Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Color Image Denoising Using The Green Channel Prior (2402.08235v1)

Published 13 Feb 2024 in eess.IV and cs.CV

Abstract: Noise removal in the standard RGB (sRGB) space remains a challenging task, in that the noise statistics of real-world images can be different in R, G and B channels. In fact, the green channel usually has twice the sampling rate in raw data and a higher signal-to-noise ratio than red/blue ones. However, the green channel prior (GCP) is often understated or ignored in color image denoising since many existing approaches mainly focus on modeling the relationship among image patches. In this paper, we propose a simple and effective one step GCP-based image denoising (GCP-ID) method, which aims to exploit the GCP for denoising in the sRGB space by integrating it into the classic nonlocal transform domain denoising framework. Briefly, we first take advantage of the green channel to guide the search of similar patches, which improves the patch search quality and encourages sparsity in the transform domain. Then we reformulate RGB patches into RGGB arrays to explicitly characterize the density of green samples. The block circulant representation is utilized to capture the cross-channel correlation and the channel redundancy. Experiments on both synthetic and real-world datasets demonstrate the competitive performance of the proposed GCP-ID method for the color image and video denoising tasks. The code is available at github.com/ZhaomingKong/GCP-ID.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (89)
  1. A high-quality denoising dataset for smartphone cameras. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 1692–1700, 2018.
  2. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process., 54(11):4311–4322, 2006.
  3. Real image denoising with feature attention. In Proc. IEEE Int. Conf. Comput. Vis., pages 3155–3164, 2019.
  4. Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans. Image Process., 18(11):2419–2434, 2009.
  5. A review of image denoising algorithms, with a new one. Multiscale Model. Simul., 4(2):490–530, 2005.
  6. Hyperspectral image restoration: Where does the low-rank property exist. IEEE Trans. Geosci. Remote Sens., 59(8):6869–6884, 2020.
  7. Hsi-denet: Hyperspectral image restoration via convolutional neural network. IEEE Trans. Geosci. Remote Sens., 57(2):667–682, 2018.
  8. Hyper-laplacian regularized unidirectional low-rank tensor recovery for multispectral image denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 4260–4268, 2017.
  9. Hyperspectral image restoration using weighted group sparsity-regularized low-rank tensor decomposition. IEEE Trans. Cybern., 50(8):3556–3570, 2019.
  10. A lossless compression scheme for bayer color filter array images. IEEE Trans. Image Process., 17(2):134–144, 2008.
  11. Videnn: Deep blind video denoising. In Proc. Conf. Comput. Vis. Pattern Recognit. Workshops, pages 0–0, 2019.
  12. Color image denoising via sparse 3d collaborative filtering with grouping constraint in luminance-chrominance space. In Proc. IEEE Int. Conf. Image Process., pages 313–316, 2007.
  13. Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. Image Process., 16(8):2080–2095, 2007.
  14. Bm3d image denoising with shape-adaptive principal component analysis. In Proc. Workshop on SPARS, pages 1–6, 2009.
  15. Multichannel nonlocal means fusion for color image denoising. IEEE Trans. Circuits Syst. Video Technol., 23(11):1873–1886, 2013.
  16. A non-local cnn for video denoising. In Proc. IEEE Conf. Int. Image Process., pages 2409–2413, 2019.
  17. Ideal spatial adaptation by wavelet shrinkage. biometrika, 81(3):425–455, 1994.
  18. Global patch search boosts video denoising. In Proc. Int. Conf. Comput. Vis. Theory Appl., volume 5, pages 124–134, 2017.
  19. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process., 15(12):3736–3745, 2006.
  20. Image denoising: The deep learning revolution and beyond–a survey paper–. arXiv preprint arXiv:2301.03362, 2023.
  21. Pointwise shape-adaptive dct for high-quality denoising and deblocking of grayscale and color images. IEEE Trans. Image Process., 16(5):1395–1411, 2007.
  22. Gigahertz-Optik. Spectral sensitivity of the human eye. https://light-measurement.com/spectral-sensitivity-of-eye.
  23. A low-rank tensor dictionary learning method for hyperspectral image denoising. IEEE Trans. Signal Process., 68:1168–1180, 2020.
