Schops Thomas, Sattler Torsten, Pollefeys Marc
IEEE Trans Pattern Anal Mach Intell. 2019 Oct 14. doi: 10.1109/TPAMI.2019.2947048.
We address the problem of mesh reconstruction from live RGB-D video, assuming a calibrated camera and poses provided externally (e.g., by a SLAM system). In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud. We asynchronously (re)triangulate the smoothed surfels to reconstruct a surface mesh. This novel approach enables to maintain a dense surface representation of the scene during SLAM which can quickly adapt to loop closures. This is possible by deforming the surfel cloud and asynchronously remeshing the surface where necessary. The surfel-based representation also naturally supports strongly varying scan resolution. In particular, it reconstructs colors at the input camera's resolution. Moreover, in contrast to many volumetric approaches, ours can reconstruct thin objects since objects do not need to enclose a volume. We demonstrate our approach in a number of experiments, showing that it produces reconstructions that are competitive with the state-of-the-art, and we discuss its advantages and limitations. The algorithm (excluding loop closure functionality) is available as open source at https://github.com/puzzlepaint/surfelmeshing.
我们解决从实时RGB-D视频进行网格重建的问题，假设相机已校准且外部提供了姿态（例如，由SLAM系统提供）。与大多数现有方法不同，我们不是在体素中融合深度测量值，而是在密集的表面点云（surfel cloud）中进行融合。我们异步地（重新）三角剖分平滑后的表面点，以重建表面网格。这种新颖的方法能够在SLAM过程中保持场景的密集表面表示，从而可以快速适应回环闭合。这通过使表面点云变形并在必要时异步地重新网格化表面来实现。基于表面点的表示还自然地支持变化很大的扫描分辨率。特别是，它以输入相机的分辨率重建颜色。此外，与许多体素方法不同，我们的方法可以重建薄物体，因为物体不需要包围一个体素。我们在一些实验中展示了我们的方法，表明它产生的重建结果与现有技术具有竞争力，并且我们讨论了其优点和局限性。该算法（不包括回环闭合功能）可在https://github.com/puzzlepaint/surfelmeshing上作为开源代码获取。
