DensePose: Dense Human Pose Estimation In The Wild

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We first 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 groundtruth values and report clear 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 highly0accurate results in real time. Supplementary materials and videos are provided on the project page

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract


Introduced in the Paper:


Used in the Paper:


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pose Estimation DensePose-COCO DensePose + keypoints AP 55.8 # 2


No methods listed for this paper. Add relevant methods here