论文标题
弱监督的3D人体姿势和形状重建，并通过标准化流量
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
论文作者
论文摘要
由于人体的自由度和缺乏人的自由度，可以在复杂的视觉场景中获取大规模监督学习，因此单眼3D人类的姿势和形状估计是具有挑战性的。在本文中，我们介绍了实用的半监督和自我监督的模型，这些模型支持训练和在现实世界中的图像和视频中进行良好的概括。我们的表述基于运动潜在的标准化流程表示和动力学，以及支持自我监督学习的可区分的，语义的身体部分比对损失函数。在使用3D运动捕获数据集（如CMU，Human3.6M，3DPW或Amass）以及Coco等图像存储库（例如COCO）等3D运动捕获数据集中进行的广泛实验，我们表明，所提出的方法优于最新技术，从而支持了基于多样化和不完整的图像和视频数据的大型模型培训的精确培训的实际构建。
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes. In this paper we present practical semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions that support self-supervised learning. In extensive experiments using 3D motion capture datasets like CMU, Human3.6M, 3DPW, or AMASS, as well as image repositories like COCO, we show that the proposed methods outperform the state of the art, supporting the practical construction of an accurate family of models based on large-scale training with diverse and incompletely labeled image and video data.
