Three-dimensional object reconstruction from multi-view images is an important topic in computer vision, which has attracted enormous attention during the past decades. With the further study in deep learning, remarkable progress of three-dimensional object reconstruct has been obtained in recent years. In this paper, we proposed three-dimensional rapid registration and reconstruction of multi-view rigid objects based on end-to-end deep surface model in the field of three-dimensional object reconstruction. Firstly, we introduce a matching algorithm called local stereo matching algorithm based on improved census transform and multi-scale spatial, aiming to improve the matching results for those regions. In cost aggregation step, guided map filtering algorithm with excellent gradient preserving property is introduced into Gaussian pyramid structure and regularization is added to strengthen cost volume consistency. Secondly, the improved inception RESNET module is added to improve the feature extraction ability of the network, and multiple features are extracted by using multiple network structures, and finally multiple features are sequentially input into the VRNN module to enhance the reconstruction effect of multi-view images. The experimental results show that our proposed method can not only achieve better reconstruction results, but also reconstruct more details and spend less time in training.

中文翻译：

---

基于端到端深面模型的多视角刚体三维快速配准与重建

从多视图图像中重建三维对象是计算机视觉中的一个重要课题，在过去的几十年中引起了极大的关注。近年来，随着深度学习的深入研究，三维对象重构取得了显着进展。在本文中，我们在三维物体重建领域提出了基于端到端深表面模型的多视图刚体三维快速配准和重建。首先，我们引入了一种基于改进的人口普查变换和多尺度空间的匹配算法，称为局部立体匹配算法，旨在改善这些区域的匹配结果。在成本聚合步骤中，在高斯金字塔结构中引入了具有优良梯度保持特性的引导图过滤算法，并加入了正则化以加强成本量的一致性。其次，加入改进的inception RESNET模块，提高网络的特征提取能力，利用多种网络结构提取多个特征，最后将多个特征依次输入VRNN模块，增强多视图的重构效果图片。实验结果表明，我们提出的方法不仅可以达到更好的重建效果，而且可以重建更多的细节，减少训练时间。加入改进的inception RESNET模块，提高网络的特征提取能力，利用多种网络结构提取多个特征，最后将多个特征依次输入VRNN模块，增强多视图图像的重建效果。实验结果表明，我们提出的方法不仅可以达到更好的重建效果，而且可以重建更多的细节，减少训练时间。加入改进的inception RESNET模块，提高网络的特征提取能力，利用多种网络结构提取多个特征，最后将多个特征依次输入VRNN模块，增强多视图图像的重建效果。实验结果表明，我们提出的方法不仅可以达到更好的重建效果，而且可以重建更多的细节，减少训练时间。