This paper presents a single image super-resolution (SR) algorithm based on self-similarity using non-local-mean (NLM) metric. In order to accurately find the best self-example even under noisy environment, NLM weight is employed as a self-similarity metric. Also, a pixel-wise soft-switching is presented to overcome an inherent drawback of conventional self-example-based SR that it seldom works for texture areas. For the pixel-wise soft-switching, an edge-oriented saliency map is generated for each input image. Here, we derived the saliency map which can be robust against noises by using a specific training. The proposed algorithm works as follows: First, auxiliary images for an input low-resolution (LR) image are generated. Second, self-examples for each LR patch are found from the auxiliary images on a block basis, and the best match in terms of self-similarity is found as the best self-example. Third, a preliminary high-resolution (HR) image is synthesized using all the self-examples. Next, an edge map and a saliency map are generated from the input LR image, and pixel-wise weights for soft-switching of the next step are computed from those maps. Finally, a super-resolved HR image is produced by soft-switching between the preliminary HR image for edges and a linearly interpolated image for non-edges. Experimental results show that the proposed algorithm outperforms state-of-the-art SR algorithms qualitatively and quantitatively.
Hui Jung LEE
Samsung Electronics Co. Ltd.
Dong-Yoon CHOI
Inha University
Kyoung Won LIM
Samsung Electronics Co. Ltd.
Byung Cheol SONG
Inha University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hui Jung LEE, Dong-Yoon CHOI, Kyoung Won LIM, Byung Cheol SONG, "A Single Image Super-Resolution Algorithm Using Non-Local-Mean Self-Similarity and Noise-Robust Saliency Map" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 7, pp. 1463-1474, July 2017, doi: 10.1587/transinf.2016EDP7291.
Abstract: This paper presents a single image super-resolution (SR) algorithm based on self-similarity using non-local-mean (NLM) metric. In order to accurately find the best self-example even under noisy environment, NLM weight is employed as a self-similarity metric. Also, a pixel-wise soft-switching is presented to overcome an inherent drawback of conventional self-example-based SR that it seldom works for texture areas. For the pixel-wise soft-switching, an edge-oriented saliency map is generated for each input image. Here, we derived the saliency map which can be robust against noises by using a specific training. The proposed algorithm works as follows: First, auxiliary images for an input low-resolution (LR) image are generated. Second, self-examples for each LR patch are found from the auxiliary images on a block basis, and the best match in terms of self-similarity is found as the best self-example. Third, a preliminary high-resolution (HR) image is synthesized using all the self-examples. Next, an edge map and a saliency map are generated from the input LR image, and pixel-wise weights for soft-switching of the next step are computed from those maps. Finally, a super-resolved HR image is produced by soft-switching between the preliminary HR image for edges and a linearly interpolated image for non-edges. Experimental results show that the proposed algorithm outperforms state-of-the-art SR algorithms qualitatively and quantitatively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7291/_p
Copy
@ARTICLE{e100-d_7_1463,
author={Hui Jung LEE, Dong-Yoon CHOI, Kyoung Won LIM, Byung Cheol SONG, },
journal={IEICE TRANSACTIONS on Information},
title={A Single Image Super-Resolution Algorithm Using Non-Local-Mean Self-Similarity and Noise-Robust Saliency Map},
year={2017},
volume={E100-D},
number={7},
pages={1463-1474},
abstract={This paper presents a single image super-resolution (SR) algorithm based on self-similarity using non-local-mean (NLM) metric. In order to accurately find the best self-example even under noisy environment, NLM weight is employed as a self-similarity metric. Also, a pixel-wise soft-switching is presented to overcome an inherent drawback of conventional self-example-based SR that it seldom works for texture areas. For the pixel-wise soft-switching, an edge-oriented saliency map is generated for each input image. Here, we derived the saliency map which can be robust against noises by using a specific training. The proposed algorithm works as follows: First, auxiliary images for an input low-resolution (LR) image are generated. Second, self-examples for each LR patch are found from the auxiliary images on a block basis, and the best match in terms of self-similarity is found as the best self-example. Third, a preliminary high-resolution (HR) image is synthesized using all the self-examples. Next, an edge map and a saliency map are generated from the input LR image, and pixel-wise weights for soft-switching of the next step are computed from those maps. Finally, a super-resolved HR image is produced by soft-switching between the preliminary HR image for edges and a linearly interpolated image for non-edges. Experimental results show that the proposed algorithm outperforms state-of-the-art SR algorithms qualitatively and quantitatively.},
keywords={},
doi={10.1587/transinf.2016EDP7291},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - A Single Image Super-Resolution Algorithm Using Non-Local-Mean Self-Similarity and Noise-Robust Saliency Map
T2 - IEICE TRANSACTIONS on Information
SP - 1463
EP - 1474
AU - Hui Jung LEE
AU - Dong-Yoon CHOI
AU - Kyoung Won LIM
AU - Byung Cheol SONG
PY - 2017
DO - 10.1587/transinf.2016EDP7291
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2017
AB - This paper presents a single image super-resolution (SR) algorithm based on self-similarity using non-local-mean (NLM) metric. In order to accurately find the best self-example even under noisy environment, NLM weight is employed as a self-similarity metric. Also, a pixel-wise soft-switching is presented to overcome an inherent drawback of conventional self-example-based SR that it seldom works for texture areas. For the pixel-wise soft-switching, an edge-oriented saliency map is generated for each input image. Here, we derived the saliency map which can be robust against noises by using a specific training. The proposed algorithm works as follows: First, auxiliary images for an input low-resolution (LR) image are generated. Second, self-examples for each LR patch are found from the auxiliary images on a block basis, and the best match in terms of self-similarity is found as the best self-example. Third, a preliminary high-resolution (HR) image is synthesized using all the self-examples. Next, an edge map and a saliency map are generated from the input LR image, and pixel-wise weights for soft-switching of the next step are computed from those maps. Finally, a super-resolved HR image is produced by soft-switching between the preliminary HR image for edges and a linearly interpolated image for non-edges. Experimental results show that the proposed algorithm outperforms state-of-the-art SR algorithms qualitatively and quantitatively.
ER -