Presentation | 2023-10-27 User-adaptable Avatar Posture Manipulation Riku Shinohara, Atsushi Hashimoto, Tadashi Kozuno, Shigeo Yoshida, Monica Perusquia-Hernandez, Yutaro Hirao, Hideaki Uchiyama, Kiyokawa Kiyoshi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, we propose a system for acquiring a method of manipulating the avatar posture using the user's hands. In order to manipulate an avatar with different physical characteristics from the hand, a mapping between the joints of the hand and the avatar is required. In conventional methods, this mapping is performed by optimization based on mathematical formulas designed from the viewpoint of biomechanics. However, it is difficult to obtain the optimal operation method for each user with this method. Therefore, we investigate a method to obtain user-optimized avatar operations by using data-based machine learning. An encoder-decoder model is used for machine learning, and user-optimized avatar operations are acquired in two stages: pre-learning and additional learning. For the additional learning, we used a small amount of data obtained from the user's calibration work. We evaluated two types of avatars: a scorpion, for which there is a difference in operation between users, and a frog, for which there is no difference between users. As a result, we found that the proposed model is effective even when there is a difference in operation between users. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Avatar Manipulation / Hand Avatar / Non-humanoid Avatar / Machine Learning / User Adaptation |
Paper # | MVE2023-29 |
Date of Issue | 2023-10-19 (MVE) |
Conference Information | |
Committee | MVE / VRSJ-SIG-MR / IPSJ-EC / HI-SIG-DeMO / VRSJ-SIG-CS |
---|---|
Conference Date | 2023/10/26(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kiyoshi Kiyokawa(NAIST) |
Vice Chair | Sumaru Niida(KDDI Research) |
Secretary | Sumaru Niida(NAIST) / (DNP) / (Kyushu Univ.) / (NTT) |
Assistant | Hidehiko Shishido(Univ. of Tsukuba) / Atsushi Nakazawa(Kyoto Univ.) / Naoya Tojo(KDDI Research) / Naoki Hagiyama(NTT) / Yuji Tatada(Univ. of Tokyo) |
Paper Information | |
Registration To | Technical Committee on Media Experience and Virtual Environment / SIG-MR / Special Interest Group on Entertainment Computing / Special Interest Group on De-vice Media Oriented UI / SIG-CS |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | User-adaptable Avatar Posture Manipulation |
Sub Title (in English) | |
Keyword(1) | Avatar Manipulation |
Keyword(2) | Hand Avatar |
Keyword(3) | Non-humanoid Avatar |
Keyword(4) | Machine Learning |
Keyword(5) | User Adaptation |
1st Author's Name | Riku Shinohara |
1st Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
2nd Author's Name | Atsushi Hashimoto |
2nd Author's Affiliation | OMRON SINIC X Corporation(OSX) |
3rd Author's Name | Tadashi Kozuno |
3rd Author's Affiliation | OMRON SINIC X Corporation(OSX) |
4th Author's Name | Shigeo Yoshida |
4th Author's Affiliation | OMRON SINIC X Corporation(OSX) |
5th Author's Name | Monica Perusquia-Hernandez |
5th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
6th Author's Name | Yutaro Hirao |
6th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
7th Author's Name | Hideaki Uchiyama |
7th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
8th Author's Name | Kiyokawa Kiyoshi |
8th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
Date | 2023-10-27 |
Paper # | MVE2023-29 |
Volume (vol) | vol.123 |
Number (no) | MVE-228 |
Page | pp.pp.40-45(MVE), |
#Pages | 6 |
Date of Issue | 2023-10-19 (MVE) |