# H2-Mapping: Real-time Dense Mapping Using Hierarchical Hybrid Representation

arXiv: https://arxiv.org/abs/2306.03207 · HTML: https://mlsanity.com/paper/2306.03207/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2023.

## Built on by (most cited first, 23 of 23)

- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting](https://mlsanity.com/paper/2410.21955/) (2024)
- [NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding](https://mlsanity.com/paper/2407.20853/) (2024)
- [PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views](https://mlsanity.com/paper/2410.18979/) (2024)
- [NeRF Director: Revisiting View Selection in Neural Volume Rendering](https://mlsanity.com/paper/2406.08839/) (2024)
- [NID-SLAM: Neural Implicit Representation-based RGB-D SLAM in dynamic environments](https://mlsanity.com/paper/2401.01189/) (2024)
- [GS-LIVO: Real-Time LiDAR, Inertial, and Visual Multi-sensor Fused Odometry with Gaussian Mapping](https://mlsanity.com/paper/2501.08672/) (2025)
- [GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction](https://mlsanity.com/paper/2503.10170/) (2025)
- [Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps](https://mlsanity.com/paper/2403.12536/) (2024)
- [Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping](https://mlsanity.com/paper/2401.03203/) (2024)
- [Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM](https://mlsanity.com/paper/2403.19473/) (2024)
- [SO-NeRF: Active View Planning for NeRF using Surrogate Objectives](https://mlsanity.com/paper/2312.03266/) (2023)
- [OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping](https://mlsanity.com/paper/2408.17223/) (2024)
- [Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems](https://mlsanity.com/paper/2409.05310/) (2024)
- [Distributed NeRF Learning for Collaborative Multi-Robot Perception](https://mlsanity.com/paper/2409.20289/) (2024)
- [LCP-Fusion: A Neural Implicit SLAM with Enhanced Local Constraints and Computable Prior](https://mlsanity.com/paper/2411.03610/) (2024)
- [Multi-robot autonomous 3D reconstruction using Gaussian splatting with Semantic guidance](https://mlsanity.com/paper/2412.02249/) (2024)
- [OREN: Octree Residual Network for Real-Time Euclidean Signed Distance Mapping](https://mlsanity.com/paper/2510.18999/) (2025)
- [From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs](https://mlsanity.com/paper/2607.19306/) (2026)
- [MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representations](https://mlsanity.com/paper/2403.17765/) (2024)
- [XGrid-Mapping: Explicit Implicit Hybrid Grid Submaps for Efficient Incremental Neural LiDAR Mapping](https://mlsanity.com/paper/2512.20976/) (2025)
- [Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstruction](https://mlsanity.com/paper/2605.26616/) (2026)
- [UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction](https://mlsanity.com/paper/2608.02145/) (2026)

## Abstract (arXiv)

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: https://github.com/SYSU-STAR/H2-Mapping