音声を用いて生成する３次元顔動画システム

• Item type: SIG Technical Reports(1)
• 公開日: 2006-11-17
• タイトル: 音声を用いて生成する３次元顔動画システム
• タイトル / 言語: en
• タイトル: Speech-Driven 3D Facial Animation
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: 台湾大学
• 著者所属: 台湾大学
• 著者所属: 台湾大学
• 著者所属: 台湾大学
• 著者所属(英): en
• 著者所属(英): National Taiwan University
• 著者所属(英): en
• 著者所属(英): National Taiwan University
• 著者所属(英): en
• 著者所属(英): National Taiwan University
• 著者所属(英): en
• 著者所属(英): National Taiwan University
• 著者名: 陳, 炳宇; 黄, 鈞澤; 黄, 輔中; 荘, 永裕
• 著者名(英): BING-YU, CHEN; JUN-ZE, HUANG; FU-CHUNG, HUANG; YUNG-YU, CHUANG
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: It is often difficult to animate a face model speaking a specific speech. Even for professional animators it always takes a lot of time. In this paper we provide a speech-driven 3D facial animation system which allows the user to easily generate facial animations. The user only needs to give a speech as the input. The output will be a 3D facial animation relative to the input speech. There are three components in our system. The first part is the multidimensional morphable model (MMM). MMM is build from the pre-recorded training video using machine learning techniques. People can use MMM to generate realistic speech video respect to the input speech. The second part is facial tracking. Facial tracking can extract the feature points of a human subject in the synthetic speech video. The third part is Mesh-IK (mesh based inverse kinematics). Mesh-IK takes the motion of feature points as the guide to deform the 3D face models and makes the result model have the same looking in the corresponding frame of the speech video. Thus we can have a 3D facial animation as the output.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: It is often difficult to animate a face model speaking a specific speech. Even for professional animators, it always takes a lot of time. In this paper, we provide a speech-driven 3D facial animation system which allows the user to easily generate facial animations. The user only needs to give a speech as the input. The output will be a 3D facial animation relative to the input speech. There are three components in our system. The first part is the multidimensional morphable model (MMM). MMM is build from the pre-recorded training video using machine learning techniques. People can use MMM to generate realistic speech video respect to the input speech. The second part is facial tracking. Facial tracking can extract the feature points of a human subject in the synthetic speech video. The third part is Mesh-IK (mesh based inverse kinematics). Mesh-IK takes the motion of feature points as the guide to deform the 3D face models, and makes the result model have the same looking in the corresponding frame of the speech video. Thus we can have a 3D facial animation as the output.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10100541
• 書誌情報: 情報処理学会研究報告グラフィクスとCAD（CG）; 巻 2006, 号 119(2006-CG-125), p. 89-94, 発行日 2006-11-17
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会