| Presentation | 2017-06-02 Quantitative evaluation method of the reality of CG images using deep learning Masaaki Sato, Masataka Imura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | With the development of 3DCG technology, to express various objects and phenomena became possible. However, there is no method for quantitatively evaluating the reality of the generated CG image. On the other hand, in recent years, deep learning has been widely used to demonstrate image discrimination performance beyond human beings. In this paper, we propose a framework to realize quantitative evaluation of reality of CG image by utilizing deep learning that has high image discrimination ability and report implementation results using CNN. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CG / Reality / Quantitative evaluation / Deep Learning / CNN |
| Paper # | MVE2017-10 |
| Date of Issue | 2017-05-25 (MVE) |
| Conference Information | |
| Committee | MVE / ITE-HI |
|---|---|
| Conference Date | 2017/6/1(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Univ. of Tokyo |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yoshinari Kameda(Univ. of Tsukuba) / 佐藤 雅之(北九州市大) |
| Vice Chair | Kenji Mase(Nagoya Univ.) |
| Secretary | Kenji Mase(Kyushu Univ.) / (Kyoto Univ.) |
| Assistant | Hideaki Uchiyama(Kyushu Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Group on Human Information |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Quantitative evaluation method of the reality of CG images using deep learning |
| Sub Title (in English) | |
| Keyword(1) | CG |
| Keyword(2) | Reality |
| Keyword(3) | Quantitative evaluation |
| Keyword(4) | Deep Learning |
| Keyword(5) | CNN |
| 1st Author's Name | Masaaki Sato |
| 1st Author's Affiliation | Kwansei Gakuin University(Kwansei Gakuin Univ.) |
| 2nd Author's Name | Masataka Imura |
| 2nd Author's Affiliation | Kwansei Gakuin University(Kwansei Gakuin Univ.) |
| Date | 2017-06-02 |
| Paper # | MVE2017-10 |
| Volume (vol) | vol.117 |
| Number (no) | MVE-73 |
| Page | pp.pp.173-176(MVE), |
| #Pages | 4 |
| Date of Issue | 2017-05-25 (MVE) |