Constructing a high-quality dense map in real-time is essential for robotics, AR/VR, and digital twins applications. As Neural Radiance Field (NeRF) greatly improves the mapping performance, in this paper, we propose a NeRF-based mapping method that enables higher-quality reconstruction and real-time capability even on edge computers. Specifically, we propose a novel hierarchical hybrid representation that leverages implicit multiresolution hash encoding aided by explicit octree SDF priors, describing the scene at different levels of detail. This representation allows for fast scene geometry initialization and makes scene geometry easier to learn. Besides, we present a coverage-maximizing keyframe selection strategy to address the forgetting issue and enhance mapping quality, particularly in marginal areas. To the best of our knowledge, our method is the first to achieve high-quality NeRF-based mapping on edge computers of handheld devices and quadrotors in real-time. Experiments demonstrate that our method outperforms existing NeRF-based mapping methods in geometry accuracy, texture realism, and time consumption. The code will be released at: https://github.com/SYSU-STAR/H2-Mapping

翻译：构建实时高质量稠密地图对于机器人、AR/VR以及数字孪生应用至关重要。鉴于神经辐射场（NeRF）显著提升了建图性能，本文提出了一种基于NeRF的建图方法，即使在边缘计算机上也能实现更高质量的重建与实时能力。具体而言，我们提出了一种新颖的层级混合表示方法，该方法利用隐式多分辨率哈希编码并辅以显式八叉树符号距离场先验，以不同细节层级描述场景。这种表示方法能够快速初始化场景几何，并使场景几何更易于学习。此外，我们提出了一种最大化覆盖的关键帧选择策略，以解决遗忘问题并提升建图质量，尤其在边缘区域效果显著。据我们所知，本方法首次实现了在手持设备与四旋翼飞行器边缘计算机上实时进行高质量的基于NeRF的建图。实验表明，本方法在几何精度、纹理真实感及时间消耗方面均优于现有基于NeRF的建图方法。代码将发布于：https://github.com/SYSU-STAR/H2-Mapping