RAL Best Paper, H2-Mapping：使用分层混合表征的实时稠密建图 IEEE RAL
合作者：@JCX- @瀚文文文问问 @中山大学RAPID机器人Lab
Preprint：https://arxiv.org/abs/2306.03207
实时构建高质量的密集地图对于机器人技术、AR/VR 和数字孪生应用至关重要。 由于神经辐射场 (NeRF) 极大地提高了建图性能，在本文中，我们提出了一种基于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和实时能力。 具体来说，我们提出了一种新颖的分层混合表示，它利用显式八叉树 SDF 先验辅助的隐式多分辨率哈希编码，以不同的细节级别描述场景。 这种表示允许快速场景几何初始化，并使场景几何更容易学习。 此外，我们提出了一种覆盖最大化的关键帧选择策略来解决遗忘问题并提高建图质量，特别是在边缘区域。 据我们所知，我们的方法是第一个在手持设备和四旋翼飞行器的边缘计算机上实时实现基于 NeRF 的高质量建图的方法。 实验表明，我们的方法在几何精度、纹理真实性和时间消耗方面优于现有的基于 NeRF 的建图方法。 代码将在 \url{https://github.com/SYSU-STAR/H2-Mapping} 发布。
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 \url{https://github.com/SYSU-STAR/H2-Mapping}.
南方科技大学助理教授，博导；微分智飞联合创始人；TRO Best Paper一作；研究机器人/具身； robotics-star.com/
顶部