mlsanityData to 7 Oct 2026

Sources of Uncertainty in 3D Scene Reconstruction

arXiv 2409.06407 ↗First posted 10 Sep 2024cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms to directly address or quantify uncertainties arising from the presence of noise, occlusions, confounding outliers, and imprecise camera pose inputs. In this paper, we introduce a taxonomy that categorizes different sources of uncertainty inherent in these methods. Moreover, we extend NeRF- and GS-based methods with uncertainty estimation techniques, including learning uncertainty outputs and ensembles, and perform an empirical study to assess their ability to capture the sensitivity of the reconstruction. Our study highlights the need for addressing various uncertainty aspects when designing NeRF/GS-based methods for uncertainty-aware 3D reconstruction.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

44 of 54 references.

References · 44

  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. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  8. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  11. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  12. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
32 more
  1. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  2. 2023Gaussian Splatting SLAMcited by 410
  3. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  4. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  5. 2017Advances in Variational Inferencecited by 236
  6. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  7. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  8. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  9. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  10. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 150
  11. 2017Practical Gauss-Newton Optimisation for Deep Learningcited by 139
  12. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  13. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  14. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
  15. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  16. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  17. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  18. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
  19. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  20. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
  21. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  22. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 63
  23. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  24. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 58
  25. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 54
  26. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 53
  27. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  28. 2023FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesiscited by 29
  29. 2024Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motioncited by 29
  30. 2021Bayesian Deep Basis Fitting for Depth Completion with Uncertaintycited by 23
  31. 2021Bayesian Surrogate Analysis and Uncertainty Propagationcited by 10
  32. 2024From NeRFs to Gaussian Splats, and Backcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024DeSplat: Decomposed Gaussian Splatting for Distractor-Free Renderingcited by 15
  2. 2025Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequencescited by 5
  3. 2025View-Dependent Uncertainty Estimation of 3D Gaussian Splattingcited by 5
  4. 2025MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarkscited by 4
  5. 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Fieldcited by 4
  6. 2025WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fieldscited by 2
  7. 2024RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learningcited by 0
  8. 2025OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGScited by 0
  9. 2026NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertaintycited by 0