论文标题
动态密集的RGB-D大满贯使用基于学习的视觉进程
Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry
论文作者
论文摘要
我们提出了一个基于基于学习的视觉探针仪Tartanvo的密集动态RGB-D SLAM管道。与其他直接方法而不是基于特征的方法一样，tartanvo估计摄像机通过密集的光流构成，这仅适用于静态场景并无视动态对象。由于颜色恒定的假设，光流无法区分动态像素和静态像素。因此，要通过此类直接方法重建静态图，我们的管道通过利用光流量输出，仅将静态点融合到地图中来解决动态/静态分割。此外，我们将输入框架启用，以便将动态像素删除并迭代地将它们传递回视觉探光仪以完善姿势估计。
We propose a dense dynamic RGB-D SLAM pipeline based on a learning-based visual odometry, TartanVO. TartanVO, like other direct methods rather than feature-based, estimates camera pose through dense optical flow, which only applies to static scenes and disregards dynamic objects. Due to the color constancy assumption, optical flow is not able to differentiate between dynamic and static pixels. Therefore, to reconstruct a static map through such direct methods, our pipeline resolves dynamic/static segmentation by leveraging the optical flow output, and only fuse static points into the map. Moreover, we rerender the input frames such that the dynamic pixels are removed and iteratively pass them back into the visual odometry to refine the pose estimate.
