Abstract Artifacts on sharp edges are easily generated when the dilated convolutional neural network(CNN) is utilized in the existing image denoising methods based on deep learning. Moreover, multiple specific denoising models are required to be trained to deal with different noise levels. Aiming at these problems, a Gaussian denoising method with tunable noise level based on dilated CNN is proposed. A noise level map is employed to make the noise level tunable. Besides, the improved dilated CNN and the reversible downsampling technology are employed, and thus the problem of artifacts on sharp edges caused by traditional dilated CNN is alleviated. The downsampled sub-images and corresponding noise level map are input into the nonlinear mapping model. Then, the model is trained by the improved CNN with the dilated rate reduced. Experiments show that the proposed method gains GPU acceleration and the ability of adjusting the noise level with the artifacts on sharp edges improved and more image details retained.
Fund:National Natural Science Foundation of China(No.61873176)
Corresponding Authors:
YU Lei, Ph.D., professor. His research interests include artificial intelligence and 3D reconstruction.
About author:: JIN Yifan, master student. His research interests include visual SALM, deep learning and 3D reconstruction. FEI Shumin, Ph.D., professor. His research interests include artificial intelligence and nonlinear system.
[1] TIAN C W, FEI L K, ZHENG W X, et al. Deep Learning on Image Denoising: An Overview. Neural Networks, 2020, 131: 251-275. [2] 邵 杭,王永雄.基于并行对抗与多条件融合的生成式高分辨率图像修复.模式识别与人工智能, 2020, 33(4): 363-374. (SHAO H, WANG Y X. Generative High-Resolution Image Inpain-ting with Parallel Adversarial Network and Multi-condition Fusion. Pattern Recognition and Artificial Intelligence, 2020, 33(4): 363-374.) [3] 高青青,赵建伟,周正华.基于递归多尺度卷积网络的图像超分辨率重建.模式识别与人工智能, 2020, 33(11): 972-980. (GAO Q Q, ZHAO J W, ZHOU Z H. Image Super-Resolution Reconstruction Based on Recursive Multi-scale Convolutional Networks. Pattern Recognition and Artificial Intelligence, 2020, 33(11): 972-980.) [4] 温立民,巨永锋,闫茂德.基于自然统计特征分布的交通图像雾浓度检测.电子学报, 2017, 45(8): 1888-1895. (WEN L M, JU Y F, YAN M D. Inspection of Fog Density for Tra-ffic Image Based on Distribution Characteristics of Natural Statistics. Acta Electronica Sinica, 2017, 45(8): 1888-1895.) [5] IGNATOV A, BYEOUNG-SU K, TIMOFTE R, et al. Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report[C/OL]. [2021-04-27]. https://arxiv.org/pdf/2105.08629.pdf. [6] DUGAD R, AHUJA N. Video Denoising by Combining Kalman and Wiener Estimates // Proc of the International Conference on Image Processing(Cat.99CH36348). Washington, USA: IEEE, 1999, IV: 152-156. [7] SONG J Y, LIU Q H, JOHNSON G A, et al. Sparseness Prior Based Iterative Image Reconstruction for Retrospectively Gated Cardiac Micro-CT. Medical Physics, 2007, 34(11): 4476-4483. [8] XU J, ZHANG L, ZUO W M, et al. Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 244-252. [9] LOUPAS T, MCDICKEN W N, ALLAN P L. An Adaptive Weighted Median Filter for Speckle Suppression in Medical Ultrasonic Images. IEEE Transactions on Circuits and Systems, 1989, 36(1): 129-135. [10] SARDY S, TSENG P, BRUCE A. Robust Wavelet Denoising. IEEE Transactions on Signal Processing, 2001, 49(6): 1146-1152. [11] 倪志伟,刘 浩,朱旭辉,等.基于深度强化学习的空间众包任务分配策略.模式识别与人工智能, 2021, 34(3): 191-205. (NI Z W, LIU H, ZHU X H, et al. Task Allocation Strategy of Spatial Crowdsourcing Based on Deep Reinforcement Learning. Pattern Recognition and Artificial Intelligence, 2021, 34(3): 191-205.) [12] 张铭津,彭晓琪,郭 杰,等.基于多残差网络的结构保持超分辨重建.模式识别与人工智能, 2021, 34(3): 232-240. (ZHANG M J, PENG X Q, GUO J, et al. Structure-Preserving Super-Resolution Reconstruction Based on Multi-residual Network. Pattern Recognition and Artificial Intelligence, 2021, 34(3): 232-240.) [13] TIAN C W, XU Y, LI Z Y, et al. Attention-Guided CNN for Image Denoising. Neural Networks, 2020, 124: 117-129. [14] 罗会兰,张 云.基于深度网络的图像语义分割综述.电子学报, 2019, 47(10): 2211-2220. (LUO H L, ZHANG Y. A Survey of Image Semantic Segmentation Based on Deep Network. Acta Electronica Sinica, 2019, 47(10): 2211-2220.) [15] JAIN V, SEUNG S. Natural Image Denoising with Convolutional Networks // Proc of the 21st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2009: 769-776. [16] BURGER H C, SCHULER C J, HARMELING S. Image Denoi-sing: Can Plain Neural Networks Compete with BM3D? // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2392-2399. [17] MAO X J, SHEN C H, YANG Y B. Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections // Proc of the 30th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2016: 2810-2818. [18] CHEN Y J, POCK T. Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1256-1272. [19] ZHANG K, ZUO W M, CHEN Y J, et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155. [20] LEFKIMMIATIS S. Non-local Color Image Denoising with Convolutional Neural Networks // Proc of the IEEE Conference on Compu-ter Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 3587-3596. [21] LEFKIMMIATIS S. Universal Denoising Networks: A Novel CNN Architecture for Image Denoising // Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 3204-3213. [22] GUO S, YAN Z F, ZHANG K, et al. Toward Convolutional Blind Denoising of Real Photographs // Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 1712-1722. [23] ZHANG K, ZUO W M, ZHANG L. FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622. [24] DABOV K, FOI A, KATKOVNIK V, et al. Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095. [25] GU S H, ZHANG L, ZUO W M, et al. Weighted Nuclear Norm Minimization with Application to Image Denoising // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 2862-2869. [26] ZHANG K, ZUO W M, GU S H, et al. Learning Deep CNN Denoiser Prior for Image Restoration // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2808-2817. [27] YANG Z C, HU Z T, SALAKHUTDINOV R, et al. Improved Va-riational Autoencoders for Text Modeling Using Dilated Convolutions // Proc of the 34th International Conference on Machine Learning. New York, USA: ACM, 2017: 3881-3890. [28] IOFFE S, SZEGEDY C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift // Proc of the 32nd International Conference on Machine Learning. New York, USA: ACM, 2015: 448-456. [29] CHEN X, ZHAN S, JI D, et al. Image Denoising via Deep Network Based on Edge Enhancement[C/OL]. [2021-04-27]. https://link.springer.com/content/pdf/10.1007/s12652-018-1036-4.pdf. [30] ZARSHENAS A, SUZUKI K. Deep Neural Network Convolution for Natural Image Denoising // Proc of the IEEE International Conference on Systems, Man, and Cybernetics. Washington, USA: IEEE, 2018: 2534-2539. [31] CHO S I, KANG S J. Gradient Prior-Aided CNN Denoiser with Separable Convolution-Based Optimization of Feature Dimension. IEEE Transactions on Multimedia, 2019, 21(2): 484-493.
2021, Vol. 34 
