TL;DR本文提出了一种新算法,将迭代梯度下降和深度神经网络结合起来,实现 3D 人体形状与图像的拟合。该算法只需人体动作捕捉数据,不需要图像到 3D 对应关系,并且在公共数据集上达到了最先进的结果。
Abstract
We propose a novel algorithm for the fitting of 3D human shape to images.
Combining the accuracy and refinement capabilities of iterative gradient-based
optimization techniques with the robustness of deep neural networks, we propose
a gradient descent algorithm that leverages a neural