MPJPE: 103.0
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.
논문
B-NMVE: 73.7B-NMJE: 72.3B-MVE: 68.5B-MPJPE: 67.2
MPJPE: 36.9PA-MPJPE: 28.9PVE: 44.7
MPJPE: 45.39
MPJPE: 60.83
MPJPE: 55.3
MPJPE: 49.1
B-NMVE: 217.0B-NMJE: 226.0B-MVE: 173.6B-MPJPE: 180.5
MPJPE: 63.0
Mean Reconstruction Error (mm): 79.9
B-NMVE: 216.3B-NMJE: 223.1B-MVE: 168.7B-MPJPE: 175.1
B-NMVE: 104.5B-NMJE: 110.4B-MVE: 86.7B-MPJPE: 91.6
B-NMVE: 70.2B-NMJE: 74B-MVE: 63.9B-MPJPE: 67.3
B-NMVE: 167.7B-NMJE: 174.0B-MVE: 140.9B-MPJPE: 146.2
MPJPE: 51.7PA-MPJPE: 37.9
MPJPE: 37.1PCK: 97.3
B-NMVE: 94.4B-NMJE: 93.5B-MVE: 84.0B-MPJPE: 83.2
B-NMVE: 87.3B-NMJE: 92.6B-MVE: 78.6B-MPJPE: 83.3
MPJPE: 57
MPJPE: 64.4
B-NMVE: 126.8B-NMJE: 133.7B-MVE: 106.5B-MPJPE: 112.3
B-NMVE: 70.4B-NMJE: 75.4B-MVE: 63.4B-MPJPE: 67.9