Table 1 Per-vertex reconstruction error measured as mean absolute error (MAE) between input and decoded meshes for held-out test meshes from Shape Up! Adults (n = 424)

From: 3D convolutional deep learning for nonlinear estimation of body composition from whole body morphology

 

d = 49

d = 301

d = 630

d = 4284

3DAE MAE (mm)

5.16

2.57

2.18

2.02

PCA MAE (mm)

5.26

2.41

2.23

1.0

  1. The dimensionality (d) represents the number of latent layer variables in the autoencoder bottleneck or the number of principal components used for a linear shape space reconstruction.
Back to article page