OCHuman

Introduced by Zhang et al. in Pose2Seg: Detection Free Human Instance Segmentation

This dataset focuses on heavily occluded human with comprehensive annotations including bounding-box, humans pose and instance mask. This dataset contains 13,360 elaborately annotated human instances within 5081 images. With average 0.573 MaxIoU of each person, OCHuman is the most complex and challenging dataset related to human.

Source: https://github.com/liruilong940607/OCHumanApi

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Pose Estimation	OCHuman	ViTPose
2D Human Pose Estimation	OCHuman	MIPNet
Keypoint Detection	OCHuman	MIPNet
Multi-Person Pose Estimation	OCHuman	MIPNet
Human Instance Segmentation	OCHuman	Pose2Seg