Multilevel Edge Features Guided Network for Image Denoising

Fang, Faming; Li, Juncheng; Yuan, Yiting; Zeng, Tieyong; Zhang, Guixu

doi:10.1109/tnnls.2020.3016321

Cited by 47 publications

(26 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we conduct extensive experiments to demonstrate the performance of the proposed denoising algorithm (TSLR). In addition, we compare our algorithm with some exsiting non-deep denoising algorithms, including BM3D [6], NCSR [5], SAIST [34], WNNM [12], LIIC [15], RM [16], BMLSVDTV [25], DPID [47], and deep learning-based denoising algorithms (e.g., Dn-CNN [19], FFDNet [44] and MLEFGN [45]). Three test datasets are used to evaluate the AWGN variance σ ∈ {10, 15, 25, 30, 50, 100}.…”

Section: Resultsmentioning

confidence: 99%

“…It is challenging for the denoising performance of non-deep methods to surpass that of deep learning-based methods. In this part, the proposed algorithm is compared with deep learning-based denoising algorithms (e.g., Dn-CNN [19], FFDNet [44] and MLEFGN [45]). The source codes of these methods are downloaded from the corresponding authors' websites, and we use the default parameter settings.…”

Section: Experimental Results Compared With Deep Learning-based Methodsmentioning

confidence: 99%

“…In recent years, as opposed to the above regularization methods using hand-crafted features for image modeling, deep learning-based methods [19,[43][44][45] can adaptively learn image representation models from large training data and then use the learned models for image denoising. These methods have achieved advanced results with the advent of deep convolutional neural networks (CNNs).…”

Section: Introductionmentioning

confidence: 99%

“…Most CNN-based methods aim to solve the problem by learning the mapping function between noisy and clean images. Considering the difficulty of learning accurate mapping, Fang et al [45] proposed an efficient multilevel edge features guided network (MLEFGN), which can make full use of edges predicted by Edge-Net to reconstruct high-quality noise-free images.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Two-Stage Image Denoising via an Enhanced Low-Rank Prior

Fan

Shi

et al. 2021

J Sci Comput

View full text Add to dashboard Cite

Restoring the image contaminated with heavy noise remains a challenging task. Since the image prior is essential to restoring a high-quality image, this paper proposes a novel twostage enhanced low-rank prior model (TSLR) for efficient image denoising. Unlike denoising an image as a whole, this algorithm divides the denoising process into two stages: contour restoration and detail restoration. First, we explore the total variation (TV) regularization term to restore the image contour, obtaining the preliminary denoised image. Although TV regularization term can reduce noise, it loses the rich details of the original image. Nevertheless, detail preservation ensures good visual quality of the denoised images. Then, to overcome the above issue, the preliminary denoised image is adopted as a rough evaluation of the original image for the second stage, and the weighted sum of the L 1 -norm and L 2 -norm is utilized as the fidelity term. Furthermore, we introduce a new enhanced low-rank prior, which combines the low-rank prior of similar patches from both gray and gradient domains, to reconstruct the fine details of the image. To further improve the validity of image denoising on the basis of the low-rank prior, the weighted nuclear norm minimization method is adopted in the present study. In addition, this work adaptively selects the search window size for different regions to accurately select similar patches. Through extensive experiments, the results reveal that our scheme can retain more detailed information while eliminating noise and can surpass a variety of advanced non-deep methods regarding both the PSNR and SSIM.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Experimental Results Compared With Deep Learning-based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Two-Stage Image Denoising via an Enhanced Low-Rank Prior

Fan

Shi

et al. 2021

J Sci Comput

View full text Add to dashboard Cite

show abstract

“…Recently, many CNN-based models Model Size Investigation on BSD68, Noise level=50 have been proposed for SID, especially for the Additive White Gaussian Noise (AWGN). Different from traditional methods, these methods [7,13,18,22,25,31,34,38] usually learn the mapping between noisy and clear images by building a well-designed CNN. For example, Zhang et al [38] proposed the first end-to-end trainable CNN model (DnCNN) for Gaussian denoising, which took the advantage of batch normalization and residual learning to recover clean images.…”

Section: Introductionmentioning

confidence: 99%

Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation

Li¹,

Yang²,

Yi³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning. However, the proposed methods are often accompanied by plenty of parameters, which greatly limits their application scenarios. Different from previous works that blindly increase the depth of the network, we explore the degradation mechanism of the noisy image and propose a lightweight Multiple Degradation and Reconstruction Network (MDRN) to progressively remove noise. Meanwhile, we propose two novel Heterogeneous Knowledge Distillation Strategies (HMDS) to enable MDRN to learn richer and more accurate features from heterogeneous models, which make it possible to reconstruct higher-quality denoised images under extreme conditions. Extensive experiments show that our MDRN achieves favorable performance against other SID models with fewer parameters. Meanwhile, plenty of ablation studies demonstrate that the introduced HMDS can improve the performance of tiny models or the model under high noise levels, which is extremely useful for related applications.

show abstract

Cartoon-Texture Features Guided Network for Low-Dose CT Denoising

Zhang,

Zhang

2024

Circuits Syst Signal Process

View full text Add to dashboard Cite

Multilevel Edge Features Guided Network for Image Denoising

Cited by 47 publications

References 56 publications

Two-Stage Image Denoising via an Enhanced Low-Rank Prior

Two-Stage Image Denoising via an Enhanced Low-Rank Prior

Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation

Cartoon-Texture Features Guided Network for Low-Dose CT Denoising

Contact Info

Product

Resources

About