A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

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}
  }