mlsanityData to 14 Oct 2026

Active Neural Mapping

arXiv 2308.16246 ↗First posted 30 Aug 2023cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

We address the problem of active mapping with a continually-learned neural scene representation, namely Active Neural Mapping. The key lies in actively finding the target space to be explored with efficient agent movement, thus minimizing the map uncertainty on-the-fly within a previously unseen environment. In this paper, we examine the weight space of the continually-learned neural field, and show empirically that the neural variability, the prediction robustness against random weight perturbation, can be directly utilized to measure the instant uncertainty of the neural map. Together with the continuous geometric information inherited in the neural map, the agent can be guided to find a traversable path to gradually gain knowledge of the environment. We present for the first time an active mapping system with a coordinate-based implicit neural representation for online scene reconstruction. Experiments in the visually-realistic Gibson and Matterport3D environment demonstrate the efficacy of the proposed method.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 54 of its 86 references that are in the map. First posted on arXiv 30 Aug 2023.

Builds on

54 of 86 references.

References · 54

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  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. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  11. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  12. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
38 more
  1. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  2. 2017Deep Bayesian Active Learning with Image Datacited by 819
  3. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  4. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  5. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  6. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  7. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
  8. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  9. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  10. 2020Learning to Explore using Active Neural SLAMcited by 316
  11. 2021Neural RGB-D Surface Reconstructioncited by 313
  12. 2017Cognitive Mapping and Planning for Visual Navigationcited by 212
  13. 2022CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memorycited by 165
  14. 2021Vision-Only Robot Navigation in a Neural Radiance Worldcited by 155
  15. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 150
  16. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  17. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  18. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  19. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  20. 2020Occupancy Anticipation for Efficient Exploration and Navigationcited by 106
  21. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  22. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 82
  23. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  24. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 73
  25. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 66
  26. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 60
  27. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  28. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 54
  29. 2020FUEL: Fast UAV Exploration using Incremental Frontier Structure and Hierarchical Planningcited by 48
  30. 2019An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environmentscited by 40
  31. 2018FutureMapping: The Computational Structure of Spatial AI Systemscited by 36
  32. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 33
  33. 2019FIESTA: Fast Incremental Euclidean Distance Fields for Online Motion Planning of Aerial Robotscited by 31
  34. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  35. 2020Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgettingcited by 28
  36. 2020Fast Frontier-based Information-driven Autonomous Exploration with an MAVcited by 24
  37. 2021Formalizing the Generalization-Forgetting Trade-off in Continual Learningcited by 24
  38. 2019FutureMapping 2: Gaussian Belief Propagation for Spatial AIcited by 17

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 9; 2026: 10.

31 papers.

Sort:

By area:

  1. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 91
  2. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 64
  3. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  4. 2024ActiveGS: Active Scene Reconstruction Using Gaussian Splattingcited by 35
  5. 2024ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splattingcited by 32
  6. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 28
  7. 2024Neural Fields in Robotics: A Surveycited by 21
  8. 2025ActiveGAMER: Active GAussian Mapping through Efficient Renderingcited by 19
  9. 2025NextBestPath: Efficient 3D Mapping of Unseen Environmentscited by 13
  10. 2025FrontierNet: Learning Visual Cues to Explorecited by 12
  11. 2025GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenescited by 11
  12. 2024Multimodal LLM Guided Exploration and Active Mapping using Fisher Informationcited by 9
19 more
  1. 2024Active Neural Mapping at Scalecited by 8
  2. 2025Understanding while Exploring: Semantics-driven Active Mappingcited by 5
  3. 2026MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mappingcited by 5
  4. 2025AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidancecited by 4
  5. 2025WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fieldscited by 3
  6. 2026Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environmentscited by 3
  7. 2026EUGens: Efficient, Unified, and General Dense Layerscited by 2
  8. 2024Autonomous Implicit Indoor Scene Reconstruction with Frontier Explorationcited by 1
  9. 2025BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fieldscited by 1
  10. 2024Decomposition of Neural Discrete Representations for Large-Scale 3D Mappingcited by 0
  11. 2024EUGens: Efficient, Unified, and General Dense Layerscited by 0
  12. 2025Data Augmentation for NeRFs in the Low Data Limitcited by 0
  13. 2026HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimizationcited by 0
  14. 2026Paparazzo: Active Mapping of Moving 3D Objectscited by 0
  15. 2026Remember to be Curious: Episodic Context and Persistent Worlds for 3D Explorationcited by 0
  16. 2026Beyond Frontiers: Scene-Anomaly Guided Autonomous Explorationcited by 0
  17. 2026Diagnosing and Dynamically Filtering Occupancy World Models for Active Mappingcited by 0
  18. 2026Matisse: Evidence-Space Reasoning for Active 3D Reconstructioncited by 0
  19. 2026VCURF: Virtual Camera-based Uncertainty of Radiance Fieldscited by 0