| Presentation | 2020-12-18 Super resolution for sea surface temperature with CNN and GAN Tomoki Izumi, Motoki Amagasaki, Kei Ishida, Masato Kiyama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we use the deep neural networks (DNN)-based single image super-resolution (SISR) method for the super resolution of sea surface temperature data. By using state of the art DNN technology, we are able to generate high quality super-resolution data. In this evaluation, generated images are compared to OISST with the root mean square error (RMSE) and Learned Perceptual Image Patch Similarity (LPIPS) and Perceptual Index(PI). RRDBNet has a better RMSE than SRCNN and ESRGAN. On the other hand, CNN-based SISR model is not a faithful representation of the ocean currents of OISST. ESRGAN can represent the complex distribution of ocean currents. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Single Image Super-Resolution / Convolutional Neural Network / Generative Adversarial Network / RRDBNet / ESRGAN |
| Paper # | NC2020-28 |
| Date of Issue | 2020-12-11 (NC) |
| Conference Information | |
| Committee | MBE / NC |
|---|---|
| Conference Date | 2020/12/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Takashi Watanabe(Tohoku Univ.) / Kazuyuki Samejima(Tamagawa Univ) |
| Vice Chair | Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) |
| Secretary | Ryuhei Okuno(Akita-noken) / Rieko Osu(NTT) |
| Assistant | Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Ken Takiyama(TUAT) / Nobuhiko Wagatsuma(Toho Univ.) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Super resolution for sea surface temperature with CNN and GAN |
| Sub Title (in English) | |
| Keyword(1) | Single Image Super-Resolution |
| Keyword(2) | Convolutional Neural Network |
| Keyword(3) | Generative Adversarial Network |
| Keyword(4) | RRDBNet |
| Keyword(5) | ESRGAN |
| 1st Author's Name | Tomoki Izumi |
| 1st Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 2nd Author's Name | Motoki Amagasaki |
| 2nd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 3rd Author's Name | Kei Ishida |
| 3rd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 4th Author's Name | Masato Kiyama |
| 4th Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| Date | 2020-12-18 |
| Paper # | NC2020-28 |
| Volume (vol) | vol.120 |
| Number (no) | NC-302 |
| Page | pp.pp.1-6(NC), |
| #Pages | 6 |
| Date of Issue | 2020-12-11 (NC) |