Hallucinating Compressed Face Images

Chih Yuan Yang, Sifei Liu, Ming Hsuan Yang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A face hallucination algorithm is proposed to generate high-resolution images from JPEG compressed low-resolution inputs by decomposing a deblocked face image into structural regions such as facial components and non-structural regions like the background. For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition. For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts. Two sets of gradient maps extracted from these two regions are combined to guide an optimization process of generating the hallucination image. Numerous experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art hallucination methods on JPEG compressed face images with different poses, expressions, and illumination conditions.

Original languageEnglish
Pages (from-to)597-614
Number of pages18
JournalInternational Journal of Computer Vision
Volume126
Issue number6
DOIs
Publication statusPublished - 2018 Jun 1

Fingerprint

Lighting
Optical resolving power
Image resolution

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Yang, Chih Yuan ; Liu, Sifei ; Yang, Ming Hsuan. / Hallucinating Compressed Face Images. In: International Journal of Computer Vision. 2018 ; Vol. 126, No. 6. pp. 597-614.
@article{b00af9b7f77848b18f72eebe81668560,
title = "Hallucinating Compressed Face Images",
abstract = "A face hallucination algorithm is proposed to generate high-resolution images from JPEG compressed low-resolution inputs by decomposing a deblocked face image into structural regions such as facial components and non-structural regions like the background. For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition. For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts. Two sets of gradient maps extracted from these two regions are combined to guide an optimization process of generating the hallucination image. Numerous experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art hallucination methods on JPEG compressed face images with different poses, expressions, and illumination conditions.",
author = "Yang, {Chih Yuan} and Sifei Liu and Yang, {Ming Hsuan}",
year = "2018",
month = "6",
day = "1",
doi = "10.1007/s11263-017-1044-4",
language = "English",
volume = "126",
pages = "597--614",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "6",

}

Hallucinating Compressed Face Images. / Yang, Chih Yuan; Liu, Sifei; Yang, Ming Hsuan.

In: International Journal of Computer Vision, Vol. 126, No. 6, 01.06.2018, p. 597-614.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Hallucinating Compressed Face Images

AU - Yang, Chih Yuan

AU - Liu, Sifei

AU - Yang, Ming Hsuan

PY - 2018/6/1

Y1 - 2018/6/1

N2 - A face hallucination algorithm is proposed to generate high-resolution images from JPEG compressed low-resolution inputs by decomposing a deblocked face image into structural regions such as facial components and non-structural regions like the background. For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition. For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts. Two sets of gradient maps extracted from these two regions are combined to guide an optimization process of generating the hallucination image. Numerous experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art hallucination methods on JPEG compressed face images with different poses, expressions, and illumination conditions.

AB - A face hallucination algorithm is proposed to generate high-resolution images from JPEG compressed low-resolution inputs by decomposing a deblocked face image into structural regions such as facial components and non-structural regions like the background. For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition. For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts. Two sets of gradient maps extracted from these two regions are combined to guide an optimization process of generating the hallucination image. Numerous experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art hallucination methods on JPEG compressed face images with different poses, expressions, and illumination conditions.

UR - http://www.scopus.com/inward/record.url?scp=85037345871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037345871&partnerID=8YFLogxK

U2 - 10.1007/s11263-017-1044-4

DO - 10.1007/s11263-017-1044-4

M3 - Article

AN - SCOPUS:85037345871

VL - 126

SP - 597

EP - 614

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 6

ER -