A Hybrid CNN for Image Denoising
Open accessAbstract
Deep convolutional neural networks (CNNs) with strong learning abilities have been used in the field of image super-resolution. However, some CNNs depends on a single deep network to training an image super-resolution model, which will have poor performance in complex screens. To address this problem, we propose a hybrid denoising CNN (HDCNN). HDCNN is composed of a dilated block (DB), RepVGG block (RVB) and feature refinement block (FB), a single convolution. DB combines a dilated convolution, batch normalization (BN), common convolutions, activation function of ReLU to obtain more context information. RVB uses parallel combination of convolution and BN, ReLU to extract complementary width features. FB is used to obtain more accurate information via refining obtained feature from the RVB. A single convolution collaborates a residual learning operation to construct a clean image. These key components make the HDCNN have good performance in image denoising. Experiment shows that the proposed HDCNN enjoys good denoising effect in public datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Restricted Boltzmann Machines (RBN) act as the fundamental building blocks for the creation of DBN.
“For the creation of DBN, Restricted Boltzmann Machines (RBN) act as the fundamental building blocks [103].”
From Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences (2023) · cites this paper as [103]
The Introduction and §III.A (Network Architecture; page unavailable) describe a convolutional image-denoising network, not a deep belief network. Searches for Restricted Boltzmann Machines and deep belief networks found no passage in our copy addressing whether the former are building blocks of the latter. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Weighted Nuclear Norm Minimization with Application to Image Denoising
Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.366 · Cited by 2,316 · see citing works
Learning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116 · cited 3× · see citing works
“Methods BM3D[35] WNNM[36] EPLL[37] TNRD[38] DnCNN[10] IRCNN[39] FFDNet[13] ECNDNet[28] HDCNN HDCNN-B σ = 15 31.”
MethodImage Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study
Sara, U., Akter, M., & Uddin, M. S. (2019) · Journal of Computer and Communications · doi:10.4236/jcc.2019.73002 · Cited by 1,689 · cited 2× · see citing works
“The HDCNN is trained by the loss function of mean square error (MSE) [31] and training pairs fIn,ICg, where In and IC denote the ith noisy image and reference clean image, i = 1,2,3,4, : : :N and N”
MethodAttention-guided CNN for image denoising
Tian, C., Xu, Y., Li, Z., Zuo, W., Fei, L., & Liu, H. (2020) · Neural Networks · doi:10.1016/j.neunet.2019.12.024 · Cited by 688 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 31
- C. Tian, Y. Xu, and W. Zuo, "Image denoising using deep CNN with batch renormalization," Neural Netw., vol. 121, pp. 461-473, 2020.
- B. Gupta and S. S. Negi, "Image denoising with linear and non-linear filters: a review," Int. J. Comput. Sci. Issues (IJCSI), vol. 10, no. 6, p. 149, 2013.
- F. Xiao and Y. Zhang, "A comparative study on thresholding methods in wavelet-based image denoising," Procedia Eng., vol. 15, pp. 3998-4003, 2011.
- M. C. Motwani, M. C. Gadiya, R. C. Motwani, et al. Survey of image denoising techniques," in Proc. GSPX, vol. 27, pp. 27-30, 2004.
- C. Tian, L. Fei, W. Zheng, et al. "Deep learning on image denoising: An overview," Neural Netw., vol. 131, pp. 251-275, 2020.
- S. Arivazhagan, S. Deivalakshmi, K. Kannan, et al. "Performance analysis of wavelet filters for image denoising," Adv. Comput. Sci. Technol., vol. 1, no. 1, pp. 1-10, 2007.
- L. Zhang and W. Zuo, "Image restoration: From sparse and low-rank priors to deep priors [lecture notes]," IEEE Signal Process. Mag., vol. 34, no. 5, pp. 172-179, 2017.
- A. Wong, A. Mishra, W. Zhang, et al. "Stochastic image denoising based on markov-chain monte carlo sampling," Signal Process., l. 91, no. 8, pp. 2112-2120, 2011.
- K. Zhang, W. Zuo, Y. Chen, et al. "Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising," IEEE Trans. Image Process., vol. 26, no. 7, pp. 3142-3155, 2017.
- S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in Int. Conf. Mach. Learn., PMLR, pp. 448-456, 2015.
- K. Zhang, W. Zuo, and L. Zhang, "FFDNet: Toward a fast and flexible solution for CNN-based image denoising," IEEE Trans. Image Process., vol. 27, no. 9, pp. 4608-4622, 2018.
- C. Tian, Y. Xu, W. Zuo, et al. "Designing and training of a dual CNN for image denoising," Knowl. Based Syst., vol. 226, p. 106949, 2021.
