Keypoint Communities
This addresses pose estimation for applications like human-computer interaction or robotics, but appears incremental as it builds on graph-based methods with a new weighting approach.
The paper tackles the problem of detecting over 100 keypoints on humans or objects for pose estimation by modeling poses as graphs and using community detection insights, resulting in outperforming previous methods on fine-grained human pose estimation with 133 keypoints and generalizing to car poses.
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.