To address the limitation that existing learning-based image denoising algorithms struggle to preserve edges and textures, we propose an adaptive edge-aware denoising model built upon a multi-directional gradient network that can capture distinct image information separately. First, multi-directional gradient operators are applied to the clean target image to generate noise-free gradient maps, which then guide the network in learning gradient representations free from corruption. Second, an adaptive gradient-fusion module is introduced to fuse gradient cues with the noisy image adaptively, increasing the network’s attention to edge and texture details. Experimental results demonstrate that the proposed model achieves competitive PSNR and SSIM values. Moreover, the denoised images consistently exhibit superior visual quality, underscoring the model’s potential for practical image-denoising applications.
传统的基于非学习的图像去噪算法分为基于滤波和基于模型先验知识两类。基于滤波图像去噪算法主要包含中值滤波[1]、均值滤波[2]、非局部均值滤波[3]、三维块匹配协同滤波(Block-matching 3D collaborative filtering, BM3D)[4,5]等。基于模型先验知识图像去噪算法分为总变分[6-8]、稀疏表示[9-13]、低秩矩阵[14-18]等。这些方法通常将图像分成多个小区域块进行分块去噪,再合并为一个完整的图像。虽然这些方法简单易行,且在多种噪声场景下均具有一定去噪效果,但存在分块操作导致图像边缘模糊、图像整体过度平滑等问题。
假设噪声为零均值且噪声水平为的高斯噪声(Additive white gaussian noise, AWGN)。采用BSD400[35]和DIV2K[36]作为训练集,将训练数据随机裁剪为128×128的图像块,并进行旋转和水平翻转以增强训练样本。此外,采用Set12[37]、BSD68[38]及Urban100[39]数据集进行验证。
ChenT, MaK K, ChenL H. Tri-state median filter for image denoising[J]. IEEE Transactions on Image Processing, 1999, 8(12): 1834-1838.
[2]
ZhangX B, ZhangS L. Diffusion scheme using mean filter and wavelet coefficient magnitude for image denoising[J]. AEU-International Journal of Electronics and Communications, 2016, 70(7): 944-952.
[3]
BuadesA, CollB, MorelJ M. A non-local algorithm for image denoising[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, LISA, 2005: 60-65.
[4]
DabovK, FoiA, KatkovnikV, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095.
[5]
DabovK, FoiA, KatkovnikV, et al. Color image denoising via sparse 3D collaborative filtering with grouping constraint in luminance-chrominance space[C]∥IEEE International Conference on Image Processing, Piscataway, LISA, 2007: 313-I-6.
[6]
RudinL I, OsherS, FatemiE. Nonlinear total variation based noise removal algorithms[J]. Physica D: nonlinear Phenomena, 1992, 60(1-4): 259-268.
[7]
WeissY, FreemanW T. What makes a good model of natural images[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2007: 1-8.
EladM, AharonM. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image Processing, 2006, 15(12): 3736-3745.
[11]
MairalJ, EladM, SapiroG. Sparse representation for color image restoration[J]. IEEE Transactions on Image Processing, 2007, 17(1): 53-69.
[12]
XieQ, ZhaoQ, MengD Y, et al. Multispectral images denoising by intrinsic tensor sparsity regularization[C]. IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2016: 1692-1700.
ZhengYi-xian. Research on image denoising methods based on sparse representation theory[D]. Shanghai: School of Electronic Information and Electronical Engineering, Shanghai Jiao Tong University, 2013.
YinZhuang-chen. Research on image denoising based on sparse representation and dictionary learning [D]. Wuhan: School of Electronic Information Wuhan University of Technology, 2014.
[17]
GuS H, ZhangL, ZuoW M, et al. Weighted nuclear norm minimization with application to image denoising[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2014: 2862-2869.
[18]
XuJ, ZhangL, ZhangD, et al. Multi-channel weighted nuclear norm minimization for real color image denoising[C]∥IEEE International Conference on Computer Vision, Piscataway, USA, 2017: 1096-104.
[19]
XieT, LiS T, SunB. Hyperspectral images denoising via nonconvex regularized low-rank and sparse matrix decomposition[J]. IEEE Transactions on Image Processing, 2019, 29: 44-56.
