arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.12287cs.CV
收藏

Body2Hands:学习从会话手势身体动力学推断3D手部

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics

UC Berkeley(加州大学伯克利分校);Facebook AI Research(Facebook人工智能研究院)

Evonne Ng, Shiry Ginosar, Trevor Darrell, Hanbyul Joo

摘要:

我们提出了一种新的学习身体运动的深度先验的3D手形合成和估计领域的会话手势。我们的模型建立在这样一种见解之上,即身体运动和手势在非语言交流环境中是密切相关的。我们制定了学习这个先验知识作为一个预测任务的3D手的形状随着时间的推移,单独的身体运动输入。通过从大规模互联网视频数据集获得的3D姿势估计进行训练,我们的手部预测模型仅以说话者手臂的3D运动作为输入,即可产生令人信服的3D手势。我们证明了我们的方法从身体运动输入的手势合成的功效,并作为一个强大的身体之前,基于单视图图像的3D手姿态估计。我们证明,我们的方法优于以前的国家的最先进的方法,可以推广到基于独白的训练数据以外的多人对话。视频结果可在http://people.eecs.berkeley.edu/~evonne_ng/projects/body2hands/上获得。

英文摘要:

We propose a novel learned deep prior of body motion for 3D hand shape synthesis and estimation in the domain of conversational gestures. Our model builds upon the insight that body motion and hand gestures are strongly correlated in non-verbal communication settings. We formulate the learning of this prior as a prediction task of 3D hand shape over time given body motion input alone. Trained with 3D pose estimations obtained from a large-scale dataset of internet videos, our hand prediction model produces convincing 3D hand gestures given only the 3D motion of the speaker's arms as input. We demonstrate the efficacy of our method on hand gesture synthesis from body motion input, and as a strong body prior for single-view image-based 3D hand pose estimation. We demonstrate that our method outperforms previous state-of-the-art approaches and can generalize beyond the monologue-based training data to multi-person conversations. Video results are available at http://people.eecs.berkeley.edu/~evonne_ng/projects/body2hands/.

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。

↑