XGrid-Mapping: Explicit Implicit Hybrid Grid Submaps for Efficient Incremental Neural LiDAR Mapping

TL;DR

The paper tackles real-time large-scale incremental LiDAR mapping by addressing the inefficiencies of dense implicit representations and gaps in conventional voxel-based fusion. It introduces XGrid-Mapping, a submap-based hybrid grid that combines an explicit sparse grid with an implicit dense grid, augmented by dynamic removal, overlap alignment, and key-scan replay to ensure cross-submap consistency. Training uses narrow-band sampling and a vertex-driven hash-grid representation with losses including $L_{bce}$ and $L_{eik}$, plus a distillation objective for cross-submap coherence. Experiments on Maicity, Newer College, and KITTI reveal real-time performance around $0.3$ s per frame and superior mapping quality compared with state-of-the-art baselines, demonstrating scalability and robustness for outdoor autonomous perception.

Abstract

Large-scale incremental mapping is fundamental to the development of robust and reliable autonomous systems, as it underpins incremental environmental understanding with sequential inputs for navigation and decision-making. LiDAR is widely used for this purpose due to its accuracy and robustness. Recently, neural LiDAR mapping has shown impressive performance; however, most approaches rely on dense implicit representations and underutilize geometric structure, while existing voxel-guided methods struggle to achieve real-time performance. To address these challenges, we propose XGrid-Mapping, a hybrid grid framework that jointly exploits explicit and implicit representations for efficient neural LiDAR mapping. Specifically, the strategy combines a sparse grid, providing geometric priors and structural guidance, with an implicit dense grid that enriches scene representation. By coupling the VDB structure with a submap-based organization, the framework reduces computational load and enables efficient incremental mapping on a large scale. To mitigate discontinuities across submaps, we introduce a distillation-based overlap alignment strategy, in which preceding submaps supervise subsequent ones to ensure consistency in overlapping regions. To further enhance robustness and sampling efficiency, we incorporate a dynamic removal module. Extensive experiments show that our approach delivers superior mapping quality while overcoming the efficiency limitations of voxel-guided methods, thereby outperforming existing state-of-the-art mapping methods.

Figures (9)

• Figure 1: Our mapping result and time efficiency on KITTI 07. Boxes in different colors indicate different submaps created by our framework. Compared with NeRF-LOAM, our method achieves over 25× speed-up and reaches real-time performance.
• Figure 2: Comparison of voxel-guided and dense sampling. Brown cells denote sampled voxels, blue cells denote occupancy, and light cells denote unknown free space. Left: voxel-guided sampling with structural priors, ray traversal is guided by known occupancy, thus samples are concentrated near surfaces. Right: dense sampling without priors, where queries are spread along the ray for free space learning.
• Figure 3: Overview of our 3D mapping pipeline. Sequential LiDAR scans with poses are processed by a submap module that manages submap creation and updates. For scans within an existing submap, the system performs normal mapping with dynamic removal and hybrid grid training. When a new submap is created, an additional overlap alignment module enforces cross-map consistency. Finally, the learned submaps are replayed with key-scans and fused into a global mesh for accurate and efficient large-scale reconstruction.
• Figure 4: Illustration of the hybrid grid training strategy. Top: narrow-band sampling in the explicit sparse grid, where black arrows indicate rays and red dots denote sampled points, combined with an implicit dense grid for scene representation. Bottom: training performs on voxel vertices (black), where multiscale embeddings are concatenated into vertex features, interpolated to sample points, and passed through an MLP to predict SDF values, optimized with two loss terms.
• Figure 5: Illustration of overlap map distillation strategy. The upper part illustrates the overlapping region between the old and new submaps, while the lower part shows a point within the overlapping area, where the information of well-trained voxels are used to constrain the learning of voxels in the new submap.