[20]
JiaX X, FengX C, WangW W. Adaptive regularizer learning for low rank approximation with application to image denoising[C]∥IEEE International Conference on Image Processing, Piscataway, USA, 2016: 3096-3100.
WangZhen-ping. Research on image denoising algorithms based on low-rank matrix recovery[D]. Chengdu: School of Information Science and Technology, Southwest Jiaotong University, 2015.
[23]
XieJ Y, XuL L, ChenE H. Image denoising and inpainting with deep neural networks[C]∥Advances in Neural Information Processing Systems. Red Hcok, NY: Curran Associates, Inc., 2012: 341-349.
[24]
AgostinelliF, AndersonM R, LeeH. Adaptive multi-column deep neural networks with application to robust image denoising[C]∥Advances in Neural Information Processing Systems, Red Hcok, NY: Curran Associates, Inc., 2013: 1493-1501.
[25]
SivakumarK, DesaiU B. Image restoration using a multilayer perceptron with a multilevel sigmoidal function[J]. IEEE Transactions on Signal Processing, 1993, 41(5): 2018-2022.
[26]
BurgerH C, SchulerC J, HarmelingS. Image denoising: Can plain neural networks compete with BM3D[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2012: 2392-2399.
[27]
ZhouY T, ChellappaR, VaidA, et al. Image restoration using a neural network[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1988, 36(7): 1141-1151.
[28]
JainV, SeungH S. Natural image denoising with convolutional networks[C]∥Advances in Neural Information Processing Systems. Red Hcok, NY: Curran Associates, Inc., 2008, 21.
[29]
ChenY J, PockT. 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.
[30]
ZhangK, ZuoW M, ChenY J, et al. Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.
[31]
MaoX J, ShenC, YangY B. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections[C]∥Advances in Neural Information Processing Systems, Piscataway, USA, 2016: 379-387.
[32]
TaiY, YangJ, LiuX M, et al. MemNet: A persistent memory network for image restoration[C]∥IEEE International Conference on Computer Vision, Piscataway, USA, 2017: 4539-4547.
[33]
ZhangK, ZuoW, ZhangL. FFDNet: Toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622.
[34]
LiuD, WenB H, FanY C, et al. Non-local recurrent network for image restoration[C]∥Advances in Neural Information Processing Systems, Red Hcok, NY: Curran Associates, Inc., 2018: 1673-1682.
[35]
PlötzT, RothS. Neural nearest neighbors networks[C]∥Advances in Neural Information Processing Systems, Red Hcok, NY: Curran Associates, Inc., 2018: 1095-1106.
[36]
CharbonnierP, Blanc-FeraudL, AubertG, et al. Two deterministic half-quadratic regularization algorithms for computed imaging[C]∥Proceedings of 1st International Conference on Image Processing, Piscataway, USA, 1994, 2: 168-172.
[37]
KingmaD P, BaJ.Adam: a method for stochastic optimization[J]. Computer Science, 2014: 1-15.
[38]
WangZ, BovikA C, SheikhH R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[39]
MartinD, FowlkesC, TalD, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]∥Proceedings Eighth IEEE International Conference on Computer Vision, Piscataway, USA,2001: 416-423.
[40]
TimofteR, AgustssonE, Van GoolL, et al. Ntire 2017 challenge on single image super-resolution: Methods and results[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Piscataway, USA, 2017: 114-125.
[41]
ZhangK, ZuoW M, ChenY J, et al. Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.
[42]
RothS, BlackM J. Fields of experts[J]. International Journal of Computer Vision, 2009, 82: 205-229.
[43]
HuangJ B, SinghA, AhujaN. Single image super-resolution from transformed self-exemplars[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Piscataway,USA, 2015: 5197-5206.
[44]
QiaoS, YangJ R, ZhangT, et al. Layered input GradiNet for image denoising[J]. Knowledge-Based Systems, 2022, 254: No.109587.
[45]
TianC W, ZhengM H, ZuoW M, et al. Multi-stage image denoising with the wavelet transform[J]. Pattern Recognition, 2023, 134(1): No.109050.
[46]
WuW C, LiuS J, XiaY, et al. Dual residual attention network for image denoising[J]. Pattern Recognition, 2024, 149: No.110291.