Human body shape reconstruction from binary silhouette images
Human body shape reconstruction from binary silhouette images
复制标题
从二值轮廓图像重建人体形状
DOI：
10.1016/j.cagd.2019.04.019
复制
发表时间：
2019-05-01
影响因子：
1.5
通讯作者：
Wu, Qing
中科院分区：
文献类型：
--
作者：
Ji, Zhongping;Qi, Xiao;Wu, Qing
3D内容创建被称为计算机图形学最基本的任务之一。在过去的几十年中，已经开发了许多基于二维图像或曲线的三维建模算法。设计师可以从正面、侧面和顶视图对齐一些概念图像或绘制一些暗示性曲线，然后将它们用作手动或半自动构建3D模型的参考。在本文中，我们提出了一种基于深度学习的从2D正投影轮廓图像重建3D人体形状的方法。设计了一种基于CNN的回归网络，该网络具有两个分支，分别对应于正面和侧面视图，用于从二值轮廓图像中估计三维人体形状。我们分别训练我们的网络，以解耦对来自不同视图的身体参数进行编码的特征描述符，并将它们融合以估计准确的人体形状。此外，为了克服训练数据的不足，我们提出了一些显着的三维人体形状的数据增强方案，这可以用来促进这一主题的进一步研究。大量的实验结果表明，视觉上逼真和准确的重建，可以有效地实现使用我们的算法。该方法只需要一个或两个轮廓图像，就可以帮助用户快速创建自己的数字化身，也可以很容易地创建数字人体的3D游戏，虚拟现实，网上时尚购物。(C)2019 Elsevier B.V.版权所有。
3D content creation is referred to as one of the most fundamental tasks of computer graphics. And many 3D modeling algorithms from 2D images or curves have been developed over the past several decades. Designers are allowed to align some conceptual images or sketch some suggestive curves, from front, side, and top views, and then use them as references in constructing a 3D model manually or semi-automatically. In this paper, we propose a deep learning based reconstruction of 3D human body shape from 2D orthographic silhouette images. A CNN-based regression network, with two branches corresponding to frontal and lateral views respectively, is designed for estimating 3D human body shape from binary silhouette images. We train our networks separately to decouple the feature descriptors which encode the body parameters from different views, and fuse them to estimate an accurate human body shape. In addition, to overcome the shortage of training data required for this purpose, we propose some significantly data augmentation schemes for 3D human body shapes, which can be used to promote further research on this topic. Extensive experimental results demonstrate that visually realistic and accurate reconstructions can be achieved effectively using our algorithm. Requiring only one or two silhouette images, our method can help users create their own digital avatars quickly, and also make it easy to create digital human body for 3D game, virtual reality, online fashion shopping. (C) 2019 Elsevier B.V. All rights reserved.