Skip to content
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Jupyter Notebook Python CMake Cuda C++ MATLAB
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
DensePoseData updated links to public densepose and detectron resources Jan 14, 2019
PoseTrack updated links to public densepose and detectron resources Jan 14, 2019
challenge use correct iou value for eval Aug 8, 2019
cmake use the classical form of the if operator, update summary Jun 22, 2018
configs updated links to public densepose and detectron resources Jan 14, 2019
detectron updated links to public densepose and detectron resources Jan 14, 2019
docker revert Dockerfile changes Jun 23, 2018
notebooks Fix wrong image location in notebook Jun 21, 2018
tools detectron_2_densepose Jun 14, 2018
.gitignore added an example results file for COCO DensePose challenge Jul 23, 2018
CMakeLists.txt use the classical form of the if operator, update summary Jun 22, 2018
CODE_OF_CONDUCT.md add contributing and code_of_conduct Jun 15, 2018
CONTRIBUTING.md add contributing and code_of_conduct Jun 15, 2018
GETTING_STARTED.md updated links to public densepose and detectron resources Jan 14, 2019
INSTALL.md added instructions to setup docker image for inference / training Jun 23, 2018
LICENSE detectron_2_densepose Jun 14, 2018
MODEL_ZOO.md corrected md5 file path Jan 14, 2019
Makefile Encapsulate detectron code in a package May 7, 2018
NOTICE Initial commit Jan 22, 2018
README.md Fixing typo in document. Jun 19, 2018
requirements.txt added missing requirements for h5py and memory_profiler Jun 20, 2018
setup.py detectron_2_densepose Jun 14, 2018

README.md

DensePose:

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.

Installation

Please find installation instructions for Caffe2 and DensePose in INSTALL.md, a document based on the Detectron installation instructions.

Inference-Training-Testing

After installation, please see GETTING_STARTED.md for examples of inference and training and testing.

Notebooks

Visualization of DensePose-COCO annotations:

See notebooks/DensePose-COCO-Visualize.ipynb to visualize the DensePose-COCO annotations on the images:


DensePose-COCO in 3D:

See notebooks/DensePose-COCO-on-SMPL.ipynb to localize the DensePose-COCO annotations on the 3D template (SMPL) model:


Visualize DensePose-RCNN Results:

See notebooks/DensePose-RCNN-Visualize-Results.ipynb to visualize the inferred DensePose-RCNN Results.


DensePose-RCNN Texture Transfer:

See notebooks/DensePose-RCNN-Texture-Transfer.ipynb to localize the DensePose-COCO annotations on the 3D template (SMPL) model:

License

This source code is licensed under the license found in the LICENSE file in the root directory of this source tree.

Citing DensePose

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}
  }
You can’t perform that action at this time.