| Presentation | 2021-01-21 [Invited Talk] GAN-based Image Coding Methods for Maximizing Subjective Image Quality Shinobu Kudo, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The increasing image resolution and the spread of IoT devices require more efficient video storage and transmission systems. Conventional image quality evaluation criteria such as peak signal-to-noise ratio and structural similarity are based on the difference of signal values. In order to improve the coding efficiency, a method based on a new evaluation criteria has been proposed, where that allows the data to be different from the original signal value if there is no subjective visual discomfort. Inthis paper, we introduce our generative adversarial networks (GAN)-based image coding methods for maximizing subjective image quality. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image coding / Deep learning / Generative adversarial networks / Subjective image quality |
| Paper # | IE2020-37 |
| Date of Issue | 2021-01-14 (IE) |
| Conference Information | |
| Committee | IE |
|---|---|
| Conference Date | 2021/1/21(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Image Processing, Image Coding, etc |
| Chair | Hideaki Kimata(NTT) |
| Vice Chair | Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) |
| Secretary | Kazuya Kodama(KDDI Research) / Keita Takahashi(Nagoya Inst. of Tech.) |
| Assistant | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Image Engineering |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] GAN-based Image Coding Methods for Maximizing Subjective Image Quality |
| Sub Title (in English) | |
| Keyword(1) | Image coding |
| Keyword(2) | Deep learning |
| Keyword(3) | Generative adversarial networks |
| Keyword(4) | Subjective image quality |
| 1st Author's Name | Shinobu Kudo |
| 1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2021-01-21 |
| Paper # | IE2020-37 |
| Volume (vol) | vol.120 |
| Number (no) | IE-329 |
| Page | pp.pp.9-13(IE), |
| #Pages | 5 |
| Date of Issue | 2021-01-14 (IE) |