We present an uncertainty learning framework for dense neural simultaneous localization and mapping (SLAM). Estimating pixel-wise uncertainties for the depth input of dense SLAM methods allows re-weighing the tracking and mapping losses towards image regions that contain more suitable information that is more reliable for SLAM. To this end, we propose an online framework for sensor uncertainty estimation that can be trained in a self-supervised manner from only 2D input data. We further discuss the advantages of the uncertainty learning for the case of multi-sensor input. Extensive analysis, experimentation, and ablations show that our proposed modeling paradigm improves both mapping and tracking accuracy and often performs better than alternatives that require ground truth depth or 3D. Our experiments show that we achieve a 38\% and 27\% lower absolute trajectory tracking error (ATE) on the 7-Scenes and TUM-RGBD datasets respectively. On the popular Replica dataset using two types of depth sensors, we report an 11\% F1-score improvement on RGBD SLAM compared to the recent state-of-the-art neural implicit approaches. Source code: https://github.com/kev-in-ta/UncLe-SLAM.

翻译：我们提出了一种用于密集神经同时定位与地图构建（SLAM）的不确定性学习框架。通过估计密集SLAM方法中深度输入的逐像素不确定性，可以重新权衡跟踪与建图损失，使其更倾向于图像中包含更可靠SLAM信息的区域。为此，我们提出了一种仅利用二维输入数据即可通过自监督方式训练的在线传感器不确定性估计框架，并进一步讨论了多传感器输入场景下不确定性学习的优势。大量分析、实验及消融研究表明，我们所提出的建模范式能够同时提升建图与跟踪精度，且性能通常优于需要真实深度或三维数据的替代方法。实验结果显示，在7-Scenes和TUM-RGBD数据集上，我们分别实现了38%和27%的绝对轨迹跟踪误差（ATE）降低。在采用两种深度传感器的流行Replica数据集上，与近期最先进的神经隐式方法相比，我们的RGBD SLAM的F1分数提升了11%。源代码：https://github.com/kev-in-ta/UncLe-SLAM。