Xin Xia
ABSTRACT
Attention mechanism has shown great potential in image noise reduction tasks. We can choose different attention mechanisms according to different noise reduction tasks to enhance the ability of network to extract corresponding information. The problem of blurring and smoothing of the denoised image in the real image denoising task is considered. This paper recommends an attention depth fusion mechanism to solve this problem. It is different from the previous use of serial or parallel channels and spatial attention mechanisms to output features directly. After parallel connection, we use the shuffle operation to achieve cross channel communication and accelerate feature fusion of the two attention mechanisms. Then use a simple MLP module to perform cross direction channel attention calculation on the acquired spatial and channel attention features. And completing the deep fusion and feature interaction of spatial attention mechanisms and channel attention mechanisms. Final we use the Cross-attention to further enhance ability of the model to extract global feature and forward long semantic information.We name this module Pseudo 3D Attention. Finally, we conduct evaluations on real image denoising benchmarks including SIDD, DND, CC15, PolyU. We proposed method achieve competitive results. In particular, PSNR of 39.71dB and SSIM of 0.961 in SIDD is achieved without extra an train set.
- Hu, X., Ma, R., Liu, Z., Cai, Y., Zhao, X., Zhang, Y., & Wang, H. (2021). Pseudo 3D auto-correlation network for real image denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16175-16184).Google Scholar
Cross Ref
- Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., & Yang, M. (2021). Restormer: Efficient Transformer for High-Resolution Image Restoration. arXiv. https://doi.org/10.48550/arXiv.2111.09881.Google ScholarCross Ref
- Bishop C M, Nasrabadi N M. Pattern recognition and machine learning[M]. New York: springer, 2006.Google Scholar
- Buades A, Coll B, Morel J M. A non-local algorithm for image denoising[C]. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). IEEE, 2005, 2: 60-65.Google Scholar
- Dabov K, Foi A, Katkovnik V, Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on image processing, 2007, 16(8): 2080-2095.Google ScholarCross Ref
- Burger H C, Schuler C J, Harmeling S. Image denoising: Can plain neural networks compete with BM3D?[C].2012 IEEE conference on computer vision and pattern recognition. IEEE, 2012: 2392-2399.Google Scholar
- Mardani M, Sun Q, Donoho D, Neural proximal gradient descent for compressive imaging[J]. Advances in Neural Information Processing Systems, 2018, 31.Google Scholar
- Batson J, Royer L. Noise2self: Blind denoising by self-supervision[C].International Conference on Machine Learning. PMLR, 2019: 524-533.Google Scholar
- Dong W, Zhang L, Shi G, Nonlocally centralized sparse representation for image restoration[J]. IEEE transactions on Image Processing, 2012, 22(4): 1620-1630.Google Scholar
- Gu S, Zhang L, Zuo W, Weighted nuclear norm minimization with application to image denoising[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 2862-2869.Google Scholar
- Guo S, Yan Z, Zhang K, Toward convolutional blind denoising of real photographs[C].Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 1712-1722.Google Scholar
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing, 26(7):3142–3155, 2017Google ScholarDigital Library
- Zhang K, Zuo W, Zhang L. FFDNet: Toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622.Google ScholarCross Ref
- Ma K, Duanmu Z, Wu Q, Waterloo exploration database: New challenges for image quality assessment models[J]. IEEE Transactions on Image Processing, 2016, 26(2): 1004-1016.Google ScholarDigital Library
- Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C].International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234-241.Google Scholar
- ABSoft N. Neat image[J]. 2017.Google Scholar
- Lebrun M, Colom M, Morel J M. Multiscale image blind denoising[J]. IEEE Transactions on Image Processing, 2015, 24(10): 3149-3161.Google ScholarDigital Library
- Xu J, Zhang L, Zhang D. A trilateral weighted sparse coding scheme for real-world image denoising[C].Proceedings of the European conference on computer vision (ECCV). 2018: 20-36.Google Scholar
- Anwar S, Barnes N. Real image denoising with feature attention[C].Proceedings of the IEEE/CVF international conference on computer vision. 2019: 3155-3164.Google Scholar
- Yue Z, Yong H, Zhao Q, Variational denoising network: Toward blind noise modeling and removal[J]. Advances in neural information processing systems, 2019, 32.Google Scholar
- Yue Z, Zhao Q, Zhang L, Dual adversarial network: Toward real-world noise removal and noise generation[C].European Conference on Computer Vision. Springer, Cham, 2020: 41-58.Google Scholar
- Zamir S W, Arora A, Khan S, Cycleisp: Real image restoration via improved data synthesis[C] .Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 2696-2705.Google Scholar
- Zamir S W, Arora A, Khan S, Multi-stage progressive image restoration[C].Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 14821-14831.Google Scholar
- Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on signal processing, 2006, 54(11): 4311-4322.Google ScholarDigital Library
- Kim Y, Soh J W, Park G Y, Transfer learning from synthetic to real-noise denoising with adaptive instance normalization[C].Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 3482-3492.Google Scholar
- Chen Y, Pock T. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1256-1272.Google Scholar
