Papers
Topics
Authors
Recent
2000 character limit reached

A unified framework of non-local parametric methods for image denoising (2402.13816v1)

Published 21 Feb 2024 in cs.CV

Abstract: We propose a unified view of non-local methods for single-image denoising, for which BM3D is the most popular representative, that operate by gathering noisy patches together according to their similarities in order to process them collaboratively. Our general estimation framework is based on the minimization of the quadratic risk, which is approximated in two steps, and adapts to photon and electronic noises. Relying on unbiased risk estimation (URE) for the first step and on ``internal adaptation'', a concept borrowed from deep learning theory, for the second, we show that our approach enables to reinterpret and reconcile previous state-of-the-art non-local methods. Within this framework, we propose a novel denoiser called NL-Ridge that exploits linear combinations of patches. While conceptually simpler, we show that NL-Ridge can outperform well-established state-of-the-art single-image denoisers.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Noise2Self: Blind denoising by self-supervision. In International Conference on Machine Learning (ICML), volume 97, pages 524–533, 2019.
  2. A. Benazza-Benyahia and J.-C. Pesquet. An extended SURE approach for multicomponent image denoising. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 2, pages ii–945, 2004.
  3. The SURE-LET approach to image denoising. IEEE Transactions on Image Processing, 16(11):2778–2786, 2007.
  4. Patch-based nonlocal functional for denoising fluorescence microscopy image sequences. IEEE Transactions on Medical Imaging, 29(2):442–454, 2010.
  5. A review of image denoising algorithms, with a new one. Multiscale Modeling & Simulation, 4(2):490–530, 2005.
  6. Image denoising: Can plain neural networks compete with BM3D? In Conference on Computer Vision and Pattern Recognition (CVPR), pages 2392–2399, 2012.
  7. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6):1256–1272, 2017.
  8. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8):2080–2095, 2007.
  9. Nonlocal image restoration with bilateral variance estimation: A low-rank approach. IEEE Transactions on Image Processing, 22(2):700–711, 2013.
  10. Nonlocally centralized sparse representation for image restoration. IEEE Transactions on Image Processing, 22(4):1620–1630, 2013.
  11. A bias-variance approach for the nonlocal means. SIAM Journal on Imaging Sciences, 4(2):760–788, 2011.
  12. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image processing, 15(12):3736–3745, 2006.
  13. Weighted nuclear norm minimization with application to image denoising. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 2862–2869, 2014.
  14. Normalization-equivariant neural networks with application to image denoising. arXiv preprint arXiv:2306.05037, 2023.
  15. DCT2net: an interpretable shallow CNN for image denoising. IEEE Transactions on Image Processing, 31:4292–4305, 2022.
  16. Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach. In IEEE International Conference on Image Processing (ICIP), pages 3376–3380, 2022.
  17. A note on patch-based low-rank minimization for fast image denoising. Journal of Visual Communication and Image Representation, 50:100–110, 2018.
  18. Single image super-resolution from transformed self-exemplars. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 5197–5206, 2015.
  19. Nonlocal means and optimal weights for noise removal. SIAM Journal on Imaging Sciences, 10(4):1878–1920, 2017.
  20. Rethinking Deep Image Prior for denoising. In International Conference on Computer Vision (ICCV), pages 5087–5096, 2021.
  21. Charles Kervrann. PEWA: Patch-based exponentially weighted aggregation for image denoising. In Advances in Neural Information Processing Systems (NIPS), volume 27, 2014.
  22. Matrix inversion using Cholesky decomposition. In Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), pages 70–72, 2013.
  23. Noise2Void - Learning denoising from single noisy images. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 2124–2132, 2019.
  24. High-quality self-supervised deep image denoising. In Advances in Neural Information Processing Systems (NeurIPS), volume 32, 2019.
  25. An unbiased risk estimator for image denoising in the presence of mixed Poisson–Gaussian noise. IEEE Transactions on Image Processing, 23(3):1255–1268, 2014.
  26. A nonlocal Bayesian image denoising algorithm. SIAM Journal on Imaging Sciences, 6(3):1665–1688, 2013.
