| Presentation | 2019-03-15 Non-blind image deblurring using deep image prior Takanori Fujisawa, Masaaki Ikehara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Deep learning has become a major tools for image generation and image restoration. General approach for deep learning is to extract a image feature from a large number of images. Recently, a method called deep image prior has shown that a generator network has an ability to hold a image's structure and it can be used as a prior information for image restoration problem such as denoising. This paper shows that combining the convolution operation to the deep image prior achieves the image restoration such as deblurring. The simulation over standard images and kernels shows that our method can achieve more accurate image restoration compared to other image deblurring methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image deblurring / Image restoration / Deep learning |
| Paper # | IMQ2018-66,IE2018-150,MVE2018-97 |
| 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) | Non-blind image deblurring using deep image prior |
| Sub Title (in English) | |
| Keyword(1) | Image deblurring |
| Keyword(2) | Image restoration |
| Keyword(3) | Deep learning |
| 1st Author's Name | Takanori Fujisawa |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Masaaki Ikehara |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2019-03-15 |
| Paper # | IMQ2018-66,IE2018-150,MVE2018-97 |
| Volume (vol) | vol.118 |
| Number (no) | IMQ-500,IE-501,MVE-502 |
| Page | pp.pp.239-244(IMQ), pp.239-244(IE), pp.239-244(MVE), |
| #Pages | 6 |
| Date of Issue | 2019-03-07 (IMQ, IE, MVE) |