mlsanityData to 14 Oct 2026

FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information

arXiv 2311.17874 ↗First posted 29 Nov 2023cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

This study addresses the challenging problem of active view selection and uncertainty quantification within the domain of Radiance Fields. Neural Radiance Fields (NeRF) have greatly advanced image rendering and reconstruction, but the cost of acquiring images poses the need to select the most informative viewpoints efficiently. Existing approaches depend on modifying the model architecture or hypothetical perturbation field to indirectly approximate the model uncertainty. However, selecting views from indirect approximation does not guarantee optimal information gain for the model. By leveraging Fisher Information, we directly quantify observed information on the parameters of Radiance Fields and select candidate views by maximizing the Expected Information Gain(EIG). Our method achieves state-of-the-art results on multiple tasks, including view selection, active mapping, and uncertainty quantification, demonstrating its potential to advance the field of Radiance Fields.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

26 of 36 references.

References · 26

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  8. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  9. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  10. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  11. 2020A Survey of Deep Active Learningcited by 554
  12. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
14 more
  1. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  2. 2017A Bayesian Perspective on Generalization and Stochastic Gradient Descentcited by 135
  3. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  4. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 91
  5. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  6. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  7. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 82
  8. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 73
  9. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 60
  10. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  11. 2023Active Neural Mappingcited by 31
  12. 2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
  13. 2023Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimizationcited by 28
  14. 2023Uncertainty-Driven Dense Two-View Structure from Motioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 19; 2025: 25; 2026: 20.

64 papers.

Sort:

By area:

  1. 2024A Survey on 3D Gaussian Splattingcited by 224
  2. 2024PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splattingcited by 95
  3. 2024ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splattingcited by 32
  4. 2024Sort-free Gaussian Splatting via Weighted Sum Renderingcited by 29
  5. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  6. 2025Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loopcited by 25
  7. 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splattingcited by 21
  8. 2025POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimalitycited by 18
  9. 2024Touch-GS: Visual-Tactile Supervised 3D Gaussian Splattingcited by 16
  10. 2024HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Renderingcited by 16
  11. 2024AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusioncited by 13
  12. 2024Manifold Sampling for Differentiable Uncertainty in Radiance Fieldscited by 12
38 more
  1. 2024Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splattingcited by 12
  2. 2025FrontierNet: Learning Visual Cues to Explorecited by 12
  3. 2025GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenescited by 11
  4. 2024Sources of Uncertainty in 3D Scene Reconstructioncited by 10
  5. 2024Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splattingcited by 10
  6. 2025MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structurecited by 10
  7. 2024Multimodal LLM Guided Exploration and Active Mapping using Fisher Informationcited by 9
  8. 2025These Magic Moments: Differentiable Uncertainty Quantification of Radiance Field Modelscited by 6
  9. 2025PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coveragecited by 6
  10. 2025ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priorscited by 6
  11. 2025Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequencescited by 5
  12. 2025View-Dependent Uncertainty Estimation of 3D Gaussian Splattingcited by 5
  13. 2025SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Groupingcited by 5
  14. 2026GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoningcited by 5
  15. 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Fieldcited by 5
  16. 2024Frequency-based View Selection in Gaussian Splatting Reconstructioncited by 4
  17. 2025Uncertainty-Aware Diffusion Guided Refinement of 3D Scenescited by 3
  18. 2026VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAMcited by 3
  19. 2026Confidence-Based Mesh Extraction from 3D Gaussianscited by 3
  20. 2025DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstructioncited by 2
  21. 2025VIN-NBV: A View Introspection Network for Next-Best-View Selectioncited by 2
  22. 2025Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splattingcited by 2
  23. 2026SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selectioncited by 2
  24. 2026B3-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updatescited by 2
  25. 2026Coverage Optimization for Camera View Selectioncited by 2
  26. 2024GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstructioncited by 1
  27. 2025Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstructioncited by 1
  28. 2025CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focuscited by 1
  29. 2025Real-World Reinforcement Learning of Active Perception Behaviorscited by 1
  30. 2025Next Best View Selections for Semantic and Dynamic 3D Gaussian Splattingcited by 1
  31. 2026FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generationcited by 1
  32. 2026A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometrycited by 1
  33. 2026GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mappingcited by 1
  34. 2026GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstructioncited by 1
  35. 2024Surface-Based Visibility-Guided Uncertainty for Continuous Active 3D Neural Reconstructioncited by 0
  36. 2024Active Scout: Multi-Target Tracking Using Neural Radiance Fields in Dense Urban Environmentscited by 0
  37. 2024RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learningcited by 0
  38. 2025Data Augmentation for NeRFs in the Low Data Limitcited by 0

50 most cited of 64 All 64 (JSON)