Efficient Deep Face Alignment with Explicit Statistical Shape Models in Convolutional Neural Networks

International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–6

Abstract

Face alignment is commonly solved by utilizing a shape representation which is either implicitly learned as in current deep architectures or explicitly given as in active shape models and their derivatives. In this work, we present a method for integrating explicit statistical shape priors into a deep convolutional network by introducing a novel layer which allows using statistical PCA-based models directly in the network, resulting in a highly efficient deep face alignment architecture capable of performing landmark detection with several hundreds of frames per second on consumer hardware. In addition to introducing the core algorithm, we also introduce and discuss extensions for improving fitting precision. We validate the performance of all methods quantitatively on the 300W dataset, where we achieve state-of-the-art precision while requiring only a fraction of the runtime of most competing methods.

Authors 3

1. Marcin Kopaczka Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany

2. Justus Schock Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany

3. Dorit Merhof Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany