mlsanityData to 14 Oct 2026

VCURF: Virtual Camera-based Uncertainty of Radiance Fields

arXiv 2610.04076 ↗First posted 2 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Radiance fields, implemented with either implicit (NeRF) or explicit (Gaussian Splatting) representations, are advancing the state of the art in novel view synthesis at a rapid pace. Even though the rendered views they generate are often compelling, they are not free of errors. In this paper, we propose a new approach for pixel-wise uncertainty quantification based on measuring the inconsistencies among renderings by the radiance field model in virtual cameras sampled near the target viewpoint. We named our approach VCURF for Virtual Camera-based Uncertainty of Radiance Fields. VCURF treats the radiance field model as a black box, only assuming that it is capable of rendering color and depth on demand. This property makes our approach applicable to both NeRF and GS models without any modification. Our experiments on a combination of datasets, radiance field models and baselines demonstrate VCURF's effectiveness in pixel-wise uncertainty estimation. We conclude the paper with findings that question the way view selection is tackled by the majority of the current literature.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 2 Oct 2026.

Builds on

43 of 55 references.

References · 43

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  7. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  8. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
  9. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 152
  10. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  11. 20243D Gaussian as a New Era: A Surveycited by 104
  12. 2024PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splattingcited by 95
31 more
  1. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 91
  2. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 82
  3. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 73
  4. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 64
  5. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 60
  6. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  7. 2021Model Zoo: A Growing "Brain" That Learns Continuallycited by 54
  8. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 54
  9. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 54
  10. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 41
  11. 2024ActiveGS: Active Scene Reconstruction Using Gaussian Splattingcited by 35
  12. 2023Active Neural Mappingcited by 31
  13. 2022ActiveRMAP: Radiance Field for Active Mapping And Planningcited by 30
  14. 2023Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimizationcited by 28
  15. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 28
  16. 2024Neural Visibility Field for Uncertainty-Driven Active Mappingcited by 26
  17. 2024Modeling uncertainty for Gaussian Splattingcited by 19
  18. 2025GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstructioncited by 17
  19. 2023Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fieldscited by 15
  20. 2024NeRF Director: Revisiting View Selection in Neural Volume Renderingcited by 15
  21. 2024RT-GuIDE: Real-Time Gaussian Splatting for Information-Driven Explorationcited by 15
  22. 2024Manifold Sampling for Differentiable Uncertainty in Radiance Fieldscited by 12
  23. 2022Efficient View Path Planning for Autonomous Implicit Reconstructioncited by 11
  24. 2024Sources of Uncertainty in 3D Scene Reconstructioncited by 10
  25. 2023Active Perception using Neural Radiance Fieldscited by 8
  26. 2025PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coveragecited by 6
  27. 2026Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Fieldcited by 5
  28. 2026Evidential Neural Radiance Fieldscited by 4
  29. 2025WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fieldscited by 3
  30. 2024Uncertainty modeling for fine-tuned implicit functionscited by 2
  31. 2024PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesiscited by 1

Built on by

Not cited yet.