Structured face hallucination

Chih Yuan Yang, Sifei Liu, Ming Hsuan Yang

Research output: Contribution to journalConference article

68 Citations (Scopus)

Abstract

The goal of face hallucination is to generate high-resolution images with fidelity from low-resolution ones. In contrast to existing methods based on patch similarity or holistic constraints in the image space, we propose to exploit local image structures for face hallucination. Each face image is represented in terms of facial components, contours and smooth regions. The image structure is maintained via matching gradients in the reconstructed high-resolution output. For facial components, we align input images to generate accurate exemplars and transfer the high-frequency details for preserving structural consistency. For contours, we learn statistical priors to generate salient structures in the high-resolution images. A patch matching method is utilized on the smooth regions where the image gradients are preserved. Experimental results demonstrate that the proposed algorithm generates hallucinated face images with favorable quality and adaptability.

Original languageEnglish
Article number6618990
Pages (from-to)1099-1106
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Publication statusPublished - 2013 Nov 15
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: 2013 Jun 232013 Jun 28

Fingerprint

Image resolution
Optical resolving power

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{458a91338fb848d7ab86e1254f7c9402,
title = "Structured face hallucination",
abstract = "The goal of face hallucination is to generate high-resolution images with fidelity from low-resolution ones. In contrast to existing methods based on patch similarity or holistic constraints in the image space, we propose to exploit local image structures for face hallucination. Each face image is represented in terms of facial components, contours and smooth regions. The image structure is maintained via matching gradients in the reconstructed high-resolution output. For facial components, we align input images to generate accurate exemplars and transfer the high-frequency details for preserving structural consistency. For contours, we learn statistical priors to generate salient structures in the high-resolution images. A patch matching method is utilized on the smooth regions where the image gradients are preserved. Experimental results demonstrate that the proposed algorithm generates hallucinated face images with favorable quality and adaptability.",
author = "Yang, {Chih Yuan} and Sifei Liu and Yang, {Ming Hsuan}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.146",
language = "English",
pages = "1099--1106",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Structured face hallucination. / Yang, Chih Yuan; Liu, Sifei; Yang, Ming Hsuan.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 15.11.2013, p. 1099-1106.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Structured face hallucination

AU - Yang, Chih Yuan

AU - Liu, Sifei

AU - Yang, Ming Hsuan

PY - 2013/11/15

Y1 - 2013/11/15

N2 - The goal of face hallucination is to generate high-resolution images with fidelity from low-resolution ones. In contrast to existing methods based on patch similarity or holistic constraints in the image space, we propose to exploit local image structures for face hallucination. Each face image is represented in terms of facial components, contours and smooth regions. The image structure is maintained via matching gradients in the reconstructed high-resolution output. For facial components, we align input images to generate accurate exemplars and transfer the high-frequency details for preserving structural consistency. For contours, we learn statistical priors to generate salient structures in the high-resolution images. A patch matching method is utilized on the smooth regions where the image gradients are preserved. Experimental results demonstrate that the proposed algorithm generates hallucinated face images with favorable quality and adaptability.

AB - The goal of face hallucination is to generate high-resolution images with fidelity from low-resolution ones. In contrast to existing methods based on patch similarity or holistic constraints in the image space, we propose to exploit local image structures for face hallucination. Each face image is represented in terms of facial components, contours and smooth regions. The image structure is maintained via matching gradients in the reconstructed high-resolution output. For facial components, we align input images to generate accurate exemplars and transfer the high-frequency details for preserving structural consistency. For contours, we learn statistical priors to generate salient structures in the high-resolution images. A patch matching method is utilized on the smooth regions where the image gradients are preserved. Experimental results demonstrate that the proposed algorithm generates hallucinated face images with favorable quality and adaptability.

UR - http://www.scopus.com/inward/record.url?scp=84887392129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887392129&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.146

DO - 10.1109/CVPR.2013.146

M3 - Conference article

AN - SCOPUS:84887392129

SP - 1099

EP - 1106

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

M1 - 6618990

ER -