B-NMVE: 73.7B-NMJE: 72.3B-MVE: 68.5B-MPJPE: 67.2
Papers with Code · CC BY-SA 4.0
Pose Estimation
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
논문
Mean Reconstruction Error (mm): 26.9
Mean Reconstruction Error (mm): 21.6
Mean Reconstruction Error (mm): 38.9
Mean Reconstruction Error (mm): 21.2
Mean Reconstruction Error (mm): 56.7
Mean Reconstruction Error (mm): 24.6
Mean Reconstruction Error (mm): 24.3
Mean Reconstruction Error (mm): 24.3
Mean Reconstruction Error (mm): 33.7
Mean Reconstruction Error (mm): 40.3
Mean Reconstruction Error (mm): 15.4
Mean Reconstruction Error (mm): 18.9
Mean Reconstruction Error (mm): 22
Mean Reconstruction Error (mm): 79.9
Mean Reconstruction Error (mm): 19.5
Mean Reconstruction Error (mm): 22.9
Mean Reconstruction Error (mm): 22.9
Mean Reconstruction Error (mm): 16.1
Mean Reconstruction Error (mm): 23.9
Mean Reconstruction Error (mm): 64
B-NMVE: 70.2B-NMJE: 74B-MVE: 63.9B-MPJPE: 67.3
Mean Reconstruction Error (mm): 18.3
Mean Reconstruction Error (mm): 30.8
Mean Reconstruction Error (mm): 19.1
Mean Reconstruction Error (mm): 71.3
Mean Reconstruction Error (mm): 39.1
Mean Reconstruction Error (mm): 74.5
B-NMVE: 70.4B-NMJE: 75.4B-MVE: 63.4B-MPJPE: 67.9