Human Instance Segmentation
1개 벤치마크 · 논문 18편 · 이 태스크의 논문 보기 →
Benchmarks
OCHuman
Most implemented
Pose2Seg: Detection Free Human Instance Segmentation
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
Papers
SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds
Segment Anything (SAM) provides an unprecedented foundation for human segmentation, but may struggle under occlusion, where keypoints may be partially or fully invisible. We adapt SAM 2.1 for pose-guided segmentation wit…
Human Instance SegmentationLeveraging Multi-View Weak Supervision for Occlusion-Aware Multi-Human Parsing
Multi-human parsing is the task of segmenting human body parts while associating each part to the person it belongs to, combining instance-level and part-level information for fine-grained human understanding. In this wo…
Human Instance SegmentationMulti-Human ParsingDetection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
Human pose estimation methods work well on separated people but struggle with multi-body scenarios. Recent work has addressed this problem by conditioning pose estimation with detected bounding boxes or bottom-up-estimat…
Human Instance SegmentationPose-Based Human Instance SegmentationPose EstimationSegmentationCrowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything…
Human Instance SegmentationInstance Segmentationobject-detectionObject Detection+1You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-…
AttributeHuman Instance SegmentationMulti-Task LearningPose EstimationObject-Centric Multi-Task Learning for Human Instances
Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation. Although much effort has been put into individual tasks, multi-task learning for these three ta…
Human DetectionHuman Instance SegmentationMulti-Task LearningObject+2