Natural and fun character action based on relevance / non-relevance with speech
| Project/Area Number |
18K11602
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 62040:Entertainment and game informatics-related
|
|---|
| Research Institution | Niigata University (2020-2021)
Yamaguchi College of Arts (2018-2019) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | キャラクタアニメーション / 発話と動作 / モーションキャプチャ / ３Dアニメーション / コンピュータアニメーション / 動作生成 / アニメキャラクタ |
|---|
| Outline of Final Research Achievements |
We considered the strength of the connection between action and reaction and the strength of the connection between speeches and movements towards a new production method of animation. First, if the action and reaction are strongly connected, the movements must be strongly related to the speeches. On the other hand, if the connection between action and reaction weak due to the content of the dialogue, actions unrelated to the speeches are better. The familiar movement tends to be favored among unrelated movements. In addition, people who perform actions unrelated to speech contents are often psychologically strong to the other person. Based on these ideas, we created an animation that switches between action related to speech and action unrelated to speech in the scenario. In order to enhance the motion database, we developed and evaluated a motion capture with pan / zoom function.
|
| Academic Significance and Societal Importance of the Research Achievements |
これまで、アニメキャラクタの動作は台詞と連動させて作られてきた。発話と動作との関連性を学習すれば、台詞から動作の自動生成が可能である。しかし、その動作は多くの動作が平均化された動作であり面白味に欠けていた。一方、演劇では、台詞と無関係で意味のない動きを俳優にさせることにより、発話の不自然さは消え、演技に面白さが生じている。本研究では、この演劇の新たな潮流をいち早くアニメの制作に取り入れたものである。この制作法には動作データベースの充実が欠かせない。カメラのパン・ズーム機能を伴ったモーションキャプチャを開発し、舞台や体育館などのような広い範囲で動き回る身体の動作測定に成功した。
|
Report
(5 results)
Research Products
(10 results)
