mlsanityData to 14 Oct 2026

Speckle Image Restoration without Clean Data

arXiv 2205.08833 ↗First posted 18 May 2022eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Speckle noise is an inherent disturbance in coherent imaging systems such as digital holography, synthetic aperture radar, optical coherence tomography, or ultrasound systems. These systems usually produce only single observation per view angle of the same interest object, imposing the difficulty to leverage the statistic among observations. We propose a novel image restoration algorithm that can perform speckle noise removal without clean data and does not require multiple noisy observations in the same view angle. Our proposed method can also be applied to the situation without knowing the noise distribution as prior. We demonstrate our method is especially well-suited for spectral images by first validating on the synthetic dataset, and also applied on real-world digital holography samples. The results are superior in both quantitative measurement and visual inspection compared to several widely applied baselines. Our method even shows promising results across different speckle noise strengths, without the clean data needed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 18 May 2022.

Builds on

15 of 32 references.

References · 15

  1. 2017Decoupled Weight Decay Regularizationcited by 1,831
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  3. 2017Deep Image Priorcited by 1,098
  4. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  5. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
  6. 2017Road Extraction by Deep Residual U-Netcited by 333
  7. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
  8. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  9. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  10. 2019Probabilistic Noise2Void: Unsupervised Content-Aware Denoisingcited by 51
  11. 2016Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connectionscited by 30
  12. 2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learningcited by 29
3 more
  1. 2018Correction by Projection: Denoising Images with Generative Adversarial Networkscited by 11
  2. 2019Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Imagecited by 3
  3. 2019Noise2Blur: Online Noise Extraction and Denoisingcited by 2

Built on by

Not cited yet.