mlsanityData to 7 Oct 2026

An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstruction

arXiv 2111.11926 ↗First posted 23 Nov 2021eess.IV cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Deep image prior (DIP) was recently introduced as an effective unsupervised approach for image restoration tasks. DIP represents the image to be recovered as the output of a deep convolutional neural network, and learns the network's parameters such that the output matches the corrupted observation. Despite its impressive reconstructive properties, the approach is slow when compared to supervisedly learned, or traditional reconstruction techniques. To address the computational challenge, we bestow DIP with a two-stage learning paradigm: (i) perform a supervised pretraining of the network on a simulated dataset; (ii) fine-tune the network's parameters to adapt to the target reconstruction task. We provide a thorough empirical analysis to shed insights into the impacts of pretraining in the context of image reconstruction. We showcase that pretraining considerably speeds up and stabilizes the subsequent reconstruction task from real-measured 2D and 3D micro computed tomography data of biological specimens. The code and additional experimental materials are available at https://educateddip.github.io/docs.educated_deep_image_prior/.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 35 of its 64 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

35 of 64 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  11. 2017Deep Image Priorcited by 1,097
  12. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
23 more
  1. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  2. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  3. 2018Rethinking ImageNet Pre-trainingcited by 376
  4. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 366
  5. 2020What is being transferred in transfer learning?cited by 365
  6. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  7. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  8. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  9. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  10. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  11. 2019DeepRED: Deep Image Prior Powered by REDcited by 84
  12. 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
  13. 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
  14. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  15. 2019A Bayesian Perspective on the Deep Image Priorcited by 52
  16. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  17. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  18. 2020Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximationcited by 39
  19. 2021Rethinking Deep Image Prior for Denoisingcited by 38
  20. 2017Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MRcited by 31
  21. 2018Regularization by architecture: A deep prior approach for inverse problemscited by 26
  22. 2020Model Adaptation for Inverse Problems in Imagingcited by 20
  23. 2021Unsupervised Knowledge-Transfer for Learned Image Reconstructioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 4; 2025: 2; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problemscited by 21
  2. 2023Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstructioncited by 15
  3. 2022Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Priorcited by 10
  4. 2024Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problemscited by 8
  5. 2025Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomographycited by 4
  6. 2023Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularizationcited by 3
  7. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstructioncited by 3
  8. 2023SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstructioncited by 2
  9. 2022Unsupervised denoising for sparse multi-spectral computed tomographycited by 1
  10. 2023Image Reconstruction via Deep Image Prior Subspacescited by 1
  11. 2025Deep Spectral Priorcited by 1
  12. 2026A Stability Benchmark of Generative Regularizers for Inverse Problemscited by 1
4 more
  1. 2024Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisationcited by 0
  2. 2024Sequential-Scanning Dual-Energy CT Imaging Using High Temporal Resolution Image Reconstruction and Error-Compensated Material Basis Image Generationcited by 0
  3. 2026Deep Image Prior for photoacoustic tomography can mitigate limited-view artifactscited by 0
  4. 2026Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstructioncited by 0