Presentation | 2019-03-14 Multi Frame Super-Resolution Magnification method using TV Regularization and Learning-based Method Taiki Kondo, Hiroto Kizuna, Hiromasa Takeda, Hiroyuki Sato, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A method combining a Based learning method and ShockFilter for Total Variation (TV) regularization, which is one of super-resolution methods, is a super-resolution technique that realizes strong edge sharpening and reconstruction of fine patterns . However, there is a possibility that ShockFilter degrades image quality depending on the processed image, and the case learning method has a problem that the processing time becomes enormous due to a large amount of correlation calculation. These problems are applied to various images, and it is difficult to apply it to moving images etc. where real time property is required. In this research, by applying Bilateral Filter as pre-processing of ShockFilter, we realized speedup of case learning method by improving image quality degradation and using multi-frame. As a result, we succeeded in improving the image quality by not causing jaggies compared to conventional edge sharpening, and achieving a total speed of 2.8 times as fast as the conventional method, and.confirmed that it can operate sufficiently in real time moving images. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Super Resolution / TV Regularization / Based learning / ShockFilter / Multi Frame |
Paper # | IMQ2018-38,IE2018-122,MVE2018-69 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |
Conference Information | |
Committee | IMQ / IE / MVE / CQ |
---|---|
Conference Date | 2019/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kagoshima University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | media of five senses, multimedia, media experience, picture codinge, image media quality, network,quality and reliability, etc |
Chair | Kenji Sugiyama(Seikei Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Kenji Mase(Nagoya Univ.) / Takanori Hayashi(Hiroshima Inst. of Tech.) |
Vice Chair | Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT) |
Secretary | Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(Sony) / Hideaki Kimata(KDDI Research) / Kazuya Kodama(Nagoya Univ.) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(Kyushu Univ.) / Jun Okamoto(Nagoya Univ.) |
Assistant | Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK) / Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(*) / Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Ryo Yamamoto(UEC) |
Paper Information | |
Registration To | Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Communication Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Multi Frame Super-Resolution Magnification method using TV Regularization and Learning-based Method |
Sub Title (in English) | |
Keyword(1) | Super Resolution |
Keyword(2) | TV Regularization |
Keyword(3) | Based learning |
Keyword(4) | ShockFilter |
Keyword(5) | Multi Frame |
1st Author's Name | Taiki Kondo |
1st Author's Affiliation | Iwate Prefectural University(Iwate Pref. Univ.) |
2nd Author's Name | Hiroto Kizuna |
2nd Author's Affiliation | Iwate Prefectural University(Iwate Pref. Univ.) |
3rd Author's Name | Hiromasa Takeda |
3rd Author's Affiliation | Iwate Prefectural University(Iwate Pref. Univ.) |
4th Author's Name | Hiroyuki Sato |
4th Author's Affiliation | Iwate Prefectural University(Iwate Pref. Univ.) |
Date | 2019-03-14 |
Paper # | IMQ2018-38,IE2018-122,MVE2018-69 |
Volume (vol) | vol.118 |
Number (no) | IMQ-500,IE-501,MVE-502 |
Page | pp.pp.91-96(IMQ), pp.91-96(IE), pp.91-96(MVE), |
#Pages | 6 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |