Mean Reconstruction Error (mm): 12.2
Papers with Code · CC BY-SA 4.0
3D Human Pose Estimation
3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
LMT R152 384x384
Average MPJPE (mm): 17.59Using 2D ground-truth joints: NoMulti-View or Monocular: Multi-ViewMPVE (mm): 23.7
논문
-
RealSR + x264
BSQ-rate over ERQA: 0.77BSQ-rate over Subjective Score: 0.196BSQ-rate over VMAF: 0.775BSQ-rate over PSNR: 0.675
논문
코드
MotionBERT (Finetune)
Average MPJPE (mm): 37.5Use Video Sequence: YesFrames Needed: 243Need Ground Truth 2D Pose: No
논문
코드
AdaptPose
Average MPJPE (mm): 42.5Number of Views: 1Number of Frames Per View: 273D Annotations: S1
논문
코드
데이터셋
75개논문
Mean Reconstruction Error (mm): 13.5
Mean Reconstruction Error (mm): 21.2
Mean Reconstruction Error (mm): 15.4
Mean Reconstruction Error (mm): 9.2
Mean Reconstruction Error (mm): 15.2
Mean Reconstruction Error (mm): 19.5
Mean Reconstruction Error (mm): 16.1
Mean Reconstruction Error (mm): 14.3
Mean Reconstruction Error (mm): 18.3
Mean Reconstruction Error (mm): 19.1
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.
하위 태스크
3A
3D Absolute Human Pose Estimation
3M
3D Multi-Person Pose Estimation
M3
Monocular 3D Human Pose Estimation
W3
Weakly-supervised 3D Human Pose Estimation
M3
Multi-Hypotheses 3D Human Pose Estimation
EP
Egocentric Pose Estimation
PP
Pose Prediction
3H
3D human pose and shape estimation
G3
Global 3D Human Pose Estimation