Accurate multi-view reconstruction using robust binocular stereo and surface meshing
Accurate multi-view reconstruction using robust binocular stereo and surface meshing
复制标题
DOI：
10.1109/cvpr.2008.4587792
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
D. Bradley;T. Boubekeur;W. Heidrich
中科院分区：
文献类型：
--
作者：
D. Bradley;T. Boubekeur;W. Heidrich
本文提出了一种精度高、效率高的多视点重建算法。该方法基于鲁棒双目立体匹配，然后对合并的点云进行自适应点滤波，以及高效、高质量的网格生成。我们方法的所有方面都被设计成随着视图的数量而高度可扩展。根据Middlebury数据集，我们的技术在当前算法中为稀疏的视点产生最准确的结果。此外，对于相同的数据集，我们证明了它是非gpu算法中最有效的方法。最后，我们的尺度窗口匹配技术也擅长于重建具有高曲率表面的可变形物体，我们用一些例子证明了这一点。
This paper presents a new algorithm for multi-view reconstruction that demonstrates both accuracy and efficiency. Our method is based on robust binocular stereo matching, followed by adaptive point-based filtering of the merged point clouds, and efficient, high-quality mesh generation. All aspects of our method are designed to be highly scalable with the number of views. Our technique produces the most accurate results among current algorithms for a sparse number of viewpoints according to the Middlebury datasets. Additionally, we prove to be the most efficient method among non-GPU algorithms for the same datasets. Finally, our scaled-window matching technique also excels at reconstructing deformable objects with high-curvature surfaces, which we demonstrate with a number of examples.