Fig. 1
From: Multiscale recurrent regression networks for face alignment
The framework of our proposed MSRRN. Our MSRRN consists of two stages: shape initialization and shape update. Accordingly , the shape initialization aims to estimate a rough facial shape for a given face image under a convolutional neural network. The shape update stage attempts to refine facial shape based on the initial shape and shape-index pixels progressively. Moreover, our MSRRN shares the network parameters across different stages and involves multiscale information to reinforce our model for accurate facial landmark localization. Since our MSRRN network learns directly from raw pixels, the network parameters are optimized via back-propagation in an end-to-end manner