权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Creating Expressive Three-Dimensional Talking Faces

创建富有表现力的三维说话面孔

基本信息

批准号：
EP/D049075/1
负责人：
Barry-John Theobald
金额：
$ 14.63万
依托单位：
University of East Anglia
依托单位国家：
英国
项目类别：
Research Grant
财政年份：
2006
资助国家：
英国
起止时间：
2006 至无数据
项目状态：
已结题

来源：
https://gtr.ukri.org/projects?ref=EP%2FD049075%2F1
关键词：
Creating Expressive Three Dimensional Talking

项目摘要

The broad aim of this work is to develop a life-like expressive talking head. This is difficult to achieve as we are extremely sensitive to subtle changes in the features of the face. Flaws in animated sequences are easy to detect and severely degrade the perceived quality of the output. This is especially true for systems that strive for videorealism (indistinguishable from real video).All previous approaches that achieve close to videorealism areimage-based and two-dimensional; the pose of the character is always face-on, emotion is usually ignored, and the vocabulary is often limited. This work will overcome, for the first time, all of these limitations.To generate realistic animated sequences, a user need only supply the text (or voice) of the sentence they wish to animate. Contrast this with animation studios, such as Pixar, that require months (or years) of manual tuning of animation parameters to create realistic animated sequences. Of course, these sequences are limited to the script of the movie - to generate further sequences would require further manual specification of the parameters. This system will generate expressive visual speech for any arbitrary utterance from the limited training data available, without the need for user intervention. Also, a user can specify a desired expression, e.g. a happy expression for good news, and the output will automatically be adapted to that expression.

这项工作的广泛目标是培养一个栩栩如生、富有表现力的会说话的脑袋。这是很难实现的，因为我们对面部特征的细微变化非常敏感。动画序列中的缺陷很容易检测到，并严重降低输出的感知质量。对于努力追求视频真实感(与真实视频难以区分)的系统来说尤其如此。以前所有接近视频真实感的方法都是基于图像和二维的；角色的姿势总是面对面的，情感通常被忽略，词汇量往往有限。这项工作将第一次克服所有这些限制。要生成逼真的动画序列，用户只需提供他们希望动画的句子的文本(或语音)。这与皮克斯等动画工作室形成对比，后者需要数月(或数年)的手动调整动画参数才能创建逼真的动画序列。当然，这些序列仅限于电影剧本--要生成更多的序列，需要进一步手动指定参数。该系统将从有限的可用训练数据中为任意发声生成富有表现力的视觉语音，而不需要用户干预。此外，用户可以指定期望的表达，例如好消息的快乐表达，并且输出将自动适应该表达。