mlsanityData to 14 Oct 2026

Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise

arXiv 2402.15635 ↗First posted 23 Feb 2024cs.IT cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We investigate both the theoretical and algorithmic aspects of likelihood-based methods for recovering a complex-valued signal from multiple sets of measurements, referred to as looks, affected by speckle (multiplicative) noise. Our theoretical contributions include establishing the first existing theoretical upper bound on the Mean Squared Error (MSE) of the maximum likelihood estimator under the deep image prior hypothesis. Our theoretical results capture the dependence of MSE upon the number of parameters in the deep image prior, the number of looks, the signal dimension, and the number of measurements per look. On the algorithmic side, we introduce the concept of bagged Deep Image Priors (Bagged-DIP) and integrate them with projected gradient descent. Furthermore, we show how employing Newton-Schulz algorithm for calculating matrix inverses within the iterations of PGD reduces the computational complexity of the algorithm. We will show that this method achieves the state-of-the-art performance.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 20 of its 53 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

20 of 53 references.

References · 20

  1. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  2. 2017Deep Image Priorcited by 1,098
  3. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  4. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  5. 2017Compressed Sensing using Generative Modelscited by 339
  6. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
  7. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 195
  8. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  9. 2019DeepRED: Deep Image Prior Powered by REDcited by 85
  10. 2018Compressed Sensing with Deep Image Prior and Learned Regularizationcited by 47
  11. 2022SUNet: Swin Transformer UNet for Image Denoisingcited by 44
  12. 2019Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generatorscited by 40
8 more
  1. 2019Algorithmic Guarantees for Inverse Imaging with Untrained Network Priorscited by 32
  2. 2020Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfittingcited by 18
  3. 2021Provable Compressed Sensing with Generative Priors via Langevin Dynamicscited by 14
  4. 2022Blind Image Deblurring with Unknown Kernel Size and Substantial Noisecited by 10
  5. 2022Practical Phase Retrieval Using Double Deep Image Priorscited by 10
  6. 2019One-dimensional Deep Image Prior for Time Series Inverse Problemscited by 7
  7. 2017Phase-error estimation and image reconstruction from digital-holography data using a Bayesian frameworkcited by 5
  8. 2020Convergence Rate Improvement of Richardson and Newton-Schulz Iterationscited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

4 papers.

  1. 2025Multilook Coherent Imaging: Theoretical Guarantees and Algorithmscited by 4
  2. 2026Maximum Likelihood Reconstruction for Multi-Look Digital Holography with Markov-Modeled Speckle Correlationcited by 2
  3. 2024Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithmscited by 1
  4. 2026Monte Carlo Maximum Likelihood Reconstruction for Digital Holography with Specklecited by 1