- C. Tian, Y. Xu, W. Zuo, et al. "Asymmetric CNN for image superresolution," IEEE Trans. Syst., Man Cybern. Syst., vol. 52, no. 6 pp. 3718-3730, 2021. DOI: 10.1109/TSMC.2021. 3069265. · DOI
- S. Lefkimmiatis, "Universal denoising networks: a novel CNN architecture for image denoising," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 3204-3213, 2018.
- R. Lan, H. Zou, C. Pang, et al. "Image denoising via deep residual convolutional neural networks," Signal, Image Video Process., vol. 15, no. 1, pp. 1-8, 2021.
- W. Shi, F. Jiang, S. Zhang, et al. "Hierarchical residual learning for image denoising," Signal Process. Image Commun., vol. 76, pp. 243- 251, 2019.
- S. Gai and Z. Bao, "New image denoising algorithm via improved deep convolutional neural network with perceptive loss," Exp. Syst. Appl., vol. 138, p. 112815, 2019.
- P. Liu, H. Zhang, K. Zhang, et al. "Multi-level wavelet-CNN for image restoration," in Proc. IEEE Conf. Comput. Vis. Pattern Re- cogn. Workshops, pp. 773-782, 2018.
- A. Sengupta, Y. Ye, R. Wang, et al. "Going deeper in spiking neural networks: VGG and residual architectures," Front. Neurosci., vol. 13, p. 95, 2019.
- C. Szegedy, W. Liu, Y. Jia, et al. "Going deeper with convolu- tions," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 1-9, 2015.
- X. Ding, X. Zhang, N. Ma, et al. "Repvgg: making vgg-style convnets great again," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recogn., pp. 13733-13742, 2021.
- F. Yu and V. Koltun, "Multi-scale context aggregation by dilated convolutions," arXiv preprint arXiv:1511.07122, 2015. · arXiv
- C. Xu, C. Shi, and Y. Chen, "End-to-end dilated convolution network for document image semantic segmentation," J. Cent South Univ., vol. 28, no. 6, pp. 1765-1774, 2021.
- T. Wang, M. Sun, and K. Hu, "Dilated deep residual network for image denoising," in 2017 IEEE 29th Int. Conf. Tools Artif. Intell. (ICTAI), IEEE, pp. 1272-1279, 2017.
- C. Tian, Y. Xu, L. Fei, et al. "Enhanced CNN for image denoising," CAAI Trans. Intell. Technol., vol. 4, no. 1, pp. 17-23, 2019.
- N. T. Trung, D. H. Trinh, N. L. Trung, et al. "Dilated residual convolutional neural networks for low-dose CT image denoising," in 2020 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), IEEE, pp. 189-192, 2020.
- D. Martin, C. Fowlkes, D. Tal, et al. "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics," in Proc. Eighth IEEE Int. Conf. Comput. Vis., ICCV, IEEE, 2001, vol. 2, pp. 416- 423, 2001.
- K. He, X. Zhang, S. Ren, et al. "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification," in Proc. IEEE Int. Conf. Comput. Vis., pp. 1026-1034, 2015.
- K. Dabov, A. Foi, V. Katkovnik, et al. "Image denoising by sparse 3- D transform-domain collaborative filtering," IEEE Trans. Image Process., vol. 16, no. 8, pp. 2080-2095, 2007.
- D. Zoran and Y. Weiss, "From learning models of natural image patches to whole image restoration," in 2011 Int. Conf. Comput. Vis., IEEE, pp. 479-486, 2011.
- Y. Chen and T. Pock, "Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1256-1272, 2016.
Cited by
Sorted by citations
Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences
Al Mudawi, N., Qureshi, A. M., Abdelhaq, M., Alshahrani, A., Alazeb, A., Alonazi, M., & Algarni, A. (2023) · Sustainability · doi:10.3390/su151914597 · Cited by 68 · see citing works
- Authors
- Zheng, M., Zhi, K., Zeng, J., Tian, C., & You, L.
- Affiliations
- Northwestern Polytechnical University (CN)
- Venue
- Journal of Artificial Intelligence and Technology
- Published
- 2022-04-11
- ISSN
- 2766-8649 (ISSN-L)
- OpenAlex
- W4223523758
- Cited by
- 83
- References
- 7
- Citations by year
- 2026: 4 · 2025: 15 · 2024: 28 · 2023: 29 · 2022: 7
- FWCI
- 6.47
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Journal of Artificial Intelligence and Technology (publishedVersion, cc-by)
- Funders
- Fundamental Research Funds for the Central Universities (D5000210966)
- Basic and Applied Basic Research Foundation of Guangdong Province (2021A1515110079)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Keywords
- image denoising, hybrid convolutional neural network, dilated convolution, RepVGG, feature refinement, residual learning, image super-resolution
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
