DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
复制标题
DOI：
10.1109/lra.2020.2965415
复制
发表时间：
2020-04-01
影响因子：
5.2
通讯作者：
Davison, Andrew J.
中科院分区：
文献类型：
--
作者：
Czarnowski, Jan;Laidlow, Tristan;Davison, Andrew J.
从单目图像估计丰富的几何形状和相机运动的能力是未来交互式机器人和增强现实应用的基础。已经提出了不同的方法，不同的场景几何表示（稀疏地标，密集的地图），用于优化多视图问题的一致性度量，并使用学习先验。我们提出了一个SLAM系统，统一这些方法在概率框架，同时仍然保持实时性能。这是通过使用学习的紧凑深度图表示和重新制定三种不同类型的错误来实现的：光度，重投影和几何，我们在标准因子图软件中使用这些错误。我们评估我们的系统在真实世界的序列上的轨迹估计和深度重建，并提出各种估计密集几何的例子。
The ability to estimate rich geometry and camera motion from monocular imagery is fundamental to future interactive robotics and augmented reality applications. Different approaches have been proposed that vary in scene geometry representation (sparse landmarks, dense maps), the consistency metric used for optimising the multi-view problem, and the use of learned priors. We present a SLAM system that unifies these methods in a probabilistic framework while still maintaining real-time performance. This is achieved through the use of a learned compact depth map representation and reformulating three different types of errors: photometric, reprojection and geometric, which we make use of within standard factor graph software. We evaluate our system on trajectory estimation and depth reconstruction on real-world sequences and present various examples of estimated dense geometry.