IEEE RAL投稿。主要作者：@JCX- @账号已注销
简介：近年来，隐式在线稠密建图方法实现了高质量的重建效果，在机器人技术、增强现实/虚拟现实以及数字孪生应用中展现出巨大潜力。然而，现有方法在纹理重建方面的缓慢处理速度限制了它们的实时性能。为了解决这些限制，我们提出了一种基于NeRF的稠密建图方法，能够实现更快速和更高质量的重建。为了提高纹理建模能力，我们引入了准异构特征网格，它继承了均匀特征网格快速查询的能力，同时能够适应不同水平的纹理复杂性。此外，我们提出了一种梯度辅助的覆盖最大化策略用于关键帧选择，这使得选定的关键帧能够更加集中地关注纹理丰富的区域，同时对于纹理较弱的区域具有更广的覆盖范围。实验结果表明，我们的方法在纹理保真度、几何精度和时间消耗方面超越了现有的基于NeRF的方法。代码将会开源：https://github.com/SYSU-STAR/H3-Mapping
In recent years, implicit online dense mapping methods have achieved high-quality reconstruction results, showcasing great potential in robotics, AR/VR, and digital twins applications. However, existing methods struggle with slow texture modeling which limits their real-time performance. To address these limitations, we propose a NeRF-based dense mapping method that enables faster and higher-quality reconstruction. To improve texture modeling, we introduce quasiheterogeneous feature grids, which inherit the fast querying ability of uniform feature grids while adapting to varying levels of texture complexity. Besides, we present a gradientaided coverage-maximizing strategy for keyframe selection that enables the selected keyframes to exhibit a closer focus on richtextured regions and a broader scope for weak-textured areas. Experimental results demonstrate that our method surpasses existing NeRF-based approaches in texture fidelity, geometry accuracy, and time consumption.
