Multi Hypotheses 3D Human Pose Estimation On 2
المقاييس
Best-Hypothesis MPJPE (n = 25)
Best-Hypothesis PMPJPE (n = 25)
H36M PMPJPE (n = 1)
H36M PMPJPE (n = 25)
Most-Likely Hypothesis PMPJPE (n = 1)
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
اسم النموذج | Best-Hypothesis MPJPE (n = 25) | Best-Hypothesis PMPJPE (n = 25) | H36M PMPJPE (n = 1) | H36M PMPJPE (n = 25) | Most-Likely Hypothesis PMPJPE (n = 1) |
---|---|---|---|---|---|
probabilistic-modeling-for-human-mesh | - | 60.1 | 41.2 | 36.8 | 67.3 |
generating-multiple-hypotheses-for-3d-human | 91.5 | 69.5 | 44.8 | 42.7 | 74.7 |
probabilistic-modeling-for-human-mesh | - | 82.6 | - | 64.3 | - |
humaniflow-ancestor-conditioned-normalising | - | - | - | - | - |
3d-multi-bodies-fitting-sets-of-plausible-3d | 90.0 | 64.2 | 41.6 | 42.2 | 67.8 |
mhentropy-entropy-meets-multiple-hypotheses | - | 50.6 | - | 36.8 | - |
3d-multi-bodies-fitting-sets-of-plausible-3d | 109.7 | 75.1 | 46.7 | 46.2 | 76.5 |
end-to-end-recovery-of-human-shape-and-pose | - | - | 56.8 | 56.8 | - |
mhentropy-entropy-meets-multiple-hypotheses | - | 66.4 | - | 51.3 | - |
end-to-end-recovery-of-human-shape-and-pose | - | 85.2 | 67.4 | 67.4 | 85.2 |