arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1905.03079cs.CV
收藏

3D说话风格的捕捉、学习和合成

Capture, Learning, and Synthesis of 3D Speaking Styles

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Daniel Cudeiro, Timo Bolkart, Cassidy Laidlaw, Anurag Ranjan, Michael J. Black

摘要:

音频驱动的3D人脸动画已经得到了广泛的探索,但实现逼真的,像人一样的表现仍然是一个悬而未决的问题。这是由于缺乏可用的3D数据集、模型和标准评估指标。为了解决这个问题,我们引入了一个独特的4D人脸数据集,其中包含以60 fps捕获的约29分钟的4D扫描和来自12个扬声器的同步音频。然后,我们在我们的数据集上训练一个神经网络,该网络从面部运动中识别身份。学习模型VOCA(Voice Operated Character Animation,语音操作角色动画)将任何语音信号作为输入--甚至是英语以外的语言--并逼真地动画化各种成人面孔。在训练过程中对主题标签的条件反射允许模型学习各种现实的说话风格。VOCA还提供动画师控制,以改变说话风格,身份依赖的面部形状和姿势(即头部,下巴和眼球旋转)在动画。据我们所知,VOCA是唯一一个逼真的3D面部动画模型,它可以很容易地应用于看不见的主题,而无需重定向。这使得VOCA适用于游戏视频、虚拟现实化身或任何事先不知道说话者、语音或语言的场景。我们在http://voca.is.tue.mpg.de上提供数据集和模型用于研究目的。

英文摘要:

Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input - even speech in languages other than English - and realistically animates a wide range of adult faces. Conditioning on subject labels during training allows the model to learn a variety of realistic speaking styles. VOCA also provides animator controls to alter speaking style, identity-dependent facial shape, and pose (i.e. head, jaw, and eyeball rotations) during animation. To our knowledge, VOCA is the only realistic 3D facial animation model that is readily applicable to unseen subjects without retargeting. This makes VOCA suitable for tasks like in-game video, virtual reality avatars, or any scenario in which the speaker, speech, or language is not known in advance. We make the dataset and model available for research purposes at http://voca.is.tue.mpg.de.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