Skip to main content

Table 2 Averaged error comparisons and percentages of images (CED) of our model with different stages, where the RMSEs are less than 0.05 and 0.1 of our model on the LFPW, HELEN, and IBUG datasets

From: Multiscale recurrent regression networks for face alignment

Datasets Meanshape Stage = 1 Stage = 2 Stage = 3
300-W fullSet 19.52 6.64 5.16 4.84
  1. The italic values denote the highest performance