Abstract
Recent advancements in RGB-only dense Simultaneous Localization and Mapping (SLAM) have predominantly utilized grid-based neural implicit encodings and/or struggle to efficiently realize global map and pose consistency. To this end, we propose an efficient RGB-only dense SLAM system using a flexible neural point cloud scene representation that adapts to keyframe poses and depth updates, without needing costly backpropagation. Another critical challenge of RGB-only SLAM is the lack of geometric priors. To alleviate this issue, with the aid of a monocular depth estimator, we introduce a novel DSPO layer for bundle adjustment which optimizes the pose and depth of keyframes along with the scale of the monocular depth. Finally, our system benefits from loop closure and online global bundle adjustment and performs either better or competitive to existing dense neural RGB SLAM methods in tracking, mapping and rendering accuracy on the Replica, TUM-RGBD and ScanNet datasets. The source code will be made available.
Abstract (translated)
近年来,在仅使用红色-绿色-蓝色(RGB)的密集同时定位与映射(SLAM)中,主要采用了基于网格的神经隐式编码,/或努力实现全局地图和姿态一致性。为此,我们提出了一个高效利用仅红色-绿色-蓝色(RGB)的密集SLAM系统,该系统具有适应关键帧姿势和深度更新的灵活神经点云表示。另一个RGB-only SLAM的关键挑战是缺乏几何先验。为了减轻这个问题,在单目深度估计器的帮助下,我们引入了一种名为DSPO的卷积神经网络层用于捆绑调整,该层优化了关键帧的姿势和深度,同时与单目深度成比例。最后,我们的系统利用环路闭合和在线全局捆绑调整在Replica、TUM-RGBD和ScanNet数据集上的跟踪、映射和渲染准确性要么更好,要么与现有密集神经RGB SLAM方法相当。源代码将提供。
URL
https://arxiv.org/abs/2403.19549