mlsanityData to 7 Oct 2026

Investigating Self-Supervised Image Denoising with Denaturation

arXiv 2405.01124 ↗First posted 2 May 2024stat.ML cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 64 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

29 of 64 references.

References · 29

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2017Deep Image Priorcited by 1,097
  6. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  7. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  8. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  9. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
  10. 2018Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalitycited by 160
  11. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  12. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
17 more
  1. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 92
  2. 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 83
  3. 2019Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks : Function Approximation and Statistical Recoverycited by 73
  4. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
  5. 2021Burst Image Restoration and Enhancementcited by 64
  6. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59
  7. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Modelscited by 50
  8. 2017Deep Burst Denoisingcited by 49
  9. 2023Random Sub-Samples Generation for Self-Supervised Real Image Denoisingcited by 31
  10. 2021Noise2Fast: Fast Self-Supervised Single Image Blind Denoisingcited by 28
  11. 2023Diffusion Model for Generative Image Denoisingcited by 27
  12. 2021Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imagingcited by 15
  13. 2020Self-Supervised Poisson-Gaussian Denoisingcited by 9
  14. 2021Deformation-Compensated Learning for Image Reconstruction without Ground Truthcited by 9
  15. 2023Multi-view Self-supervised Disentanglement for General Image Denoisingcited by 7
  16. 2022Patch-Craft Self-Supervised Training for Correlated Image Denoisingcited by 5
  17. 2022Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Imagecited by 2

Built on by

Not cited yet.