DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

Abstract : In this paper we propose to learn a mapping from image pixels into a dense template grid through a fully convolu-tional 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 convo-lutional 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 demonstrate its use for other correspondence estimation tasks, such as the human body and the human ear. DenseReg code is made available at along with supplementary materials.
Liste complète des métadonnées

Cited literature [52 references]  Display  Hide  Download
Contributor : Riza Alp Guler <>
Submitted on : Saturday, November 18, 2017 - 2:44:23 PM
Last modification on : Monday, March 4, 2019 - 2:44:13 PM
Document(s) archivé(s) le : Monday, February 19, 2018 - 12:38:35 PM


Files produced by the author(s)


  • HAL Id : hal-01637896, version 1
  • ARXIV : 1612.01202


Riza Alp Güler, George Trigeorgis, Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, et al.. DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, CVF, Jul 2017, Honolulu, United States. pp.6799-6808. ⟨hal-01637896⟩



Record views


Files downloads