mlsanityData to 7 Oct 2026

Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior

arXiv 2203.00479 ↗First posted 28 Feb 2022eess.IV cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment. This paper develops a method, termed as the linearised deep image prior (DIP), to estimate the uncertainty associated with reconstructions produced by the DIP with total variation regularisation (TV). Specifically, we endow the DIP with conjugate Gaussian-linear model type error-bars computed from a local linearisation of the neural network around its optimised parameters. To preserve conjugacy, we approximate the TV regulariser with a Gaussian surrogate. This approach provides pixel-wise uncertainty estimates and a marginal likelihood objective for hyperparameter optimisation. We demonstrate the method on synthetic data and real-measured high-resolution 2D μCT data, and show that it provides superior calibration of uncertainty estimates relative to previous probabilistic formulations of the DIP. Our code is available at https://github.com/educating-dip/bayesdip.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 41 of its 88 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

41 of 88 references.

References · 41

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  4. 2017Deep Image Priorcited by 1,097
  5. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  6. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  7. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  8. 2015Weight Uncertainty in Neural Networkscited by 554
  9. 2018Deep Learning for Classical Japanese Literaturecited by 415
  10. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  11. 2017Compressed Sensing using Generative Modelscited by 337
  12. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
29 more
  1. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  2. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  3. 2018Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processescited by 164
  4. 2019Neural Tangents: Fast and Easy Infinite Neural Networks in Pythoncited by 149
  5. 2018Deep Convolutional Networks as shallow Gaussian Processescited by 137
  6. 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 128
  7. 2021Bayesian Neural Network Priors Revisitedcited by 121
  8. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  9. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
  10. 2020Getting a CLUE: A Method for Explaining Uncertainty Estimatescited by 92
  11. 2019Approximate Inference Turns Deep Networks into Gaussian Processescited by 89
  12. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 85
  13. 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
  14. 2020Pathwise Conditioning of Gaussian Processescited by 63
  15. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  16. 2020Depth Uncertainty in Neural Networkscited by 56
  17. 2019A Bayesian Perspective on the Deep Image Priorcited by 52
  18. 2021Early Stopping for Deep Image Priorcited by 44
  19. 2021On Measuring and Controlling the Spectral Bias of the Deep Image Priorcited by 36
  20. 2017Scalable Log Determinants for Gaussian Process Kernel Learningcited by 34
  21. 2021Fast Adaptation with Linearized Neural Networkscited by 32
  22. 2014On the folded normal distributioncited by 31
  23. 2018Variational Bayesian dropout: pitfalls and fixescited by 22
  24. 2022UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomographycited by 19
  25. 2020Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Priorcited by 18
  26. 2020Learning Discrete Distributions by Dequantizationcited by 17
  27. 2021An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstructioncited by 16
  28. 2020Predictive Complexity Priorscited by 14
  29. 2021Edge-promoting adaptive Bayesian experimental design for X-ray imagingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 1; 2026: 3.

10 papers.

  1. 2023UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Seriescited by 28
  2. 2023Sampling from Gaussian Process Posteriors using Stochastic Gradient Descentcited by 27
  3. 2023Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problemscited by 17
  4. 2024Nonlinear Assimilation via Score-based Sequential Langevin Samplingcited by 7
  5. 2024Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processescited by 5
  6. 2025Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomographycited by 4
  7. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstructioncited by 3
  8. 2023One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solverscited by 1
  9. 2026Principled Confidence Estimation for Deep Computed Tomographycited by 1
  10. 2026Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstructioncited by 0