Low-rank total variation for image super-resolution.

Feng Shi, Jian Cheng, L. Wang, Pew Thian Yap, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Most natural images can be approximated using their low-rank components. This fact has'been successfully exploited in recent advancements of matrix completion algorithms for image recovery. However, a major limitation of low-rank matrix completion algorithms is that they cannot recover the case where a whole row or column is missing. The missing row or column will be simply filled as an arbitrary combination of other rows or columns with known values. This precludes the application of matrix completion to problems such as super-resolution (SR) where missing values in many rows and columns need to be recovered in the process of up-sampling a low-resolution image. Moreover, low-rank regularization considers information globally from the whole image and does not take proper consideration of local spatial consistency. Accordingly, we propose in this paper a solution to the SR problem via simultaneous (global) low-rank and (local) total variation (TV) regularization. We solve the respective cost function using the alternating direction method of multipliers (ADMM). Experiments on MR images of adults and pediatric subjects demonstrate that the proposed method enhances the details of the recovered high-resolution images, and outperforms the nearest-neighbor interpolation, cubic interpolation, non-local means, and TV-based up-sampling.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages155-162
Number of pages8
Volume16
EditionPt 1
Publication statusPublished - 2013 Dec 1
Externally publishedYes

Fingerprint

Pediatrics
Costs and Cost Analysis
Direction compound

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Shi, F., Cheng, J., Wang, L., Yap, P. T., & Shen, D. (2013). Low-rank total variation for image super-resolution. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Pt 1 ed., Vol. 16, pp. 155-162)

Low-rank total variation for image super-resolution. / Shi, Feng; Cheng, Jian; Wang, L.; Yap, Pew Thian; Shen, Dinggang.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 16 Pt 1. ed. 2013. p. 155-162.

Research output: Chapter in Book/Report/Conference proceedingChapter

Shi, F, Cheng, J, Wang, L, Yap, PT & Shen, D 2013, Low-rank total variation for image super-resolution. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 1 edn, vol. 16, pp. 155-162.
Shi F, Cheng J, Wang L, Yap PT, Shen D. Low-rank total variation for image super-resolution. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 1 ed. Vol. 16. 2013. p. 155-162
Shi, Feng ; Cheng, Jian ; Wang, L. ; Yap, Pew Thian ; Shen, Dinggang. / Low-rank total variation for image super-resolution. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 16 Pt 1. ed. 2013. pp. 155-162
@inbook{473afee5c7d74893aa4e69d93ac92267,
title = "Low-rank total variation for image super-resolution.",
abstract = "Most natural images can be approximated using their low-rank components. This fact has'been successfully exploited in recent advancements of matrix completion algorithms for image recovery. However, a major limitation of low-rank matrix completion algorithms is that they cannot recover the case where a whole row or column is missing. The missing row or column will be simply filled as an arbitrary combination of other rows or columns with known values. This precludes the application of matrix completion to problems such as super-resolution (SR) where missing values in many rows and columns need to be recovered in the process of up-sampling a low-resolution image. Moreover, low-rank regularization considers information globally from the whole image and does not take proper consideration of local spatial consistency. Accordingly, we propose in this paper a solution to the SR problem via simultaneous (global) low-rank and (local) total variation (TV) regularization. We solve the respective cost function using the alternating direction method of multipliers (ADMM). Experiments on MR images of adults and pediatric subjects demonstrate that the proposed method enhances the details of the recovered high-resolution images, and outperforms the nearest-neighbor interpolation, cubic interpolation, non-local means, and TV-based up-sampling.",
author = "Feng Shi and Jian Cheng and L. Wang and Yap, {Pew Thian} and Dinggang Shen",
year = "2013",
month = "12",
day = "1",
language = "English",
volume = "16",
pages = "155--162",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
edition = "Pt 1",

}

TY - CHAP

T1 - Low-rank total variation for image super-resolution.

AU - Shi, Feng

AU - Cheng, Jian

AU - Wang, L.

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Most natural images can be approximated using their low-rank components. This fact has'been successfully exploited in recent advancements of matrix completion algorithms for image recovery. However, a major limitation of low-rank matrix completion algorithms is that they cannot recover the case where a whole row or column is missing. The missing row or column will be simply filled as an arbitrary combination of other rows or columns with known values. This precludes the application of matrix completion to problems such as super-resolution (SR) where missing values in many rows and columns need to be recovered in the process of up-sampling a low-resolution image. Moreover, low-rank regularization considers information globally from the whole image and does not take proper consideration of local spatial consistency. Accordingly, we propose in this paper a solution to the SR problem via simultaneous (global) low-rank and (local) total variation (TV) regularization. We solve the respective cost function using the alternating direction method of multipliers (ADMM). Experiments on MR images of adults and pediatric subjects demonstrate that the proposed method enhances the details of the recovered high-resolution images, and outperforms the nearest-neighbor interpolation, cubic interpolation, non-local means, and TV-based up-sampling.

AB - Most natural images can be approximated using their low-rank components. This fact has'been successfully exploited in recent advancements of matrix completion algorithms for image recovery. However, a major limitation of low-rank matrix completion algorithms is that they cannot recover the case where a whole row or column is missing. The missing row or column will be simply filled as an arbitrary combination of other rows or columns with known values. This precludes the application of matrix completion to problems such as super-resolution (SR) where missing values in many rows and columns need to be recovered in the process of up-sampling a low-resolution image. Moreover, low-rank regularization considers information globally from the whole image and does not take proper consideration of local spatial consistency. Accordingly, we propose in this paper a solution to the SR problem via simultaneous (global) low-rank and (local) total variation (TV) regularization. We solve the respective cost function using the alternating direction method of multipliers (ADMM). Experiments on MR images of adults and pediatric subjects demonstrate that the proposed method enhances the details of the recovered high-resolution images, and outperforms the nearest-neighbor interpolation, cubic interpolation, non-local means, and TV-based up-sampling.

UR - http://www.scopus.com/inward/record.url?scp=84894607594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894607594&partnerID=8YFLogxK

M3 - Chapter

C2 - 24505661

VL - 16

SP - 155

EP - 162

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -