Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
复制标题
DOI：
10.1109/iccv.2019.00445
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Junbang Liang;M. Lin
中科院分区：
文献类型：
--
作者：
Junbang Liang;M. Lin
我们提出了一个可扩展的神经网络框架，在SMPL模型的子空间中，从多视图图像中重建人体的三维网格。使用多视点图像可以显著降低投影模糊问题，提高服装下三维人体的重建精度。我们的实验表明，该方法受益于从我们的管道生成的合成数据集，因为它具有良好的变量控制的灵活性，并可以提供地面实况验证。我们的方法优于现有的方法对现实世界的图像，特别是形状估计。
We propose a scalable neural network framework to reconstruct the 3D mesh of a human body from multi-view images, in the subspace of the SMPL model. Use of multi-view images can significantly reduce the projection ambiguity of the problem, increasing the reconstruction accuracy of the 3D human body under clothing. Our experiments show that this method benefits from the synthetic dataset generated from our pipeline since it has good flexibility of variable control and can provide ground-truth for validation. Our method outperforms existing methods on real-world images, especially on shape estimations.