# SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations

arXiv: https://arxiv.org/abs/2210.02299 · HTML: https://mlsanity.com/paper/2210.02299/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 5 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning](https://mlsanity.com/paper/1611.03631/) (2016)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [Neural 3D Reconstruction in the Wild](https://mlsanity.com/paper/2205.12955/) (2022)
- [DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors](https://mlsanity.com/paper/2012.05551/) (2020)
- [The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth](https://mlsanity.com/paper/2003.05691/) (2020)
- [GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction](https://mlsanity.com/paper/2206.14735/) (2022)
- [Range Image-based LiDAR Localization for Autonomous Vehicles](https://mlsanity.com/paper/2105.12121/) (2021)
- [OVPC Mesh: 3D Free-space Representation for Local Ground Vehicle Navigation](https://mlsanity.com/paper/1811.10266/) (2018)
- [Semantic Segmentation from Limited Training Data](https://mlsanity.com/paper/1709.07665/) (2017)
- [Safe Local Exploration for Replanning in Cluttered Unknown Environments for Micro-Aerial Vehicles](https://mlsanity.com/paper/1710.00604/) (2017)

## Built on by (most cited first, 30 of 44)

- [vMAP: Vectorised Object Mapping for Neural Field SLAM](https://mlsanity.com/paper/2302.01838/) (2023)
- [PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency](https://mlsanity.com/paper/2401.09101/) (2024)
- [NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping](https://mlsanity.com/paper/2303.10709/) (2023)
- [DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2409.18092/) (2024)
- [SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection](https://mlsanity.com/paper/2403.06877/) (2024)
- [HiMo: High-Speed Objects Motion Compensation in Point Clouds](https://mlsanity.com/paper/2503.00803/) (2025)
- [PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map](https://mlsanity.com/paper/2502.05752/) (2025)
- [3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation](https://mlsanity.com/paper/2405.03388/) (2024)
- [GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction](https://mlsanity.com/paper/2503.10170/) (2025)
- [Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments](https://mlsanity.com/paper/2601.01075/) (2026)
- [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)
- [MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.04026/) (2024)
- [Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Models](https://mlsanity.com/paper/2309.10900/) (2023)
- [PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments](https://mlsanity.com/paper/2402.09325/) (2024)
- [SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset](https://mlsanity.com/paper/2410.21739/) (2024)
- [Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping](https://mlsanity.com/paper/2503.17491/) (2025)
- [PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments](https://mlsanity.com/paper/2310.00874/) (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)
- [SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification](https://mlsanity.com/paper/2502.02657/) (2025)
- [Empir3D : A Framework for Multi-Dimensional Point Cloud Assessment](https://mlsanity.com/paper/2306.03660/) (2023)
- [STAIR: Semantic-Targeted Active Implicit Reconstruction](https://mlsanity.com/paper/2403.11233/) (2024)
- [Neural Implicit Representation for Highly Dynamic LiDAR Mapping and Odometry](https://mlsanity.com/paper/2409.17729/) (2024)
- [Neural Semantic Map-Learning for Autonomous Vehicles](https://mlsanity.com/paper/2410.07780/) (2024)
- [NeRF-enabled Analysis-Through-Synthesis for ISAR Imaging of Small Everyday Objects with Sparse and Noisy UWB Radar Data](https://mlsanity.com/paper/2410.10085/) (2024)
- [A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields](https://mlsanity.com/paper/2411.01725/) (2024)
- [LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction](https://mlsanity.com/paper/2603.12647/) (2026)
- [LISNeRF Mapping: LiDAR-based Implicit Mapping via Semantic Neural Fields for Large-Scale 3D Scenes](https://mlsanity.com/paper/2311.02313/) (2023)
- [VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis](https://mlsanity.com/paper/2311.05289/) (2023)

## Abstract (arXiv)

Accurate mapping of large-scale environments is an essential building block of most outdoor autonomous systems. Challenges of traditional mapping methods include the balance between memory consumption and mapping accuracy. This paper addresses the problem of achieving large-scale 3D reconstruction using implicit representations built from 3D LiDAR measurements. We learn and store implicit features through an octree-based, hierarchical structure, which is sparse and extensible. The implicit features can be turned into signed distance values through a shallow neural network. We leverage binary cross entropy loss to optimize the local features with the 3D measurements as supervision. Based on our implicit representation, we design an incremental mapping system with regularization to tackle the issue of forgetting in continual learning. Our experiments show that our 3D reconstructions are more accurate, complete, and memory-efficient than current state-of-the-art 3D mapping methods.