mlsanityData to 14 Oct 2026

Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping

arXiv 2503.17491 ↗First posted 21 Mar 2025cs.RO cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times. In this work, we build on recent advancements in Gaussian Splatting methods to develop a novel LiDAR odometry and mapping pipeline that exclusively relies on Gaussian primitives for its scene representation. Leveraging spherical projection, we drive the refinement of the primitives uniquely from LiDAR measurements. Experiments show that our approach matches the current registration performance, while achieving SOTA results for mapping tasks with minimal GPU requirements. This efficiency makes it a strong candidate for further exploration and potential adoption in real-time robotics estimation tasks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

36 of 55 references.

References · 36

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  4. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  5. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  6. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  7. 2023Gaussian Splatting SLAMcited by 415
  8. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  9. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  10. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  11. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 150
  12. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
24 more
  1. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66
  2. 2019LO-Net: Deep Real-time Lidar Odometrycited by 60
  3. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
  4. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  5. 2022SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representationscited by 44
  6. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  7. 2023NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mappingcited by 41
  8. 2021CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closurecited by 38
  9. 2024GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAMcited by 36
  10. 2020PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimizationcited by 35
  11. 2024LIV-GaussMap: LiDAR-Inertial-Visual Fusion for Real-time 3D Radiance Field Map Renderingcited by 28
  12. 2021Multi-Camera LiDAR Inertial Extension to the Newer College Datasetcited by 17
  13. 2024VBR: A Vision Benchmark in Romecited by 16
  14. 2023LONER: LiDAR Only Neural Representations for Real-Time SLAMcited by 15
  15. 2024LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splattingcited by 15
  16. 2023SLAMesh: Real-time LiDAR Simultaneous Localization and Meshingcited by 13
  17. 2025GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splattingcited by 13
  18. 2021Real-time Multi-Adaptive-Resolution-Surfel 6D LiDAR Odometry using Continuous-time Trajectory Optimizationcited by 9
  19. 2021Efficient LiDAR Odometry for Autonomous Drivingcited by 7
  20. 2024MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenescited by 6
  21. 2022MD-SLAM: Multi-cue Direct SLAMcited by 5
  22. 2024N3-Mapping: Normal Guided Neural Non-Projective Signed Distance Fields for Large-scale 3D Mappingcited by 4
  23. 2024MAD-ICP: It Is All About Matching Data -- Robust and Informed LiDAR Odometrycited by 4
  24. 2023Photometric LiDAR and RGB-D Bundle Adjustmentcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Benchmarking PhD-Level Coding in 3D Geometric Computer Visioncited by 2
  2. 2026RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustmentcited by 1
  3. 2026Real-Time LiDAR Gaussian Splatting SLAMcited by 0
  4. 2026SplatLabel: Pseudo-Labelling through 4D Gaussian Splattingcited by 0