This letter proposes a novel post-processing method for self-similarity based super-resolution (SR). Existing back-projection (BP) methods enhance SR images by refining the reconstructed coarse high-frequency (HF) information. However, it causes artifacts due to interpolation and excessively smoothes small HF signals, particularly in texture regions. Motivated by these observations, we propose a novel post-processing method referred to as middle-frequency (MF) based refinement. The proposed method refines the reconstructed HF information in the MF domain rather than in the spatial domain, as in BP. In addition, it does not require an internal interpolation process, so it is free from the side-effects of interpolation. Experimental results show that the proposed algorithm provides superior performance in terms of both the quantity of reproduced HF information and the visual quality.
Jae-Hee JUN
Korea University
Ji-Hoon CHOI
Korea University
Jong-Ok KIM
Korea 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
Jae-Hee JUN, Ji-Hoon CHOI, Jong-Ok KIM, "Middle-Frequency Based Refinement for Image Super-Resolution" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 1, pp. 300-304, January 2016, doi: 10.1587/transinf.2015EDL8180.
Abstract: This letter proposes a novel post-processing method for self-similarity based super-resolution (SR). Existing back-projection (BP) methods enhance SR images by refining the reconstructed coarse high-frequency (HF) information. However, it causes artifacts due to interpolation and excessively smoothes small HF signals, particularly in texture regions. Motivated by these observations, we propose a novel post-processing method referred to as middle-frequency (MF) based refinement. The proposed method refines the reconstructed HF information in the MF domain rather than in the spatial domain, as in BP. In addition, it does not require an internal interpolation process, so it is free from the side-effects of interpolation. Experimental results show that the proposed algorithm provides superior performance in terms of both the quantity of reproduced HF information and the visual quality.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8180/_p
Copy
@ARTICLE{e99-d_1_300,
author={Jae-Hee JUN, Ji-Hoon CHOI, Jong-Ok KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Middle-Frequency Based Refinement for Image Super-Resolution},
year={2016},
volume={E99-D},
number={1},
pages={300-304},
abstract={This letter proposes a novel post-processing method for self-similarity based super-resolution (SR). Existing back-projection (BP) methods enhance SR images by refining the reconstructed coarse high-frequency (HF) information. However, it causes artifacts due to interpolation and excessively smoothes small HF signals, particularly in texture regions. Motivated by these observations, we propose a novel post-processing method referred to as middle-frequency (MF) based refinement. The proposed method refines the reconstructed HF information in the MF domain rather than in the spatial domain, as in BP. In addition, it does not require an internal interpolation process, so it is free from the side-effects of interpolation. Experimental results show that the proposed algorithm provides superior performance in terms of both the quantity of reproduced HF information and the visual quality.},
keywords={},
doi={10.1587/transinf.2015EDL8180},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Middle-Frequency Based Refinement for Image Super-Resolution
T2 - IEICE TRANSACTIONS on Information
SP - 300
EP - 304
AU - Jae-Hee JUN
AU - Ji-Hoon CHOI
AU - Jong-Ok KIM
PY - 2016
DO - 10.1587/transinf.2015EDL8180
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2016
AB - This letter proposes a novel post-processing method for self-similarity based super-resolution (SR). Existing back-projection (BP) methods enhance SR images by refining the reconstructed coarse high-frequency (HF) information. However, it causes artifacts due to interpolation and excessively smoothes small HF signals, particularly in texture regions. Motivated by these observations, we propose a novel post-processing method referred to as middle-frequency (MF) based refinement. The proposed method refines the reconstructed HF information in the MF domain rather than in the spatial domain, as in BP. In addition, it does not require an internal interpolation process, so it is free from the side-effects of interpolation. Experimental results show that the proposed algorithm provides superior performance in terms of both the quantity of reproduced HF information and the visual quality.
ER -