mlsanityData to 7 Oct 2026

UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography

arXiv 2202.10847 ↗First posted 22 Feb 2022eess.IV cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Implicit neural representations (INRs) have achieved impressive results for scene reconstruction and computer graphics, where their performance has primarily been assessed on reconstruction accuracy. As INRs make their way into other domains, where model predictions inform high-stakes decision-making, uncertainty quantification of INR inference is becoming critical. To that end, we study a Bayesian reformulation of INRs, UncertaINR, in the context of computed tomography, and evaluate several Bayesian deep learning implementations in terms of accuracy and calibration. We find that they achieve well-calibrated uncertainty, while retaining accuracy competitive with other classical, INR-based, and CNN-based reconstruction techniques. Contrary to common intuition in the Bayesian deep learning literature, we find that INRs obtain the best calibration with computationally efficient Monte Carlo dropout, outperforming Hamiltonian Monte Carlo and deep ensembles. Moreover, in contrast to the best-performing prior approaches, UncertaINR does not require a large training dataset, but only a handful of validation images.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 61 of its 141 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

61 of 141 references.

References · 61

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
38 more
  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  4. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  9. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  10. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  11. 2017Deep Neural Networks as Gaussian Processescited by 617
  12. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  13. 2019Measuring Calibration in Deep Learningcited by 443
  14. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  15. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  16. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  17. 2017The Expressive Power of Neural Networks: A View from the Widthcited by 318
  18. 2018Gaussian Process Behaviour in Wide Deep Neural Networkscited by 314
  19. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  20. 2016On the Expressive Power of Deep Neural Networkscited by 302
  21. 2017Learned Primal-dual Reconstructioncited by 251
  22. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  23. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  24. 2021COIN: COmpression with Implicit Neural representationscited by 232
  25. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  26. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  27. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 207
  28. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  29. 2019Universal Approximation with Deep Narrow Networkscited by 198
  30. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 187
  31. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  32. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  33. 2019NASA: Neural Articulated Shape Approximationcited by 149
  34. 2018Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networkscited by 140
  35. 2021Bayesian Neural Network Priors Revisitedcited by 121
  36. 2017Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activationscited by 104
  37. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  38. 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 3; 2025: 1; 2026: 8.

19 papers.

Sort:

By area:

  1. 2022DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstructioncited by 73
  2. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  3. 2022Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomographycited by 31
  4. 2022Conditional Injective Flows for Bayesian Imagingcited by 13
  5. 2023Using AI Uncertainty Quantification to Improve Human Decision-Makingcited by 11
  6. 2022Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Priorcited by 10
  7. 2023Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reductioncited by 9
  8. 2024Regularized Multi-Decoder Ensemble for an Error-Aware Scene Representation Networkcited by 6
  9. 2024Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fieldscited by 3
  10. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstructioncited by 3
  11. 2026REV-INR: Regularized Evidential Implicit Neural Representation for Uncertainty-Aware Volume Visualizationcited by 1
  12. 2026Principled Confidence Estimation for Deep Computed Tomographycited by 1
7 more
  1. 2026Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstructioncited by 1
  2. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  3. 2026When Variance Is Not an Error Map: Calibrated Uncertainty for Radiative Gaussian Splatting in Sparse-View CTcited by 1
  4. 2023IntraSeismic: a coordinate-based learning approach to seismic inversioncited by 0
  5. 2025TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imagingcited by 0
  6. 2026Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methodscited by 0
  7. 2026ScoreField: Neural Inverse Scattering with Score-Based Generative Priorscited by 0