  24. Joint denoising and demosaicking with green channel prior for real-world burst images. IEEE Trans. Image Process., 30:6930–6942, 2021.
  25. Toward convolutional blind denoising of real photographs. In Proc. Conf. Comput. Vis. Pattern Recognit., pages 1712–1722, 2019.
  26. Non-local meets global: An integrated paradigm for hyperspectral denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 6861–6870, 2019.
  27. Nlh: A blind pixel-level non-local method for real-world image denoising. IEEE Trans. Image Process., 29:5121–5135, 2020.
  28. Neighbor2neighbor: Self-supervised denoising from single noisy images. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 14781–14790, 2021.
  29. C2n: Practical generative noise modeling for real-world denoising. In Proc. IEEE Int. Conf. Comput. Vis., pages 2350–2359, 2021.
  30. Denoising by singular value decomposition and its application to electronic nose data processing. IEEE Sens. J., 11(1):35–44, 2010.
  31. Third-order tensors as operators on matrices: A theoretical and computational framework with applications in imaging. SIAM J. Matrix Anal. Appl., 34(1):148–172, 2013.
  32. Factorization strategies for third-order tensors. Linear Algebra Appl., 435(3):641–658, 2011.
  33. Transfer learning from synthetic to real-noise denoising with adaptive instance normalization. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 3482–3492, 2020.
  34. Tensor decompositions and applications. SIAM Rev., 51(3):455–500, 2009.
  35. A comparison of image denoising methods. arXiv preprint arXiv:2304.08990, 2023.
  36. Color image and multispectral image denoising using block diagonal representation. IEEE Trans. Image Process., 28(9):4247–4259, 2019.
  37. Mixed attention network for hyperspectral image denoising. arXiv preprint arXiv:2301.11525, 2023.
  38. Ap-bsn: Self-supervised denoising for real-world images via asymmetric pd and blind-spot network. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 17725–17734, 2022.
  39. Unidirectional video denoising by mimicking backward recurrent modules with look-ahead forward ones. In Proc. Eur. Conf. Comput. Vis., pages 592–609. Springer, 2022.
  40. Spatially adaptive self-supervised learning for real-world image denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2023.
  41. Image demosaicing: A systematic survey. In Vis. commun. image process., volume 6822, pages 489–503. SPIE, 2008.
  42. Swinir: Image restoration using swin transformer. In Proc. IEEE Int. Conf. Comput. Vis., pages 1833–1844, 2021.
  43. Recurrent video restoration transformer with guided deformable attention. Proc. Advances Neural Inf. Process. Syst., 35:378–393, 2022.
  44. Joint demosaicing and denoising with self guidance. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 2240–2249, 2020.
  45. Invertible denoising network: A light solution for real noise removal. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 13365–13374, 2021.
  46. A single model cnn for hyperspectral image denoising. IEEE Trans. Geosci. Remote Sens., 58(4):2516–2529, 2019.
  47. Video denoising, deblocking, and enhancement through separable 4-d nonlocal spatiotemporal transforms. IEEE Trans. Image Process., 21(9):3952–3966, 2012.
  48. Nonlocal transform-domain filter for volumetric data denoising and reconstruction. IEEE Trans. Image Process., 22(1):119–133, 2012.
  49. Image denoising using a compressive sensing approach based on regularization constraints. Sensors, 22(6):2199, 2022.
  50. Color image demosaicking: An overview. Signal Process. Image Commun., 26(8-9):518–533, 2011.
  51. A holistic approach to cross-channel image noise modeling and its application to image denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 1683–1691, 2016.
  52. Graph laplacian regularization for image denoising: Analysis in the continuous domain. IEEE Trans. Image Process., 26(4):1770–1785, 2017.
  53. Decomposable nonlocal tensor dictionary learning for multispectral image denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 2949–2956, 2014.
  54. Benchmarking denoising algorithms with real photographs. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 1586–1595, 2017.
  55. Self2self with dropout: Learning self-supervised denoising from single image. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 1890–1898, 2020.
