BM3D-Net: A Convolutional Neural Network for Transform-Domain Collaborative Filtering

Dong, Yingshan; Sun, Jian

doi:10.1109/lsp.2017.2768660

Cited by 145 publications

(88 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are tested on 3 images of size256 × 256 (Cameraman, Peppers and Montage), and 7 images of size 512 × 512 (Lena, Barbara, Boat, fingerprint, Man, Couple, Hill. Here, the performance of the proposed approach is evaluated and compared it with the existing denoising methods, including NL Means based methods (BM3D [2], and WNNM [7] and training based methods DCNN [12],BMCNN [17]. Training and Testing Data:, Two noise levels, i.e., σ = 25 and 50 are considered to train model for Gaussian denoising with with a standard square patch size of 32.…”

Section: Resultsmentioning

confidence: 99%

“…[2] ,WNNN [7], DCNN [12], BMCNN [17], Proposed for sigma value 25 and 50.The proposed method performs well for the images cameraman, couple, fingerprint, Lena, Hill, Man and Peppers. Table 4 shows the visual results.…”

Section: Resultsmentioning

confidence: 99%

“…In contrast, the proposed approach recovers clear texture in both repetitive and non repetitive regions. Figure 1 shows the PSNR values in dB for image dataset as in table 8.3 for BM3D [2] ,WNNN [7], DCNN [12], BMCNN [17], Proposed for sigma value 50.The proposed method performs well for the images cameraman, couple, fingerprint, Lena, Hill, Man and Peppers.…”

Section: Resultsmentioning

confidence: 99%

“…Formresnet: Formatted residual learning for image restoration. In [17] authors proposed convolution Neural Networks for BM3D with residual and batch normalization and obtained promising results. Dong Yang and Jian Sun and et al [18] introduced Convolution network for BM3D and obtained good results.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Sparse Residual Learning of Deep Convolution Network for De-Noising Patch Based Block Match Three Dimension Algorithm

Kamalakshi¹

2018

IJRASET

View full text Add to dashboard Cite

This paper introduces a unique approach to de-noise an image based on concepts of Deep Convolution Neural Networks (DCNN) with sparse residual learning sparse reconstruction and batch normalization. The basic concept is modification of existing block match three dimension algorithm in which similar local patches in the input image are integrated into a 3D block. Here first patches are retrieved the features are extracted. The de-noised image is employed as a basic estimate for the block matching, and then de-noising function for the block is learned by a DCNN structure. Most of the residual network has many residual units (i.e., identity shortcuts), our method employs a single scarified residual unit to classify the residual image. Experimental results demonstrate the effectiveness of the sparse residual learning, sparse reconstruction and batch normalization in the tasks of image de-noising. Our experiment results proves that our model provide better efficiency in terms of PSNR. Keywords: Noise, patch, BM3D, sparse residual, sparse reconstruction batch normalization I. INTRODUCTIONRecently, image de-noising methods has gained popularity by a method called patch based method or non local means. This approach is measured an incredible in most of current state-of-the-art methods. The concept employed is to find related patterns that occur randomly all across the image and the image patches that have related patterns can be located far from each other. The patch based approach is a determining work that exploit this NSS prior [1]. The employment of patch based approach has boosted the performance of image de-noising significantly. The best example is the Block Matching and 3D Filtering (BM3D) method [2] which is a very good in performance and highly engineered approach that made the state-of-the-art record in image de-noising stay ahead for almost a decade. In past decade ,Machine learning is gaining popularity and progressively escalating its prominence. Among these deep learning concepts are overtaking shallow learning methods. It is a sort of overhyped. And very potential results have been noticed for image processing applications such as image restoration class. The significant improvement in the performance can be achieved by deep networks is due to their advanced modeling capabilities, deep structure and the adaption of non-linearities that in fact can be combined with qualified learning on large training datasets. Among all the deep learning methods, the convolutional neural networks have shown great performance for image processing tasks because of the reason of its quite easy access to large-scale dataset and the advances in deep learning methods. The proposed work is a modification of BM3D[2] [3][4] where CNN with sparse residual Learning ,sparse reconstruction and batch normalization It also adopts the residual learning formulation .

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Sparse Residual Learning of Deep Convolution Network for De-Noising Patch Based Block Match Three Dimension Algorithm

Kamalakshi¹

2018

IJRASET

View full text Add to dashboard Cite

show abstract

“…Also, they used 7 × 7 sized blocks for classification, but did not report or discuss the possible effects of choosing other block sizes. Lastly, even a very recent attempt at replacing parts of the BM3D pipeline with a CNN did not show potential for real-time performance, even using the fastest GPUs available in the market [32].…”

Section: Motivationmentioning

confidence: 99%

CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance

Mukherjee

Kottayil

Sun

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We propose a novel direction to improve the denoising quality of filtering-based denoising algorithms in real time by predicting the best filter parameter value using a Convolutional Neural Network (CNN). We take the use case of BM3D, the state-of-the-art filtering-based denoising algorithm, to demonstrate and validate our approach. We propose and train a simple, shallow CNN to predict in real time, the optimum filter parameter value, given the input noisy image. Each training example consists of a noisy input image (training data) and the filter parameter value that produces the best output (training label). Both qualitative and quantitative results using the widely used PSNR and SSIM metrics on the popular BSD68 dataset show that the CNN-guided BM3D outperforms the original, unguided BM3D across different noise levels. Thus, our proposed method is a CNN-based improvement on the original BM3D which uses a fixed, default parameter value for all images.

show abstract

Image Reconstruction Using Deep Learning

Christopher

Kishan

Sudeep

2022

Machine Learning Algorithms for Signal and Image Processing

View full text Add to dashboard Cite

BM3D-Net: A Convolutional Neural Network for Transform-Domain Collaborative Filtering

Cited by 145 publications

References 29 publications

Sparse Residual Learning of Deep Convolution Network for De-Noising Patch Based Block Match Three Dimension Algorithm

Sparse Residual Learning of Deep Convolution Network for De-Noising Patch Based Block Match Three Dimension Algorithm

CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance

Image Reconstruction Using Deep Learning

Contact Info

Product

Resources

About