Advanced search
1 file | 193.77 KB

Single-image super-resolution using sparsity constraints and non-local similarities at multiple resolution scales

Author
Organization
Abstract
Traditional super-resolution methods produce a clean high-resolution image from several observed degraded low-resolution images following an acquisition or degradation model. Such a model describes how each output pixel is related to one or more input pixels and it is called data fidelity term in the regularization framework. Additionally, prior knowledge such as piecewise smoothness can be incorporated to improve the image restoration result. The impact of an observed pixel on the restored pixels is thus local according to the degradation model and the prior knowledge. Therefore, the traditional methods only exploit the spatial redundancy in a local neighborhood and are therefore referred to as local methods. Recently, non-local methods, which make use of similarities between image patches across the whole image, have gained popularity in image restoration in general. In super-resolution literature they are often referred to as exemplar-based methods. In this paper, we exploit the similarity of patches within the same scale (which is related to the class of non-local methods) and across different resolution scales of the same image (which is also related to the fractal-based methods). For patch fusion, we employ a kernel regression algorithm, which yields a blurry and noisy version of the desired high-resolution image. For the final reconstruction step, we develop a novel restoration algorithm. The joint deconvolution/denoising algorithm is based on the split Bregman iterations and, as prior knowledge, the algorithm exploits the sparsity of the image in the shearlet-transformed domain. Initial results indicate an improvement over both classical local and state-of-the art non-local super-resolution methods.
Keywords
image restoration, exemplar-based methods, super-resolution literature, single-image super-resolution, super-resolution methods, piecewise smoothness, deconvolution algorithm, kernel regression algorithm, split Bregman iterations, denoising algorithm, patch fusion, fractal-based methods

Downloads

  • hluong photonics2010.pdf
    • full text
    • |
    • PDF
    • |
    • 193.77 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Luong, Hiep, Tijana Ruzic, Aleksandra Pizurica, and Wilfried Philips. 2010. “Single-image Super-resolution Using Sparsity Constraints and Non-local Similarities at Multiple Resolution Scales.” In Proceedings of the Society of Photo-optical Instrumentation Engineers (spie), ed. Peter Schelkens, Touradj Ebrahimi, Gabriel Cristóbal, Frédéric Truchetet, and Pasi Saarikko. Vol. 7723. Bellingham, WA, USA: SPIE, the International Society for Optical Engineering.
APA
Luong, Hiep, Ruzic, T., Pizurica, A., & Philips, W. (2010). Single-image super-resolution using sparsity constraints and non-local similarities at multiple resolution scales. In Peter Schelkens, T. Ebrahimi, G. Cristóbal, F. Truchetet, & P. Saarikko (Eds.), PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE) (Vol. 7723). Presented at the Optics, Photonics, and Digital Technologies for Multimedia Applications (SPIE Photonics Europe), Bellingham, WA, USA: SPIE, the International Society for Optical Engineering.
Vancouver
1.
Luong H, Ruzic T, Pizurica A, Philips W. Single-image super-resolution using sparsity constraints and non-local similarities at multiple resolution scales. In: Schelkens P, Ebrahimi T, Cristóbal G, Truchetet F, Saarikko P, editors. PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE). Bellingham, WA, USA: SPIE, the International Society for Optical Engineering; 2010.
MLA
Luong, Hiep, Tijana Ruzic, Aleksandra Pizurica, et al. “Single-image Super-resolution Using Sparsity Constraints and Non-local Similarities at Multiple Resolution Scales.” Proceedings of the Society of Photo-optical Instrumentation Engineers (spie). Ed. Peter Schelkens et al. Vol. 7723. Bellingham, WA, USA: SPIE, the International Society for Optical Engineering, 2010. Print.
@inproceedings{1061996,
  abstract     = {Traditional super-resolution methods produce a clean high-resolution image from several observed degraded low-resolution images following an acquisition or degradation model. Such a model describes how each output pixel is related to one or more input pixels and it is called data fidelity term in the regularization framework. Additionally, prior knowledge such as piecewise smoothness can be incorporated to improve the image restoration result. The impact of an observed pixel on the restored pixels is thus local according to the degradation model and the prior knowledge. Therefore, the traditional methods only exploit the spatial redundancy in a local neighborhood and are therefore referred to as local methods. Recently, non-local methods, which make use of similarities between image patches across the whole image, have gained popularity in image restoration in general. In super-resolution literature they are often referred to as exemplar-based methods. In this paper, we exploit the similarity of patches within the same scale (which is related to the class of non-local methods) and across different resolution scales of the same image (which is also related to the fractal-based methods). For patch fusion, we employ a kernel regression algorithm, which yields a blurry and noisy version of the desired high-resolution image. For the final reconstruction step, we develop a novel restoration algorithm. The joint deconvolution/denoising algorithm is based on the split Bregman iterations and, as prior knowledge, the algorithm exploits the sparsity of the image in the shearlet-transformed domain. Initial results indicate an improvement over both classical local and state-of-the art non-local super-resolution methods.},
  articleno    = {772305},
  author       = {Luong, Hiep and Ruzic, Tijana and Pizurica, Aleksandra and Philips, Wilfried},
  booktitle    = {PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE)},
  editor       = {Schelkens, Peter and Ebrahimi, Touradj and Crist{\'o}bal, Gabriel and Truchetet, Fr{\'e}d{\'e}ric and Saarikko, Pasi},
  isbn         = {9780819481962},
  issn         = {0277-786X},
  keyword      = {image restoration,exemplar-based methods,super-resolution literature,single-image super-resolution,super-resolution methods,piecewise smoothness,deconvolution algorithm,kernel regression algorithm,split Bregman iterations,denoising algorithm,patch fusion,fractal-based methods},
  language     = {eng},
  location     = {Brussels, Belgium},
  pages        = {8},
  publisher    = {SPIE, the International Society for Optical Engineering},
  title        = {Single-image super-resolution using sparsity constraints and non-local similarities at multiple resolution scales},
  url          = {http://dx.doi.org/10.1117/12.854437},
  volume       = {7723},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: