Pose-Based Human Instance Segmentation
2 papers with code • 1 benchmarks • 1 datasets
Pose-Based Human Instance Segmentation is the task of delineating each distinct person of interest appearing in an image based on its ground-truth pose.
Benchmarks
These leaderboards are used to track progress in Pose-Based Human Instance Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
OCHuman
Most implemented papers
Pose2Seg: Detection Free Human Instance Segmentation
liruilong940607/Pose2Seg
•
•
CVPR 2019
We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
MiraPurkrabek/BBoxMaskPose
•
•
arXiv 2024
We condition pose estimation model by segmentation masks instead of bounding boxes to improve instance separation.