- Kim J, Lee J K, Lee K M. Accurate image super-resolution using very deep convolutional networks[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1646-1654.Google Scholar
- Lefkimmiatis S. Universal denoising networks: a novel CNN architecture for image denoising[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 3204-3213.Google Scholar
- Tai Y, Yang J, Liu X, Memnet: A persistent memory network for image restoration[C].Proceedings of the IEEE international conference on computer vision. 2017: 4539-4547.Google Scholar
- Zamir S W, Arora A, Khan S, Learning enriched features for real image restoration and enhancement[C]//European Conference on Computer Vision. Springer, Cham, 2020: 492-511.Google Scholar
- Lebrun M, Colom M, Morel J M. The noise clinic: a blind image denoising algorithm[J]. Image Processing On Line, 2015, 5: 1-54.Google ScholarCross Ref
- Xu J, Li H, Liang Z, Real-world noisy image denoising: A new benchmark[J]. arXiv preprint arXiv:1804.02603, 2018.Google Scholar
- Cheng S, Wang Y, Huang H, Nbnet: Noise basis learning for image denoising with subspace projection[C].Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 4896-4906.Google Scholar
- Dosovitskiy A, Beyer L, Kolesnikov A, An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.Google Scholar
- Schmidt U, Roth S. Shrinkage fields for effective image restoration[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 2774-2781.Google Scholar
- Nam S, Hwang Y, Matsushita Y, A holistic approach to cross-channel image noise modeling and its application to image denoising[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1683-1691.Google Scholar
- 2016.He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv. https://doi.org/10.48550/arXiv.1512.03385Google ScholarCross Ref
- Mairal J, Bach F, Ponce J, Non-local sparse models for image restoration[C]. 2009 IEEE 12th international conference on computer vision. IEEE, 2009: 2272-2279.Google Scholar
- Wang Z, Bovik A C, Sheikh H R, Image quality assessment: from error visibility to structural similarity[J]. IEEE transactions on image processing, 2004, 13(4): 600-612.Google Scholar
- Plotz T, Roth S. Benchmarking denoising algorithms with real photographs[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1586-1595.Google Scholar
- Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image processing, 2006, 15(12): 3736-3745.Google ScholarDigital Library
- Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration[J]. IEEE Transactions on image processing, 2007, 17(1): 53-69.Google ScholarDigital Library
- Xu J, Zhang L, Zhang D, Multi-channel weighted nuclear norm minimization for real color image denoising[C]. Proceedings of the IEEE international conference on computer vision. 2017: 1096-1104.Google Scholar
- Chang M, Li Q, Feng H, Spatial-adaptive network for single image denoising[C]. European Conference on Computer Vision. Springer, Cham, 2020: 171-187.Google Scholar
- Chen H, Wang Y, Guo T, Pre-trained image processing transformer[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 12299-12310.Google Scholar
- Wang Z, Cun X, Bao J, Uformer: A general u-shaped transformer for image restoration[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 17683-17693.Google Scholar
- Fu J, Liu J, Tian H, Dual attention network for scene segmentation[C]. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 3146-3154.Google Scholar
- Vaswani, Ashish, "Attention is all you need." Advances in neural information processing systems 30 (2017).Google Scholar
- Tian, C., Xu, Y., Li, Z., Zuo, W., Fei, L., & Liu, H. (2020). Attention-guided CNN for image denoising. Neural Networks, 124, 117-129. https://doi.org/10.1016/j.neunet.2019.12.024Google ScholarDigital Library
- Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).Google ScholarDigital Library
- Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2019). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. arXiv. https://doi.org/10.48550/arXiv.1910.03151Google ScholarCross Ref
- Amin Tavakoli and Ali Pourmohammad, "Image Denoising Based on Compressed Sensing," International Journal of Computer Theory and Engineering vol. 4, no. 2, pp. 266-269, 2012.Google ScholarCross Ref
- Rakesh Kumar and B. S. Saini, "Improved Image Denoising Technique Using Neighboring Wavelet Coefficients of Optimal Wavelet with Adaptive Thresholding," International Journal of Computer Theory and Engineering vol. 4, no. 3, pp. 395-400, 2012.Google ScholarCross Ref
Index Terms
- Pseudo 3D-Attention for Real Image Denoising
Recommendations
Pseudo Ridgelet Transform for Image Denoising
ICIE '09: Proceedings of the 2009 WASE International Conference on Information Engineering - Volume 01Wavelet transforms have been successfully used in many scientific fields such as image denoising. Ridgelets is a new system of representations, which deals effectively with line singularities in 2-D. However, the discrete version of the ridgelet ...
Towards Boosting Channel Attention for Real Image Denoising: Sub-band Pyramid Attention
Image and GraphicsAbstractConvolutional layers treat the Channel features equally with no prioritization. When Convolutional Neural Networks (CNNs) are used for image denoising in real-world applications with unknown noise distributions, particularly structured noise with ...
A Multi-Head Convolutional Neural Network with Multi-Path Attention Improves Image Denoising
PRICAI 2022: Trends in Artificial IntelligenceAbstractRecently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image, limiting the ...
Comments