In this paper, we introduce FMapping, an efficient neural field mapping framework that facilitates the continuous estimation of a colorized point cloud map in real-time dense RGB SLAM. To achieve this challenging goal without depth, a hurdle is how to improve efficiency and reduce the mapping uncertainty of the RGB SLAM system. To this end, we first build up a theoretical analysis by decomposing the SLAM system into tracking and mapping parts, and the mapping uncertainty is explicitly defined within the frame of neural representations. Based on the analysis, we then propose an effective factorization scheme for scene representation and introduce a sliding window strategy to reduce the uncertainty for scene reconstruction. Specifically, we leverage the factorized neural field to decompose uncertainty into a lower-dimensional space, which enhances robustness to noise and improves training efficiency. We then propose the sliding window sampler to reduce uncertainty by incorporating coherent geometric cues from observed frames during map initialization to enhance convergence. Our factorized neural mapping approach enjoys some advantages, such as low memory consumption, more efficient computation, and fast convergence during map initialization. Experiments on two benchmark datasets show that our method can update the map of high-fidelity colorized point clouds around 2 seconds in real time while requiring no customized CUDA kernels. Additionally, it utilizes x20 fewer parameters than the most concise neural implicit mapping of prior methods for SLAM, e.g., iMAP [ 31] and around x1000 fewer parameters than the state-of-the-art approach, e.g., NICE-SLAM [ 42]. For more details, please refer to our project homepage: https://vlis2022.github.io/fmap/.

翻译：本文提出FMapping，一种高效的神经场建图框架，可实现实时稠密RGB SLAM中彩色点云地图的连续估计。在不依赖深度信息实现这一挑战性目标的过程中，核心难题在于如何提升效率并降低RGB SLAM系统的建图不确定性。为此，我们首先通过将SLAM系统解耦为跟踪与建图两部分进行理论分析，并在神经表示框架下明确定义建图不确定性。基于该分析，我们提出一种高效的场景表示分解方案，并引入滑动窗口策略以降低场景重建的不确定性。具体而言，我们利用分解式神经场将不确定性降至低维空间，从而增强对噪声的鲁棒性并提升训练效率；进而提出滑动窗口采样器，通过在初始化阶段融合观测帧中的连贯几何先验来降低不确定性，加速收敛。所提出的分解式神经建图方法具备低内存消耗、高效计算及初始化快速收敛等优势。在两个基准数据集上的实验表明，本方法可在无需定制CUDA内核的情况下，以约2秒的实时速度更新高保真彩色点云地图。此外，其参数量仅为当前SLAM方法中最简洁的神经隐式建图方案（如iMAP [31]）的1/20，以及最先进方法（如NICE-SLAM [42]）的约1/1000。更多详情请参见项目主页：https://vlis2022.github.io/fmap/。