mlsanityData to 7 Oct 2026

iMAP: Implicit Mapping and Positioning in Real-Time

arXiv 2103.12352 ↗First posted 23 Mar 2021cs.CVcited by 476

Not on the map. Why?

Abstract (arXiv)

We show for the first time that a multilayer perceptron (MLP) can serve as the only scene representation in a real-time SLAM system for a handheld RGB-D camera. Our network is trained in live operation without prior data, building a dense, scene-specific implicit 3D model of occupancy and colour which is also immediately used for tracking. Achieving real-time SLAM via continual training of a neural network against a live image stream requires significant innovation. Our iMAP algorithm uses a keyframe structure and multi-processing computation flow, with dynamic information-guided pixel sampling for speed, with tracking at 10 Hz and global map updating at 2 Hz. The advantages of an implicit MLP over standard dense SLAM techniques include efficient geometry representation with automatic detail control and smooth, plausible filling-in of unobserved regions such as the back surfaces of objects.

Key facts. Cited by 476 papers in the map (data through 7 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

24 of 39 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2016Progressive Neural Networkscited by 1,332
  9. 2017Continual Learning with Deep Generative Replaycited by 1,152
  10. 2018Experience Replay for Continual Learningcited by 1,074
  11. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  12. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
12 more
  1. 2020Convolutional Occupancy Networkscited by 760
  2. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  3. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  4. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  5. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  6. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  7. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  8. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  9. 2018Generative Models from the perspective of Continual Learningcited by 69
  10. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  11. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  12. 2020Deep Implicit Volume Compressioncited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 64; 2023: 113; 2024: 135; 2025: 95; 2026: 52.

476 papers.

Sort:

By area:

  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  2. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  3. 2021Neural Fields in Visual Computing and Beyondcited by 539
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  5. 2023Gaussian Splatting SLAMcited by 410
  6. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  7. 2021Advances in Neural Renderingcited by 365
  8. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 357
  9. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  10. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  11. 20243D Reconstruction with Spatial Memorycited by 269
  12. 2021Urban Radiance Fieldscited by 263
38 more
  1. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  2. 2024A Survey on 3D Gaussian Splattingcited by 221
  3. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  4. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  5. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  6. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  7. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
  8. 2022CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memorycited by 164
  9. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  10. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  11. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  12. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  13. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
  14. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  15. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  16. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 139
  17. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  18. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  19. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 107
  20. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100
  21. 2023Language Embedded Radiance Fields for Zero-Shot Task-Oriented Graspingcited by 91
  22. 2022NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fieldscited by 86
  23. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  24. 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 86
  25. 2023OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Datacited by 81
  26. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  27. 2021Learning to Stylize Novel Viewscited by 76
  28. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  29. 2024Deep Patch Visual SLAMcited by 68
  30. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  31. 2022Removing Objects From Neural Radiance Fieldscited by 66
  32. 2024RGBD GS-ICP SLAMcited by 65
  33. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 64
  34. 2023PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustmentcited by 62
  35. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  36. 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
  37. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
  38. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 58

50 most cited of 476 All 476 (JSON)