Single image super-resolution using deformable patches

Yu Zhu; Yanning Zhang; Alan L. Yuille

doi:10.1109/CVPR.2014.373

Single image super-resolution using deformable patches

Yu Zhu, Yanning Zhang, Alan L. Yuille

School of Computer Science

University of California at Los Angeles

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

116 Scopus citations

Abstract

We proposed a deformable patches based method for single image super-resolution. By the concept of deformation, a patch is not regarded as a fixed vector but a flexible deformation flow. Via deformable patches, the dictionary can cover more patterns that do not appear, thus becoming more expressive. We present the energy function with slow, smooth and flexible prior for deformation model. During example-based super-resolution, we develop the deformation similarity based on the minimized energy function for basic patch matching. For robustness, we utilize multiple deformed patches combination for the final reconstruction. Experiments evaluate the deformation effectiveness and super-resolution performance, showing that the deformable patches help improve the representation accuracy and perform better than the state-of-art methods.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Computer Society
Pages	2917-2924
Number of pages	8
ISBN (Electronic)	9781479951178, 9781479951178
DOIs	https://doi.org/10.1109/CVPR.2014.373
State	Published - 24 Sep 2014
Event	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 23 Jun 2014 → 28 Jun 2014

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Conference

Conference	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/Territory	United States
City	Columbus
Period	23/06/14 → 28/06/14

Keywords

deformable patches
single super-resolution

Access to Document

10.1109/CVPR.2014.373

Cite this

Zhu, Y., Zhang, Y., & Yuille, A. L. (2014). Single image super-resolution using deformable patches. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2917-2924). Article 6909769 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.373

@inproceedings{962b9137e0644935a345c387865ec419,

title = "Single image super-resolution using deformable patches",

abstract = "We proposed a deformable patches based method for single image super-resolution. By the concept of deformation, a patch is not regarded as a fixed vector but a flexible deformation flow. Via deformable patches, the dictionary can cover more patterns that do not appear, thus becoming more expressive. We present the energy function with slow, smooth and flexible prior for deformation model. During example-based super-resolution, we develop the deformation similarity based on the minimized energy function for basic patch matching. For robustness, we utilize multiple deformed patches combination for the final reconstruction. Experiments evaluate the deformation effectiveness and super-resolution performance, showing that the deformable patches help improve the representation accuracy and perform better than the state-of-art methods.",

keywords = "deformable patches, single super-resolution",

author = "Yu Zhu and Yanning Zhang and Yuille, {Alan L.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 ; Conference date: 23-06-2014 Through 28-06-2014",

year = "2014",

month = sep,

day = "24",

doi = "10.1109/CVPR.2014.373",

language = "英语",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "2917--2924",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

Zhu, Y , Zhang, Y & Yuille, AL 2014, Single image super-resolution using deformable patches. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909769, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 2917-2924, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 23/06/14. https://doi.org/10.1109/CVPR.2014.373

Single image super-resolution using deformable patches. / Zhu, Yu ; Zhang, Yanning; Yuille, Alan L.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 2917-2924 6909769 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Single image super-resolution using deformable patches

AU - Zhu, Yu

AU - Zhang, Yanning

AU - Yuille, Alan L.

PY - 2014/9/24

Y1 - 2014/9/24

N2 - We proposed a deformable patches based method for single image super-resolution. By the concept of deformation, a patch is not regarded as a fixed vector but a flexible deformation flow. Via deformable patches, the dictionary can cover more patterns that do not appear, thus becoming more expressive. We present the energy function with slow, smooth and flexible prior for deformation model. During example-based super-resolution, we develop the deformation similarity based on the minimized energy function for basic patch matching. For robustness, we utilize multiple deformed patches combination for the final reconstruction. Experiments evaluate the deformation effectiveness and super-resolution performance, showing that the deformable patches help improve the representation accuracy and perform better than the state-of-art methods.

AB - We proposed a deformable patches based method for single image super-resolution. By the concept of deformation, a patch is not regarded as a fixed vector but a flexible deformation flow. Via deformable patches, the dictionary can cover more patterns that do not appear, thus becoming more expressive. We present the energy function with slow, smooth and flexible prior for deformation model. During example-based super-resolution, we develop the deformation similarity based on the minimized energy function for basic patch matching. For robustness, we utilize multiple deformed patches combination for the final reconstruction. Experiments evaluate the deformation effectiveness and super-resolution performance, showing that the deformable patches help improve the representation accuracy and perform better than the state-of-art methods.

KW - deformable patches

KW - single super-resolution

UR - http://www.scopus.com/inward/record.url?scp=84911370719&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2014.373

DO - 10.1109/CVPR.2014.373

M3 - 会议稿件

AN - SCOPUS:84911370719

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 2917

EP - 2924

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

PB - IEEE Computer Society

T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014

Y2 - 23 June 2014 through 28 June 2014

ER -

Single image super-resolution using deformable patches

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this