePose-COCO-on-SMPL.ipynbto localize the DensePose-COCO annotations on the 3D template (
SMPL) model:
notebooks/DensePose-RCNN-Visualize-Results.ipynbto visualize the inferred DensePose-RCNN Results.
notebooks/DensePose-RCNN-Texture-Transfer.ipynbto localize the DensePose-COCO annotations on the 3D template (
SMPL) model:
This source code is licensed under the license found in the
LICENSEfile in the root directory of this source tree.
If you use Densepose, please use the following BibTeX entry.
@InProceedings{Guler2018DensePose, title={DensePose: Dense Human Pose Estimation In The Wild}, author={R\{i}za Alp G\"uler, Natalia Neverova, Iasonas Kokkinos}, journal={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2018} }