Whole-body pose estimation on COCO-WholeBody 1.0
70.2Whole-body APRTMW-x
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| RTMW-xInput Size=384x288, training=Combined dataset [4]2024.07 | 70.2 | 78.1 | 76.3 | 82.6 | 79.6 | 88.8 | 88.4 | 92.3 | 66.4 | 75.5 | |
| RTMW-lInput Size=384x288, training=Combined dataset [4]2024.07 | 70.1 | 78 | 76.1 | 82.4 | 79.3 | 88.5 | 88.4 | 92.1 | 66.3 | 75.2 | |
| RTMW3D-xInput Size=384x288, training=Combined dataset [4]2024.07 | 68 | 75.9 | 73.9 | 80.5 | 76.6 | 86.8 | 88.6 | 92.1 | 62.7 | 72.2 | |
| RTMW3D-lInput Size=384x288, training=Combined dataset [4]2024.07 | 67.8 | 75.5 | 74.4 | 80.7 | 77.1 | 86.7 | 88.2 | 91.9 | 61.7 | 70.6 | |
| RTMW-xInput Size=256x192, training=Combined dataset [4]2024.07 | 67.2 | 75.2 | 74.6 | 80.8 | 77 | 86.9 | 84.4 | 89.6 | 61 | 71 | |
| DWPose-lInput Size=384x2882024.07 | 66.5 | 74.3 | 72.2 | 78.9 | 70.4 | 81.6 | 88.7 | 92.1 | 62.1 | 72 | |
| RTMW-lInput Size=256x192, training=Combined dataset [4]2024.07 | 66.2 | 74.6 | 74.3 | 80.7 | 76.3 | 86.8 | 83.4 | 88.9 | 59.8 | 70.1 | |
| ZoomNASInput Size=384x2882024.07 | 65.4 | 74.4 | 74 | 80.7 | 61.7 | 71.8 | 88.9 | 93 | 62.5 | 74 | |
| RTMPose-xInput Size=384x288, pre-trained=AIC+COCO, repro_id=22024.07 | 65.3 | 73.3 | 71.4 | 78.4 | 69.2 | 81 | 88.9 | 92.3 | 59 | 68.5 | |
| RTMPose-xInput Size=384x288, pre-trained=AIC+COCO, repro_id=12024.07 | 65.2 | 73.2 | 71.2 | 78 | 68.1 | 80.4 | 89 | 92.2 | 59.3 | 68.7 | |
| RTMPose-lInput Size=384x288, pre-trained=AIC+COCO2024.07 | 64.8 | 73 | 71.2 | 78.1 | 69.3 | 81.1 | 88.2 | 91.9 | 57.9 | 67.7 | |
| ZoomNetInput Size=384x2882024.07 | 63 | 74.2 | 74.5 | 81 | 60.9 | 70.8 | 88 | 92.4 | 57.9 | 73.4 | |
| RTMPose-lInput Size=256x192, pre-trained=AIC+COCO2024.07 | 61.1 | 70 | 69.5 | 76.9 | 65.8 | 78.5 | 83.3 | 88.7 | 51.9 | 62.8 | |
| FastPose50-dcn-v2Input Size=256x1922024.07 | 59.2 | 66.5 | 70.6 | 75.6 | 70.2 | 77.5 | 77.5 | 82.5 | 45.7 | 53.9 | |
| PVTInput Size=384x2882024.07 | 58.9 | 68.9 | 67.3 | 76.1 | 66 | 79.4 | 74.5 | 82.2 | 54.5 | 65.4 | |
| HRNetInput Size=384x2882024.07 | 58.6 | 67.4 | 70.1 | 77.3 | 58.6 | 69.2 | 72.7 | 78.3 | 51.6 | 60.4 | |
| RTMPose-mInput Size=256x192, pre-trained=AIC+COCO2024.07 | 58.2 | 67.4 | 67.3 | 75 | 61.5 | 75.2 | 81.3 | 87.1 | 47.5 | 58.9 | |
| RTMW-mInput Size=256x192, training=Combined dataset [4]2024.07 | 58 | 67.3 | 67.6 | 74.7 | 67.1 | 79.4 | 78.3 | 85.4 | 49.1 | 60.4 | |
| SimpleBaselineInput Size=384x2882024.07 | 57.3 | 67.1 | 66.6 | 74.7 | 63.5 | 76.3 | 73.2 | 81.2 | 53.7 | 64.7 | |
| DeepPoseInput Size=384x2882024.07 | 33.5 | 45.6 | 42.7 | 58.3 | 9.9 | 36.9 | 64.9 | 69.7 | 40.8 | 58 |