Real-time volumetric reconstruction of Manhattan indoor scenes from depth sequences
Real-time volumetric reconstruction of Manhattan indoor scenes from depth sequences
复制标题
根据深度序列实时重建曼哈顿室内场景
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
W. Sheng
中科院分区：
文献类型：
--
作者：
Mahdi Yazdanpour;Guoliang Fan;W. Sheng
我们提出了一种高效的 3D 建模方法，以支持基于 RGB-D 相机捕获的顺序深度序列的室内场景的实时体积重建。具体来说，我们希望减少由于深度数据中的噪声和异常值而导致的连续 ICP 配准的累积误差。我们利用在大多数室内场景中有效的曼哈顿框架假设，可用于促进大规模 3D 表面配准。在我们的方法中，从每个深度帧中提取曼哈顿帧，并将其用于平面到平面的帧对齐，以初始化点到平面 ICP 表面配准。包括 LIDAR 地面实况数据在内的三个不同室内数据集的实验结果证明了所提出的算法相对于原始基于 ICP 的体积重建方法的优势。
We propose an efficient 3D modeling method to support real-time volumetric reconstruction of indoor scenes based on sequential depth sequences captured from a RGB-D camera. Specifically, we want to reduce the cumulative error from sequential ICP registration due to noise and outliers in the depth data. We take advantage of the Manhattan frame assumption valid in most indoor scenes that can be used to facilitate large scale 3D surface registration. In our approach, the Manhattan frame is extracted from each depth frame and used for plane-to-plane frame alignment to initialize point-to-plane ICP surface registration. Experimental results on three different indoor datasets including LIDAR ground-truth data demonstrate the advantages of the proposed algorithm over the original ICP-based approaches to volumetric reconstruction.
影响因子：
6.2
作者：
Niessner, Matthias;Zollhoefer, Michael;Stamminger, Marc
通讯作者：
Stamminger, Marc