Table 4 Quantitative comparison with state-of-the-art methods on MPI-INF-3DHP. The top two best methods of each action are highlighted in bold and underlined respectively.

From: Dual chain dynamic hypergraph convolution network for 3D human pose estimation

Method

PCK

AUC

Parameters (M)

Flops (M)

Ci et al.5

74.0

36.7

2.92

16.52

Xu et al.8

80.1

45.8

3.70

27.42

Martinez et al.6

42.5

17.0

19.31

22.43

Pavllo et al.44

81.6

48.2

14.23

26.98

Ours

88.1

52.5

11.22

17.94

Back to article page