https://github.com/MiraPurkrabek/BBoxMaskPose
공식 코드Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
Papers with Code 아카이브
Human Instance Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 18
Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/felixcaae/crowdsam
공식 코드Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
https://github.com/iigroup/hvisnet
공식 코드Real-time Human-Centric Segmentation for Complex Video Scenes
https://github.com/levan92/occlusion-copy-paste
공식 코드Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
https://github.com/liruilong940607/OCHumanApi
공식 코드https://github.com/liruilong940607/Pose2Seg
공식 코드https://github.com/lishuhuai527/coco-unihuman
공식 코드https://github.com/lkeab/BCNet
공식 코드Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
https://github.com/nii-yamagishilab/fashion_adv
공식 코드https://github.com/Jittor/InstanceSegmentation-jittor
https://github.com/hz-ants/Pose2Seg
https://github.com/jacksonlli/ProjectQuarantine_HumanSegmentation
https://github.com/ligaoqi2/Pose2Seg-single-person-video-demo
https://github.com/open-mmlab/mmpose
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.