mlsanityData to 14 Oct 2026

Point-SLAM: Dense Neural Point Cloud-based SLAM

arXiv 2304.04278 ↗First posted 9 Apr 2023cs.CVcited by 160

Not on the map. Why?

Abstract (arXiv)

We propose a dense neural simultaneous localization and mapping (SLAM) approach for monocular RGBD input which anchors the features of a neural scene representation in a point cloud that is iteratively generated in an input-dependent data-driven manner. We demonstrate that both tracking and mapping can be performed with the same point-based neural scene representation by minimizing an RGBD-based re-rendering loss. In contrast to recent dense neural SLAM methods which anchor the scene features in a sparse grid, our point-based approach allows dynamically adapting the anchor point density to the information density of the input. This strategy reduces runtime and memory usage in regions with fewer details and dedicates higher point density to resolve fine details. Our approach performs either better or competitive to existing dense neural RGBD SLAM methods in tracking, mapping and rendering accuracy on the Replica, TUM-RGBD and ScanNet datasets. The source code is available at https://github.com/eriksandstroem/Point-SLAM.

Key facts. Cited by 160 papers in the map (data through 14 Oct 2026). Builds on 51 of its 86 references that are in the map. First posted on arXiv 9 Apr 2023.

Builds on

51 of 86 references.

References · 51

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
38 more
  1. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  2. 2020Convolutional Occupancy Networkscited by 761
  3. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  4. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  5. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  6. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  7. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  8. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  9. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  10. 2021Neural RGB-D Surface Reconstructioncited by 313
  11. 2021Urban Radiance Fieldscited by 263
  12. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  13. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  14. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  15. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  16. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
  17. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  18. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 150
  19. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  20. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  21. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  22. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 106
  23. 2018DS-SLAM: A Semantic Visual SLAM towards Dynamic Environmentscited by 91
  24. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  25. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  26. 2020DI-Fusion: Online Implicit 3D Reconstruction with Deep Priorscited by 70
  27. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  28. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  29. 2020NeuralFusion: Online Depth Fusion in Latent Spacecited by 46
  30. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  31. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  32. 2021VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusioncited by 38
  33. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  34. 2022BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusioncited by 29
  35. 2023CATNIPS: Collision Avoidance Through Neural Implicit Probabilistic Scenescited by 20
  36. 2022FD-SLAM: 3-D Reconstruction Using Features and Dense Matchingcited by 17
  37. 2022MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priorscited by 17
  38. 2020DeepSurfels: Learning Online Appearance Fusioncited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 63; 2025: 56; 2026: 31.

160 papers.

Sort:

By area:

  1. 2023Gaussian Splatting SLAMcited by 415
  2. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  3. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  4. 2024A Survey on 3D Gaussian Splattingcited by 224
  5. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  6. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 141
  7. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102
  8. 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 87
  9. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  10. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66
  11. 2024RGBD GS-ICP SLAMcited by 65
  12. 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
38 more
  1. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
  2. 2024GeoGaussian: Geometry-aware Gaussian Splatting for Scene Renderingcited by 52
  3. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  4. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  5. 2024SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAMcited by 42
  6. 2024GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAMcited by 36
  7. 2024EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splattingcited by 33
  8. 2024Spectrally Pruned Gaussian Fields with Neural Compensationcited by 33
  9. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
  10. 2024Compact 3D Gaussian Splatting For Dense Visual SLAMcited by 25
  11. 2024GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyondcited by 25
  12. 2024HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstructioncited by 25
  13. 2023DNS SLAM: Dense Neural Semantic-Informed SLAMcited by 23
  14. 2024MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesiscited by 22
  15. 2025Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmapscited by 22
  16. 2024GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusioncited by 20
  17. 2024Neural Radiance Field in Autonomous Driving: A Surveycited by 19
  18. 2024NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understandingcited by 19
  19. 2023Implicit Event-RGBD Neural SLAMcited by 16
  20. 2024NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splattingcited by 16
  21. 2024Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methodscited by 16
  22. 2024High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimizationcited by 15
  23. 2024Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splattingcited by 15
  24. 2024DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splattingcited by 15
  25. 2025DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Priorcited by 14
  26. 2025GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splatscited by 14
  27. 2025VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenescited by 13
  28. 20254DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussianscited by 13
  29. 2024MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAMcited by 12
  30. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  31. 2024Q-SLAM: Quadric Representations for Monocular SLAMcited by 11
  32. 2024PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environmentscited by 11
  33. 2025SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embeddingcited by 11
  34. 2025Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and Mappingcited by 11
  35. 2025Rig3R: Rig-Aware Conditioning for Learned 3D Reconstructioncited by 11
  36. 2025MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representationcited by 11
  37. 2025Gaussian-Plus-SDF SLAM: High-fidelity 3D Reconstruction at 150+ fpscited by 11
  38. 2023NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fieldscited by 10

50 most cited of 160 All 160 (JSON)