Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation
Chenxing Jiang*, Yiming Luo, Boyu Zhou †, Shaojie Shen
Submitted to IEEE Robotics and Automation Letters 2024
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 quasi-heterogeneous feature grids, which inherit the fast querying ability of uniform feature grids while adapting to varying levels of texture complexity. Besides, we present a gradient-aided coverage-maximizing strategy for keyframe selection that enables the selected keyframes to exhibit a closer focus on rich-textured 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.
The code will coming soon ~.
You can contact the author through email: cjiangan@connect.ust.hk and zhouby23@mail.sysu.edu.cn
If you find our work useful, please consider citing:
@article{jiang2024h3,
title={H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation},
author={Jiang, Chenxing and Luo, Yiming and Zhou, Boyu and Shen, Shaojie},
journal={arXiv preprint arXiv:2403.10821},
year={2024}
}