DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
Preprint
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. DenseReg code is made available at http://alpguler.com/DenseReg.html along with supplementary materials.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- gvnn: Neural Network Library for Geometric Computer Vision2016
- Deep Residual Learning for Image Recognition2016
- Multi-view facial landmark detector learned by the Structured Output SVMImage and Vision Computing, 2016
- 300 Faces In-The-Wild Challenge: database and resultsImage and Vision Computing, 2016
- Multi-view facial landmark detection by using a 3D shape modelImage and Vision Computing, 2016
- M3 CSR: Multi-view, multi-scale and multi-component cascade shape regressionImage and Vision Computing, 2016
- L2,1-based regression and prediction accumulation across views for robust facial landmark detectionImage and Vision Computing, 2016
- An Elastic Deformation Field Model for Object Detection and TrackingInternational Journal of Computer Vision, 2014
- A Wavelet Tour of Signal Processing1999
- Distortion invariant object recognition in the dynamic link architectureIEEE Transactions on Computers, 1993