Keypoint Communities
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.
PDF Abstract ICCV 2021 PDF ICCV 2021 AbstractCode
Spaces
Datasets
MS COCO
COCO-WholeBody
ApolloCar3D
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Car Pose Estimation | ApolloCar3D | Zauss et al. | Detection Rate | 91.9 | # 1 | ||
| 2D Human Pose Estimation | COCO-WholeBody | Zauss et al. | WB | 60.4 | # 9 | ||
| body | 69.6 | # 9 | |||||
| foot | 63.4 | # 9 | |||||
| face | 85.0 | # 7 | |||||
| hand | 52.9 | # 9 |
