close× Call Us +1 (777) 123 45 67

Category: arXiv

Authors: Rıza Alp Güler, George Trigeorgis , Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, Iasonas Kokkinos

Date: December 2016

Keywords: Dense Shape Regression · Face Alignment · Face Analysis · In-the-wild · Quantized Regression ·Fully Convolutional Neural Networks · Face Part Segmentation · Landmark Localization

arXiv

Supplementary

CODE
A link to the short clip at 1:08 with sound.

Abstract

In this paper we propose to learn a mapping from image pixels into a dense template grid through a fully convolutional network. We formulate this task as a regression problem and train our network by leveraging upon manually annotated facial landmarks “in-the-wild”. We use such landmarks to establish a dense correspondence field between a three-dimensional object template and the input image, which then serves as the ground-truth for training our regression system. We show that we can combine ideas from semantic segmentation with regression networks, yielding a highly-accurate ‘quantized regression’ architecture.

Our system, called DenseReg allows us to estimate dense image-to-template correspondences in a fully convolutional manner. As such our network can provide useful correspondence information as a stand-alone system, while when used as an initialization for Statistical Deformable Models we obtain landmark localization results that largely outperform the current state-of-the-art on the challenging 300W benchmark. We thoroughly evaluate our method on a host of facial analysis tasks, and also demonstrate its use for other correspondence estimation tasks, such as modelling of the human ear.