  27. Implementation of the "Non-Local Bayes" (NL-Bayes) image denoising algorithm. Image Processing On Line, 3:1–42, 2013.
  28. Secrets of image denoising cuisine. Acta Numerica, 21(4):475 – 576, 2012.
  29. Noise2Noise: Learning image restoration without clean data. In International Conference on Machine Learning (ICML), volume 80, pages 2965–2974, 2018.
  30. Deep image prior. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 9446–9454, 2018.
  31. A fast blind zero-shot denoiser. Nature Machine Intelligence, 4(11):953–963, 2022.
  32. SwinIR: Image restoration using Swin Transformer. In International Conference on Computer Vision Workshops (ICCVW), pages 1833–1844, 2021.
  33. Non-local recurrent network for image restoration. In Advances in Neural Information Processing Systems (NeurIPS), volume 31, 2018.
  34. Self-supervised image prior learning with GMM from a single noisy image. In International Conference on Computer Vision (ICCV), pages 2825–2834, 2021.
  35. Multi-level wavelet-CNN for image restoration. In Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 773–782, 2018.
  36. A new SURE approach to image denoising: interscale orthonormal wavelet thresholding. IEEE Transactions on Image Processing, 16(3):593–606, 2007.
  37. Fast interscale wavelet denoising of Poisson-corrupted images. Signal Processing, 90:415–427, 2010.
  38. Non-local sparse models for image restoration. In International Conference on Computer Vision (ICCV), pages 2272–2279, 2009.
  39. Zero-Shot Noise2Noise: Efficient image denoising without any data. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 14018–14027, 2023.
  40. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In Advances in Neural Information Processing Systems (NIPS), volume 29, 2016.
  41. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In International Conference on Computer Vision (ICCV), volume 2, pages 416–423 vol.2, 2001.
  42. Noisier2Noise: Learning to denoise from unpaired noisy data. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 12061–12069, 2020.
  43. Collaborative filtering of correlated noise: Exact transform-domain variance for improved shrinkage and patch matching. IEEE Transactions on Image Processing, 29:8339–8354, 2020.
  44. Numerical Optimization. Springer, 1999.
  45. Recorrupted-to-Recorrupted: Unsupervised deep learning for image denoising. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 2043–2052, 2021.
  46. Neural nearest neighbors networks. In Advances in Neural Information Processing Systems (NeurIPS), volume 31, 2018.
  47. Benchmarking denoising algorithms with real photographs. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 2750–2759, 2017.
  48. Self2Self with dropout: Learning self-supervised denoising from single image. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 1887–1895, 2020.
  49. J. Salmon and Y. Strozecki. From patches to pixels in non-local methods: Weighted-average reprojection. In IEEE International Conference on Image Processing (ICIP), pages 1929–1932, 2010.
  50. Image Processing and Data Analysis: the multiscale approach. Cambridge University Press, 1998.
  51. Charles M. Stein. Estimation of the mean of a multivariate normal distribution. The Annals of Statistics, 9(6):1135–1151, 1981.
  52. LIDIA: Lightweight learned image denoising with instance adaptation. In Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 2220–2229, 2020.
  53. Dimitri Van De Ville and Michel Kocher. SURE-based Non-Local Means. IEEE Signal Processing Letters, 16(11):973–976, 2009.
  54. SURE guided Gaussian mixture image denoising. SIAM Journal on Imaging Sciences, 6(2):999–1034, 2013.
  55. A trilateral weighted sparse coding scheme for real-world image denoising. In European Conference on Computer Vision (ECCV), pages 20–36, 2018.
  56. Restormer: Efficient transformer for high-resolution image restoration. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 5718–5729, 2022.
  57. Practical blind image denoising via Swin-Conv-UNet and data synthesis. Machine Intelligence Research, 2023.
  58. Plug-and-Play image restoration with deep denoiser prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10):6360–6376, 2022.
  59. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing, 26(7):3142–3155, 2017.
  60. FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing, 27(9):4608–4622, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Paper to Video (Beta)

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up