mlsanityData to 7 Oct 2026

Loopy-SLAM: Dense Neural SLAM with Loop Closures

arXiv 2402.09944 ↗First posted 14 Feb 2024cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization And Mapping (SLAM), yet face challenges such as error accumulation during camera tracking resulting in distorted maps. In response, we introduce Loopy-SLAM that globally optimizes poses and the dense 3D model. We use frame-to-model tracking using a data-driven point-based submap generation method and trigger loop closures online by performing global place recognition. Robust pose graph optimization is used to rigidly align the local submaps. As our representation is point based, map corrections can be performed efficiently without the need to store the entire history of input frames used for mapping as typically required by methods employing a grid based mapping structure. Evaluation on the synthetic Replica and real-world TUM-RGBD and ScanNet datasets demonstrate competitive or superior performance in tracking, mapping, and rendering accuracy when compared to existing dense neural RGBD SLAM methods. Project page: notchla.github.io/Loopy-SLAM.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 43 of its 78 references that are in the map. First posted on arXiv 14 Feb 2024.

Builds on

43 of 78 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  6. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  7. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  8. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  9. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  10. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  11. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  12. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
31 more
  1. 2021Neural RGB-D Surface Reconstructioncited by 312
  2. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  3. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  4. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  5. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  6. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
  7. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  8. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  9. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  10. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  11. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  12. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 148
  13. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  14. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  15. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 107
  16. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  17. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  18. 2020DI-Fusion: Online Implicit 3D Reconstruction with Deep Priorscited by 70
  19. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  20. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  21. 2020NeuralFusion: Online Depth Fusion in Latent Spacecited by 46
  22. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  23. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  24. 2021VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusioncited by 38
  25. 2020Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submapscited by 26
  26. 2023MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstructioncited by 24
  27. 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
  28. 2022FD-SLAM: 3-D Reconstruction Using Features and Dense Matchingcited by 17
  29. 2023NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAMcited by 17
  30. 2017Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstructioncited by 12
  31. 2022Learning Online Multi-Sensor Depth Fusioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 19; 2026: 10.

48 papers.

Sort:

  1. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100
  2. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  3. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 64
  4. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
  5. 2024GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAMcited by 36
  6. 2024Compact 3D Gaussian Splatting For Dense Visual SLAMcited by 24
  7. 2024MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesiscited by 22
  8. 2024Neural Radiance Field in Autonomous Driving: A Surveycited by 19
  9. 2025RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenescited by 16
  10. 2024High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimizationcited by 15
  11. 2024DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splattingcited by 15
  12. 2025DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Priorcited by 14
36 more
  1. 2024MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAMcited by 12
  2. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  3. 2025VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenescited by 12
  4. 2025SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embeddingcited by 11
  5. 2025Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and Mappingcited by 11
  6. 2025MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representationcited by 11
  7. 2025Gaussian-Plus-SDF SLAM: High-fidelity 3D Reconstruction at 150+ fpscited by 11
  8. 2024MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularizationcited by 10
  9. 2024EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping Systemcited by 9
  10. 2025VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussianscited by 8
  11. 2024CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAMcited by 7
  12. 2025HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAMcited by 6
  13. 2025DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representationscited by 6
  14. 2024MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstructioncited by 5
  15. 2025Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mappingcited by 4
  16. 2025GRAND-SLAM: Local Optimization for Globally Consistent Large-Scale Multi-Agent Gaussian SLAMcited by 4
  17. 2024Neural Graph Map: Dense Mapping with Efficient Loop Closure Integrationcited by 3
  18. 2024Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstructioncited by 3
  19. 2025LEGO-SLAM: Language-Embedded Gaussian Optimization SLAMcited by 3
  20. 2026VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAMcited by 3
  21. 2025Deblur Gaussian Splatting SLAMcited by 2
  22. 2026The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Modelscited by 2
  23. 2026Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directionscited by 2
  24. 2025TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraintscited by 1
  25. 2026PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAMcited by 1
  26. 2026SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMcited by 1
  27. 2026Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistencycited by 1
  28. 2024An Earth Rover dataset recorded at the ICRA@40 partycited by 0
  29. 2024XRDSLAM: A Flexible and Modular Framework for Deep Learning based SLAMcited by 0
  30. 2025ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integrationcited by 0
  31. 2025ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAMcited by 0
  32. 2025SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Renderingcited by 0
  33. 2026MipSLAM: Alias-Free Gaussian Splatting SLAMcited by 0
  34. 2026DINO-VO: Learning Where to Focus for Enhanced State Estimationcited by 0
  35. 2026LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closurecited by 0
  36. 2026HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understandingcited by 0