Keypoint Communities

Duncan Zauss, Sven Kreiss, Alexandre Alahi

Abstract

We present a fast bottom-up method that jointly detects over 100 keypoints on humans or objects, also referred to as human/object pose estimation. We model all keypoints belonging to a human or an object –the pose– as a graph and leverage insights from community detection to quantify the independence of keypoints. We use a graph centrality measure to assign training weights to different parts of a pose. Our proposed measure quantifies how tightly a keypoint is connected to its neighborhood. Our experiments show that our method outperforms all previous methods for human pose estimation with fine-grained keypoint annotations on the face, the hands and the feet with a total of 133 keypoints. We also show that our method generalizes to car poses.
BibTeX
@inproceedings{zauss2021keypoint,
  author = {Duncan Zauss and Sven Kreiss and Alexandre Alahi},
  title = {{Keypoint Communities}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  doi = {10.1109/iccv48922.2021.01087},
}
Figure