H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Chenxing, Luo, Yiming, Zhou, Boyu, Shen, Shaojie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929421675397120
author Jiang, Chenxing
Luo, Yiming
Zhou, Boyu
Shen, Shaojie
author_facet Jiang, Chenxing
Luo, Yiming
Zhou, Boyu
Shen, Shaojie
contents 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 for our method will be available at: https://github.com/SYSU-STAR/H3-Mapping.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation
Jiang, Chenxing
Luo, Yiming
Zhou, Boyu
Shen, Shaojie
Robotics
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 for our method will be available at: https://github.com/SYSU-STAR/H3-Mapping.
title H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation
topic Robotics
url https://arxiv.org/abs/2403.10821