mlsanityData to 14 Oct 2026

Neural Visibility Field for Uncertainty-Driven Active Mapping

arXiv 2406.06948 ↗First posted 11 Jun 2024cs.CV cs.ROcited by 26

Not on the map. Why?

Abstract (arXiv)

This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region, resulting in increased uncertainty in the synthesized views. To address this, we propose to use Bayesian Networks to composite position-based field uncertainty into ray-based uncertainty in camera observations. Consequently, NVF naturally assigns higher uncertainty to unobserved regions, aiding robots to select the most informative next viewpoints. Extensive evaluations show that NVF excels not only in uncertainty quantification but also in scene reconstruction for active mapping, outperforming existing methods.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

36 of 58 references.

References · 36

  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. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  9. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  10. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  11. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  12. 2021Neural Fields in Visual Computing and Beyondcited by 540
24 more
  1. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  2. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  3. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  4. 2021Neural RGB-D Surface Reconstructioncited by 313
  5. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  6. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  7. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  8. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  9. 2020Occupancy Anticipation for Efficient Exploration and Navigationcited by 106
  10. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 82
  11. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 60
  12. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  13. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 54
  14. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 54
  15. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 33
  16. 2022ActiveRMAP: Radiance Field for Active Mapping And Planningcited by 30
  17. 2022BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusioncited by 29
  18. 2023Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimizationcited by 28
  19. 2020Fast Frontier-based Information-driven Autonomous Exploration with an MAVcited by 24
  20. 2023Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environmentscited by 19
  21. 2022ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Imagescited by 12
  22. 2023NeRF Revisited: Fixing Quadrature Instability in Volume Renderingcited by 10
  23. 2023NerfBridge: Bringing Real-time, Online Neural Radiance Field Training to Roboticscited by 9
  24. 2022Uncertainty-Driven Active Vision for Implicit Scene Reconstructioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 15.

26 papers.

Sort:

  1. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  2. 2025Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstructioncited by 5
  3. 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Fieldcited by 5
  4. 2024Frequency-based View Selection in Gaussian Splatting Reconstructioncited by 4
  5. 2025Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantificationcited by 4
  6. 2024Towards a Science Exocortexcited by 3
  7. 2024Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstructioncited by 3
  8. 2025WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fieldscited by 3
  9. 2026Confidence-Based Mesh Extraction from 3D Gaussianscited by 3
  10. 2026ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstructioncited by 2
  11. 2026The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Modelscited by 2
  12. 2026Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstructioncited by 2
14 more
  1. 2026OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robotscited by 2
  2. 2026Coverage Optimization for Camera View Selectioncited by 2
  3. 2025Camera Calibration via Circular Patterns: A Comprehensive Framework with Detection Uncertainty and Unbiased Projection Modelcited by 1
  4. 2025Data Augmentation for NeRFs in the Low Data Limitcited by 0
  5. 2025Geometry-Aware Scene Configurations for Novel View Synthesiscited by 0
  6. 2025OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGScited by 0
  7. 2026SonoSelect: Efficient Ultrasound Perception via Active Probe Explorationcited by 0
  8. 2026MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scenecited by 0
  9. 2026PInVerify: An Offline Embodied Benchmark for Active Instance Verificationcited by 0
  10. 2026TRACE: Ergodic Trajectory Optimization for Active Scene Reconstructioncited by 0
  11. 2026DA-NBV: A Direction-Aware Next-Best-View Planner for Efficient 3D Reconstruction of Ships at Seacited by 0
  12. 2026Filling the Unseen: Scene Extrapolation via 3D Gaussian Splattingcited by 0
  13. 2026Matisse: Evidence-Space Reasoning for Active 3D Reconstructioncited by 0
  14. 2026VCURF: Virtual Camera-based Uncertainty of Radiance Fieldscited by 0