mlsanityData to 7 Oct 2026

Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field

arXiv 2605.30342 ↗First posted 28 May 2026cs.CV cs.ROcited by 4

Not on the map. Why?

Abstract (arXiv)

We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 60 of its 112 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

60 of 112 references.

References · 60

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  9. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  10. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  11. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  12. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
38 more
  1. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  2. 2023Gaussian Splatting SLAMcited by 410
  3. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  4. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  5. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  6. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  7. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  8. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
  9. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  10. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
  11. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
  12. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  13. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  14. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 63
  15. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 62
  16. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 58
  17. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 54
  18. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 53
  19. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 53
  20. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  21. 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Productscited by 35
  22. 2024ActiveGS: Active Scene Reconstruction Using Gaussian Splattingcited by 34
  23. 2024ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splattingcited by 32
  24. 2024GS-Planner: A Gaussian-Splatting-based Planning Framework for Active High-Fidelity Reconstructioncited by 30
  25. 2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
  26. 2023Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimizationcited by 27
  27. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 27
  28. 2024Neural Visibility Field for Uncertainty-Driven Active Mappingcited by 25
  29. 2020Fast Frontier-based Information-driven Autonomous Exploration with an MAVcited by 23
  30. 2020Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphscited by 23
  31. 2023Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environmentscited by 19
  32. 2025ActiveGAMER: Active GAussian Mapping through Efficient Renderingcited by 19
  33. 2021Self-Supervised Visibility Learning for Novel View Synthesiscited by 14
  34. 2023Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fieldscited by 14
  35. 2024RT-GuIDE: Real-Time Gaussian Splatting for Information-Driven Explorationcited by 14
  36. 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Modelscited by 12
  37. 2024Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splattingcited by 12
  38. 2024Manifold Sampling for Differentiable Uncertainty in Radiance Fieldscited by 11

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026View-Structured Conformal Prediction for 3D Gaussian Splattingcited by 0
  2. 2026LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splattingcited by 0
  3. 2026ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videoscited by 0
  4. 2026Matisse: Evidence-Space Reasoning for Active 3D Reconstructioncited by 0