  56. Image denoising using the higher order singular value decomposition. IEEE Trans. Pattern Anal. Mach. Intell., 35(4):849–862, 2012.
  57. Adaptive consistency prior based deep network for image denoising. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 8596–8606, 2021.
  58. Wavelet based image denoising technique. Int. J. Adv. Comput. Sci. Appl., 2(3), 2011.
  59. Unsupervised deep video denoising. In Proc. IEEE Int. Conf. Comput. Vis., pages 1759–1768, 2021.
  60. Robust tensor svd and recovery with rank estimation. IEEE Trans. Cybern., 52(10):10667–10682, 2021.
  61. Variational deep image restoration. IEEE Trans. Image Process., 31:4363–4376, 2022.
  62. Deep maximum a posterior estimator for video denoising. Int. J. Comput. Vis., 129:2827–2845, 2021.
  63. Dvdnet: A fast network for deep video denoising. In Proc. IEEE Conf. Int. Image Process., pages 1805–1809, 2019.
  64. Fastdvdnet: Towards real-time deep video denoising without flow estimation. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., June 2020.
  65. Multi-stage image denoising with the wavelet transform. Pattern Recognit., 134:109050, 2023.
  66. Graham Treece. Real image denoising with a locally-adaptive bitonic filter. IEEE Trans. Image Process., 31:3151–3165, 2022.
  67. Lucien Wald. Data fusion: definitions and architectures: fusion of images of different spatial resolutions. Les Presses de l’Ecoledes Mines, 2002.
  68. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process., 13(4):600–612, 2004.
  69. 3-d quasi-recurrent neural network for hyperspectral image denoising. IEEE Trans. Neural Netw. Learn. Syst., 2020.
  70. Vidosat: High-dimensional sparsifying transform learning for online video denoising. IEEE Trans. Image Process., 28(4):1691–1704, 2018.
  71. Real-world noisy image denoising: A new benchmark. arXiv preprint arXiv:1804.02603, 2018.
  72. A trilateral weighted sparse coding scheme for real-world image denoising. In Proc. Eur. Conf. Comput. Vis., pages 20–36, 2018.
  73. Multi-channel weighted nuclear norm minimization for real color image denoising. In Proc. IEEE Int. Conf. Comput. Vis., pages 1096–1104, 2017.
  74. Patch group based nonlocal self-similarity prior learning for image denoising. In Proc. IEEE Conf. Comput. Vis., pages 244–252, 2015.
  75. Transform domain image restoration methods: review, comparison, and interpretation. In Proc. Nonlinear Image Process. Pattern Anal. XII, volume 4304, pages 155–169, 2001.
  76. Deep iterative down-up cnn for image denoising. In Proc. Conf. Comput. Vis. Pattern Recognit. Workshops, 2019.
  77. Supervised raw video denoising with a benchmark dataset on dynamic scenes. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 2301–2310, 2020.
  78. High iso jpeg image denoising by deep fusion of collaborative and convolutional filtering. IEEE Trans. Image Process., 28(9):4339–4353, 2019.
  79. Determination of semi-arid landscape endmembers and seasonal trends using convex geometry spectral unmixing techniques. ratio, 4:22, 1990.
  80. Restormer: Efficient transformer for high-resolution image restoration. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 5728–5739, 2022.
  81. Cycleisp: Real image restoration via improved data synthesis. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 2696–2705, 2020.
  82. Learning enriched features for real image restoration and enhancement. In Proc. Eur. Conf. Comput. Vis., 2020.
  83. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans. Image Process., 26(7):3142–3155, 2017.
  84. Ffdnet: Toward a fast and flexible solution for cnn-based image denoising. IEEE Trans. Image Process., 27(9):4608–4622, 2018.
  85. Two-stage image denoising by principal component analysis with local pixel grouping. Pattern Recognit., 43(4):1531–1549, 2010.
  86. Hyperspectral image denoising with realistic data. In Proc. IEEE Int. Conf. Comput. Vis., pages 2248–2257, 2021.
  87. Joint image demosaicking and denoising with mutual guidance of color channels. Signal Process., 200:108674, 2022.
  88. Novel methods for multilinear data completion and de-noising based on tensor-svd. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pages 3842–3849, 2014.
  89. From learning models of natural image patches to whole image restoration. In Proc. IEEE Int. Conf. Comput. Vis., pages 479–486, 2011.

Summary

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

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