Presentation | 2021-03-02 Image Generation Method Considering Aesthetics Based on Generative Adversarial Networks Yu Tajima, Chen Qiu, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The designs of various products and movie posters need to attract customers. In this paper, we propose an image generation method using Adversarial Generative Networks (GANs), so as to obtain more powerful visual effects that support the work of designers. Specifically, we first extract characteristic scenes from the video, filter them to determine the aesthetic quality of the image, and then enlarge the objects in the image and adjust their brightness. The generated images are evaluated by using MTurk. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | GANs / Video Summary / Scene Extraction / Aethetics |
Paper # | IMQ2020-27,IE2020-67,MVE2020-59 |
Date of Issue | 2021-02-22 (IMQ, IE, MVE) |
Conference Information | |
Committee | MVE / IMQ / IE / CQ |
---|---|
Conference Date | 2021/3/1(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC) |
Vice Chair | Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
Secretary | Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.) |
Assistant | Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
Paper Information | |
Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Image Generation Method Considering Aesthetics Based on Generative Adversarial Networks |
Sub Title (in English) | |
Keyword(1) | GANs |
Keyword(2) | Video Summary |
Keyword(3) | Scene Extraction |
Keyword(4) | Aethetics |
1st Author's Name | Yu Tajima |
1st Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
2nd Author's Name | Chen Qiu |
2nd Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
Date | 2021-03-02 |
Paper # | IMQ2020-27,IE2020-67,MVE2020-59 |
Volume (vol) | vol.120 |
Number (no) | IMQ-389,IE-390,MVE-391 |
Page | pp.pp.82-86(IMQ), pp.82-86(IE), pp.82-86(MVE), |
#Pages | 5 |
Date of Issue | 2021-02-22 (IMQ, IE, MVE) |