Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation
This addresses overlapping joints and rapid pose changes in instance-level segmentation for applications like live environments, though it appears incremental as it builds on existing keypoint and segmentation methods.
The paper tackles the challenge of dynamic human body movement in pose estimation and segmentation by proposing Keypoints as Dynamic Centroid (KDC), a centroid-based representation that improves accuracy and runtime performance on benchmarks like CrowdPose, OCHuman, and COCO.
The dynamic movement of the human body presents a fundamental challenge for human pose estimation and body segmentation. State-of-the-art approaches primarily rely on combining keypoint heatmaps with segmentation masks but often struggle in scenarios involving overlapping joints or rapidly changing poses during instance-level segmentation. To address these limitations, we propose Keypoints as Dynamic Centroid (KDC), a new centroid-based representation for unified human pose estimation and instance-level segmentation. KDC adopts a bottom-up paradigm to generate keypoint heatmaps for both easily distinguishable and complex keypoints and improves keypoint detection and confidence scores by introducing KeyCentroids using a keypoint disk. It leverages high-confidence keypoints as dynamic centroids in the embedding space to generate MaskCentroids, allowing for swift clustering of pixels to specific human instances during rapid body movements in live environments. Our experimental evaluations on the CrowdPose, OCHuman, and COCO benchmarks demonstrate KDC's effectiveness and generalizability in challenging scenarios in terms of both accuracy and runtime performance. The implementation is available at: https://sites.google.com/view/niazahmad/projects/kdc.