mlsanityData to 14 Oct 2026

Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations

arXiv 2108.05851 ↗First posted 12 Aug 2021cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Recent advances have enabled a single neural network to serve as an implicit scene representation, establishing the mapping function between spatial coordinates and scene properties. In this paper, we make a further step towards continual learning of the implicit scene representation directly from sequential observations, namely Continual Neural Mapping. The proposed problem setting bridges the gap between batch-trained implicit neural representations and commonly used streaming data in robotics and vision communities. We introduce an experience replay approach to tackle an exemplary task of continual neural mapping: approximating a continuous signed distance function (SDF) from sequential depth images as a scene geometry representation. We show for the first time that a single network can represent scene geometry over time continually without catastrophic forgetting, while achieving promising trade-offs between accuracy and efficiency.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 49 of its 73 references that are in the map. First posted on arXiv 12 Aug 2021.

Builds on

49 of 73 references.

References · 49

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2016Learning without Forgettingcited by 2,496
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  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. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  9. 2016Progressive Neural Networkscited by 1,361
  10. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  11. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  12. 2018Experience Replay for Continual Learningcited by 1,095
37 more
  1. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  2. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  3. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  4. 2020Convolutional Occupancy Networkscited by 761
  5. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  6. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  9. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  10. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  11. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  12. 2019Three scenarios for continual learningcited by 614
  13. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  14. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 372
  15. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  16. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  17. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  18. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  19. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  20. 2020Understanding the Role of Training Regimes in Continual Learningcited by 180
  21. 2019CvxNet: Learnable Convex Decompositioncited by 174
  22. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  23. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 152
  24. 2019Continual Unsupervised Representation Learningcited by 147
  25. 2020A Neural Dirichlet Process Mixture Model for Task-Free Continual Learningcited by 134
  26. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  27. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  28. 2017Encoder Based Lifelong Learningcited by 102
  29. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  30. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
  31. 2020NeuralFusion: Online Depth Fusion in Latent Spacecited by 46
  32. 2017OctNetFusion: Learning Depth Fusion from Datacited by 45
  33. 2019SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representationscited by 37
  34. 2020PointGMM: a Neural GMM Network for Point Cloudscited by 33
  35. 2018SurfelMeshing: Online Surfel-Based Mesh Reconstructioncited by 29
  36. 2019RayNet: Learning Volumetric 3D Reconstruction with Ray Potentialscited by 26
  37. 2020Learning Implicit Surface Light Fieldscited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 8; 2024: 9; 2025: 3; 2026: 1.

30 papers.

Sort:

By area:

  1. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  2. 2021Neural Fields in Visual Computing and Beyondcited by 540
  3. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  4. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  5. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  6. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  7. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  8. 2023Active Neural Mappingcited by 31
  9. 2023Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimizationcited by 28
  10. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 28
  11. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  12. 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
18 more
  1. 2022IR-MCL: Implicit Representation-Based Online Global Localizationcited by 14
  2. 2025NextBestPath: Efficient 3D Mapping of Unseen Environmentscited by 13
  3. 2024Active Neural Mapping at Scalecited by 8
  4. 2022City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representationcited by 7
  5. 2022Learning Online Multi-Sensor Depth Fusioncited by 6
  6. 2024Depth Reconstruction with Neural Signed Distance Fields in Structured Light Systemscited by 4
  7. 2024Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAMcited by 4
  8. 2022UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representationcited by 3
  9. 2023HIO-SDF: Hierarchical Incremental Online Signed Distance Fieldscited by 3
  10. 2024Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environmentscited by 1
  11. 2025Meta-Continual Learning of Neural Fieldscited by 1
  12. 2023A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstructioncited by 0
  13. 2024AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenescited by 0
  14. 2024LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updatingcited by 0
  15. 2024Decomposition of Neural Discrete Representations for Large-Scale 3D Mappingcited by 0
  16. 2024CCNDF: Curvature Constrained Neural Distance Fields from 3D LiDAR Sequencescited by 0
  17. 2025Matching-Free Depth Recovery from Structured Lightcited by 0
  18. 2026Continual Learning as a Multiphase Moving-Boundary Problemcited by 0