Publications

BibTex format

@inproceedings{Guler:2017,
author = {Guler, R and Trigeorgis, G and Antonakos, E and Snape, P and Zafeiriou, S and Kokkinos, I},
publisher = {IEEE},
title = {DenseReg: fully convolutional dense shape regression in-the-wild},
url = {http://hdl.handle.net/10044/1/45425},
year = {2017}
}

Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - In this paper we propose to learn a mapping from imagepixels into a dense template grid through a fully convolutionalnetwork. We formulate this task as a regression problemand train our network by leveraging upon manually annotatedfacial landmarks “in-the-wild”. We use such landmarksto establish a dense correspondence field betweena three-dimensional object template and the input image,which then serves as the ground-truth for training our regressionsystem. We show that we can combine ideas fromsemantic segmentation with regression networks, yielding ahighly-accurate ‘quantized regression’ architecture.Our system, called DenseReg, allows us to estimatedense image-to-template correspondences in a fully convolutionalmanner. As such our network can provide usefulcorrespondence information as a stand-alone system, whilewhen used as an initialization for Statistical DeformableModels we obtain landmark localization results that largelyoutperform the current state-of-the-art on the challenging300W benchmark. We thoroughly evaluate our method ona host of facial analysis tasks, and demonstrate its use forother correspondence estimation tasks, such as the humanbody and the human ear. DenseReg code is made availableat http://alpguler.com/DenseReg.html alongwith supplementary materials.
AU  - Guler,R
AU  - Trigeorgis,G
AU  - Antonakos,E
AU  - Snape,P
AU  - Zafeiriou,S
AU  - Kokkinos,I
PB  - IEEE
PY  - 2017///
TI  - DenseReg: fully convolutional dense shape regression in-the-wild
UR  - http://hdl.handle.net/10044/1/45425
ER  -

Download

STEFANOS ZAFEIRIOU, PhD

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)