Outlier and artifact removal filters for multi-view stereo
Outlier and artifact removal filters for multi-view stereo
复制标题
用于多视图立体的异常值和伪影去除滤波器
DOI：
10.1109/icip.2018.8451348
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Kouya Yodokawa
中科院分区：
文献类型：
--
作者：
藤田 典久;小林 諒平;山口 佳樹;朴 泰祐;吉川 耕司;安部 牧人;梅村 雅之;Kouya Yodokawa
提出了一种多视点立体图像的异常点和伪影去除方法。该方法引入了三种滤波器，分别检查(i)深度图之间的一致性及其可见性，（ii）左右一致性和（iii）深度图与颜色强度之间的一致性。提出的方法可以去除PatchMatch多视点立体生成的深度图中的异常值和伪影。通过一组公开数据集和实际场景的实验，我们证明了该方法与传统方法相比具有有效的三维重建性能。
This paper proposes an outlier and artifact removal method for multiview stereo. The proposed method introduces the three filters, which check (i) consistency among depth maps and their visibility, (ii) left-right consistency and (iii) consistency between the depth map and color intensity, respectively. The proposed method removes outliers and artifacts from depth maps generated by PatchMatch Multi-View Stereo. We demonstrate that the proposed method exhibits the efficient performance on 3D reconstruction compared with conventional methods through a set of experiments using public datasets and under practical situations.