| Presentation | 2019-03-14 [Poster Presentation] Image Super-Resolution via Generative Adversarial Network Considering Objective Quality Hiroya Yamamoto, Daichi Kitahara, Akira Hirabayashi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a super-resolution method based on a conventional technique using the generative adversarial network (GAN). The conventional method suffers from pixel-wise black or white artifacts. This is because the number of training data was not sufficient for a network with huge parameters. To solve this problem, we exploit the observation error by adding it to the conventional cost function. This guarantees the consistency for training examples, but not for a novel input data after training. Hence, we further introduce the orthogonal projection onto a linear manifold, in which the observation error is completely zero. These two ideas enable us to produce high quality super-resolution results without the artifact. Simulation results show the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image Super-Resolution / Generative Adversarial Network / Orthogonal Projection |
| Paper # | EA2018-115,SIP2018-121,SP2018-77 |
| Date of Issue | 2019-03-07 (EA, SIP, SP) |
| Conference Information | |
| Committee | EA / SIP / SP |
|---|---|
| Conference Date | 2019/3/14(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | i+Land nagasaki (Nagasaki-shi) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Engineering/Electro Acoustics, Signal Processing, Speech, and Related Topics |
| Chair | Suehiro Shimauchi(Kanazawa Inst. of Tech.) / Shogo Muramatsu(Niigata Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) |
| Vice Chair | Kenichi Furuya(Oita Univ.) / Kanji Watanabe(Akita Pref. Univ.) / Naoyuki Aikawa(TUS) / Kazunori Hayashi(Osaka City Univ) / Akinobu Ri(Nagoya Inst. of Tech.) |
| Secretary | Kenichi Furuya(Shizuoka Inst. of Science and Tech.) / Kanji Watanabe(NHK) / Naoyuki Aikawa(Takushoku Univ.) / Kazunori Hayashi(Hiroshima Univ.) / Akinobu Ri(Kyoto Univ.) |
| Assistant | Keisuke Imoto(Ritsumeikan Univ.) / Daisuke Morikawa(Toyama Pref Univ.) / Katsumi Konishi(Hosei Univ.) / hyihsin(Takushoku Univ.) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Poster Presentation] Image Super-Resolution via Generative Adversarial Network Considering Objective Quality |
| Sub Title (in English) | |
| Keyword(1) | Image Super-Resolution |
| Keyword(2) | Generative Adversarial Network |
| Keyword(3) | Orthogonal Projection |
| 1st Author's Name | Hiroya Yamamoto |
| 1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| 2nd Author's Name | Daichi Kitahara |
| 2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| 3rd Author's Name | Akira Hirabayashi |
| 3rd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| Date | 2019-03-14 |
| Paper # | EA2018-115,SIP2018-121,SP2018-77 |
| Volume (vol) | vol.118 |
| Number (no) | EA-495,SIP-496,SP-497 |
| Page | pp.pp.93-98(EA), pp.93-98(SIP), pp.93-98(SP), |
| #Pages | 6 |
| Date of Issue | 2019-03-07 (EA, SIP, SP) |