| Presentation | 2020-12-17 Synthesize talking anime-heads images by tunneling through human-heads domain Shun Fujiuchi, Ryo Hachiuma, Kunihiro Hasegawa, Hideo Saito, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Avatars are widely used on the Internet to establish non-verbal communication without exposing one's physical identity. In order to accomplish effective avatar-based communication, it is important that avatars reflect user's facial expression precisely. In this work, we propose a method to drive a single anime-face image by user's talking-heads video to synthesize talking anime-heads images. Our method takes an anime-like face image and a real-world speaker's head image as input, and generates an anime-like speaker's head image when the input anime-like face image is moved in the same way as the input head image. In order to validate the effectiveness of the proposed method, we present the results of qualitative evaluation experiments of the generation results of the proposed method and quantitative comparison with the generation results using the First Order Motion Model as a baseline method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image Animation / Image-to-Image Translation / anime-like face image / dataset normalization |
| Paper # | PRMU2020-39 |
| Date of Issue | 2020-12-10 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2020/12/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Transfer learning and few shot learning |
| Chair | Yoichi Sato(Univ. of Tokyo) |
| Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
| Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
| Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Synthesize talking anime-heads images by tunneling through human-heads domain |
| Sub Title (in English) | |
| Keyword(1) | Image Animation |
| Keyword(2) | Image-to-Image Translation |
| Keyword(3) | anime-like face image |
| Keyword(4) | dataset normalization |
| 1st Author's Name | Shun Fujiuchi |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Ryo Hachiuma |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| 3rd Author's Name | Kunihiro Hasegawa |
| 3rd Author's Affiliation | Keio University(Keio Univ.) |
| 4th Author's Name | Hideo Saito |
| 4th Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2020-12-17 |
| Paper # | PRMU2020-39 |
| Volume (vol) | vol.120 |
| Number (no) | PRMU-300 |
| Page | pp.pp.7-11(PRMU), |
| #Pages | 5 |
| Date of Issue | 2020-12-10 (PRMU) |