Inpainting

Programming language

Task (project management)

Convolutional neural network

Artificial intelligence

Economics

Set (abstract data type)

Representation (politics)

Code (set theory)

Deep learning

Test set

Pattern recognition (psychology)

Pipeline (software)

Politics

Image (mathematics)

Political science

Management

Computer science

Pose

RGB color model

Ground truth

Annotation

Computer vision

Training set

In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an inpainting network that can fill in missing ground truth values and report improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter. We further improve accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Supplementary materials, data, code, and videos are provided on the project page http://densepose.org.

DensePose: Dense Human Pose Estimation in the Wild