基于学习的鲁棒三维射影重建

摘要

Image-based 3D reconstruction is an important research topic in computer vision. The current deep neural networks cannot effectively eliminate outliers from point correspondences across multiple images. To ad-dress this problem, a robust deep convolutional neural network is proposed to accurately recover the 3D projec-tive structure of scenes from point correspondences across multiple images. First, the network divides the input point correspondences into several different subsets, and each subset acts independently for a projective recon-struction; then, the weight of each projective reconstruction is estimated through a weight-learning layer; finally, a merging layer is activated to perform weighted summation of these different projective reconstructions to get the final robust projective reconstruction. Experimental results demonstrate both the reconstruction accuracy and strong robustness of our network.%基于图像的三维重建是计算机视觉领域中一个重要的研究主题.针对目前深度神经网络无法有效剔除多幅图像对应点中的外点的问题,提出一种鲁棒的深度卷积神经网络,用以从多幅图像对应点中准确地恢复场景的三维射影结构.该网络首先把输入的对应点分为多个不同的子集,每个子集独立地进行射影重建;然后通过权重计算层得到每个射影重建的权重;最后通过合并层对这些不同的射影重建加权求和,得到最终的鲁棒的射影重建.实验结果表明,该网络具有较高的重建精度和很强的鲁棒性.