mlsanityData to 14 Oct 2026

Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising

arXiv 2412.16460 ↗First posted 21 Dec 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Image denoising enhances image quality, serving as a foundational technique across various computational photography applications. The obstacle to clean image acquisition in real scenarios necessitates the development of self-supervised image denoising methods only depending on noisy images, especially a single noisy image. Existing self-supervised image denoising paradigms (Noise2Noise and Noise2Void) rely heavily on information-lossy operations, such as downsampling and masking, culminating in low quality denoising performance. In this paper, we propose a novel self-supervised single image denoising paradigm, Positive2Negative, to break the information-lossy barrier. Our paradigm involves two key steps: Renoised Data Construction (RDC) and Denoised Consistency Supervision (DCS). RDC renoises the predicted denoised image by the predicted noise to construct multiple noisy images, preserving all the information of the original image. DCS ensures consistency across the multiple denoised images, supervising the network to learn robust denoising. Our Positive2Negative paradigm achieves state-of-the-art performance in self-supervised single image denoising with significant speed improvements. The code is released to the public at https://github.com/Li-Tong-621/P2N.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 41 of its 60 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

41 of 60 references.

References · 41

  1. 2017Decoupled Weight Decay Regularizationcited by 1,831
  2. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  3. 2017Deep Image Priorcited by 1,098
  4. 2022Simple Baselines for Image Restorationcited by 708
  5. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  6. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
  7. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
  8. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  9. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  10. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 173
  11. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  12. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 126
29 more
  1. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
  2. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
  3. 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 84
  4. 2020Practical Deep Raw Image Denoising on Mobile Devicescited by 76
  5. 2018Real-world Noisy Image Denoising: A New Benchmarkcited by 74
  6. 2020Unpaired Learning of Deep Image Denoisingcited by 74
  7. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 71
  8. 2021Physics-based Noise Modeling for Extreme Low-light Photographycited by 67
  9. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 61
  10. 2023Masked Image Training for Generalizable Deep Image Denoisingcited by 57
  11. 2020Noise2Same: Optimizing A Self-Supervised Bound for Image Denoisingcited by 56
  12. 2019When AWGN-based Denoiser Meets Real Noisescited by 53
  13. 2019Probabilistic Noise2Void: Unsupervised Content-Aware Denoisingcited by 51
  14. 2022CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Imagecited by 45
  15. 2023LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoisingcited by 37
  16. 2021IDR: Self-Supervised Image Denoising via Iterative Data Refinementcited by 36
  17. 2023Spatially Adaptive Self-Supervised Learning for Real-World Image Denoisingcited by 33
  18. 2023Random Sub-Samples Generation for Self-Supervised Real Image Denoisingcited by 31
  19. 2023MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Networkcited by 30
  20. 2024Transfer CLIP for Generalizable Image Denoisingcited by 29
  21. 2021FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noisecited by 22
  22. 2021Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matchingcited by 18
  23. 2022Learn from Unpaired Data for Image Restoration: A Variational Bayes Approachcited by 18
  24. 2023Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarioscited by 17
  25. 2023Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensemblingcited by 17
  26. 2023Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoisingcited by 15
  27. 2023Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Networkcited by 12
  28. 2024Masked and Shuffled Blind Spot Denoising for Real-World Imagescited by 12
  29. 2023SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoisingcited by 2
  2. 2025MID: A Self-supervised Multimodal Iterative Denoising Frameworkcited by 0
  3. 2026Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoisingcited by 0
  4. 2026Closed-Form Nonlocal Shrinkage for Multiplicative Image Denoising and SAR Despecklingcited by 0
  5. 2026Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoisingcited by 0
  6. 2026Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoisingcited by 0