A unified bottom-up model that refines keypoints with disk-relative centroid vectors and uses high-confidence keypoints as dynamic mask centers outperforms prior pose and segmentation models on COCO, CrowdPose, and OCHuman.
Personlab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation
A unified bottom-up model that refines keypoints with disk-relative centroid vectors and uses high-confidence keypoints as dynamic mask centers outperforms prior pose and segmentation models on COCO, CrowdPose, and OCHuman.