mlsanityData to 14 Oct 2026

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

arXiv 2210.02299 ↗First posted 5 Oct 2022cs.CV cs.LG cs.ROcited by 44

Not on the map. Why?

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.

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

23 of 42 references.

References · 23

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  6. 2020Convolutional Occupancy Networkscited by 761
  7. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  8. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  9. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  10. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  11. 2021Neural RGB-D Surface Reconstructioncited by 313
  12. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
11 more
  1. 2019ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residualscited by 181
  2. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 150
  3. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  4. 2022Neural 3D Reconstruction in the Wildcited by 79
  5. 2020DI-Fusion: Online Implicit 3D Reconstruction with Deep Priorscited by 70
  6. 2020The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truthcited by 61
  7. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  8. 2021Range Image-based LiDAR Localization for Autonomous Vehiclescited by 25
  9. 2018OVPC Mesh: 3D Free-space Representation for Local Ground Vehicle Navigationcited by 7
  10. 2017Semantic Segmentation from Limited Training Datacited by 5
  11. 2017Safe Local Exploration for Replanning in Cluttered Unknown Environments for Micro-Aerial Vehiclescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 21; 2025: 10; 2026: 6.

44 papers.

Sort:

By area:

  1. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  2. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  3. 2023NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mappingcited by 41
  4. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  5. 2024SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspectioncited by 14
  6. 2025HiMo: High-Speed Objects Motion Compensation in Point Cloudscited by 12
  7. 2025PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Mapcited by 10
  8. 20243D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representationcited by 8
  9. 2025GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstructioncited by 8
  10. 2026Flow Equivariant World Models: Memory for Partially Observed Dynamic Environmentscited by 8
  11. 2024Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mappingcited by 6
  12. 2024Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAMcited by 6
32 more
  1. 2024MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenescited by 6
  2. 2023Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Modelscited by 5
  3. 2024PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environmentscited by 5
  4. 2024SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Datasetcited by 4
  5. 2025Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mappingcited by 4
  6. 2023PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environmentscited by 3
  7. 2024OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mappingcited by 3
  8. 2024Neural Surface Reconstruction and Rendering for LiDAR-Visual Systemscited by 3
  9. 2025SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantificationcited by 3
  10. 2023Empir3D : A Framework for Multi-Dimensional Point Cloud Assessmentcited by 1
  11. 2024STAIR: Semantic-Targeted Active Implicit Reconstructioncited by 1
  12. 2024Neural Implicit Representation for Highly Dynamic LiDAR Mapping and Odometrycited by 1
  13. 2024Neural Semantic Map-Learning for Autonomous Vehiclescited by 1
  14. 2024NeRF-enabled Analysis-Through-Synthesis for ISAR Imaging of Small Everyday Objects with Sparse and Noisy UWB Radar Datacited by 1
  15. 2024A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fieldscited by 1
  16. 2026LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstructioncited by 1
  17. 2023LISNeRF Mapping: LiDAR-based Implicit Mapping via Semantic Neural Fields for Large-Scale 3D Scenescited by 0
  18. 2023VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesiscited by 0
  19. 2024DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mappingcited by 0
  20. 2024LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updatingcited by 0
  21. 2024UAV-based Intelligent Information Systems on Winter Road Safety for Autonomous Vehiclescited by 0
  22. 2024Decomposition of Neural Discrete Representations for Large-Scale 3D Mappingcited by 0
  23. 2024CCNDF: Curvature Constrained Neural Distance Fields from 3D LiDAR Sequencescited by 0
  24. 2025LiLMaps: Learnable Implicit Language Mapscited by 0
  25. 2025KN-LIO: Geometric Kinematics and Neural Field Coupled LiDAR-Inertial Odometrycited by 0
  26. 2025HessianForge: Scalable LiDAR reconstruction with Physics-Informed Neural Representation and Smoothness Energy Constraintscited by 0
  27. 2025Multi-Representation Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognitioncited by 0
  28. 2025XGrid-Mapping: Explicit Implicit Hybrid Grid Submaps for Efficient Incremental Neural LiDAR Mappingcited by 0
  29. 2026G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localizationcited by 0
  30. 2026LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fieldscited by 0
  31. 2026AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyondcited by 0
  32. 2026Real-Time LiDAR Gaussian Splatting SLAMcited by 0