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

arXiv: https://arxiv.org/abs/2403.10821 · HTML: https://mlsanity.com/paper/2403.10821/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 16 Mar 2024.

## Built on by (most cited first, 3 of 3)

- [ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting](https://mlsanity.com/paper/2410.21955/) (2024)
- [GS-LIVO: Real-Time LiDAR, Inertial, and Visual Multi-sensor Fused Odometry with Gaussian Mapping](https://mlsanity.com/paper/2501.08672/) (2025)
- [OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping](https://mlsanity.com/paper/2408.17223/) (2024)

## Abstract (arXiv)

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.