Toward Convolutional Blind Denoising of Real Photographs

@article{Guo2019TowardCB,
  title={Toward Convolutional Blind Denoising of Real Photographs},
  author={Shi Guo and Zifei Yan and K. Zhang and Wangmeng Zuo and Lei Zhang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={1712-1722}
}
  • Shi Guo, Zifei Yan, +2 authors Lei Zhang
  • Published 12 July 2018
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. [...] Key Method On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet.Expand
A Simple and Robust Deep Convolutional Approach to Blind Image Denoising
TLDR
Experimental results demonstrate that the proposed blind denoiser achieves fairly competitive or even better performance than state-of-the-art algorithms in terms of both quantitative and qualitative assessment. Expand
Learning Blind Pixelwise Affine Image Denoiser With Single Noisy Images
TLDR
Blind Pixelwise Affine Image DEnoiser (BP-AIDE) is proposed, which can be blindly trained solely with single real-noise corrupted images and first outperforms both CNN-based and conventional denoisers for the same setting, on several real-world noisy image benchmark datasets. Expand
Pyramid Real Image Denoising Network
TLDR
A novel pyramid real image denoising network (PRIDNet), which contains three stages, which uses channel attention mechanism to recalibrate the channel importance of input noise and adopts a kernel selecting operation to adaptively fuse multi-scale features. Expand
CycleISP: Real Image Restoration via Improved Data Synthesis
TLDR
This paper presents a framework that models camera imaging pipeline in forward and reverse directions that allows any number of realistic image pairs for denoising both in RAW and sRGB spaces and achieves the state-of-the-art performance on real camera benchmark datasets. Expand
Deep Universal Blind Image Denoising
  • Jae Woong Soh, N. Cho
  • Computer Science
  • 2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
TLDR
A CNN-based method that can successfully remove blind and real-world noise, with a moderate number of parameters of universal CNN, rooted in CNNs and proposed a novel design of network for efficient inference is presented. Expand
Real Image Denoising With Feature Attention
  • Saeed Anwar, N. Barnes
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
A novel single-stage blind real image denoising network (RIDNet) is proposed by employing a modular architecture that uses residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Expand
Reconstructing the Noise Variance Manifold for Image Denoising
TLDR
This work introduces the idea of a cGAN which explicitly leverages structure in the image noise variance space, and substantially outperforms existing state-of-the-art architectures, resulting in denoised images with less over-smoothing and better detail. Expand
Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising
TLDR
Extensive quantitative and qualitative evaluations spanning multiple metrics and four highresolution real-world noisy image datasets against the state-ofthe-art deep CNN network, DnCNN, reveal that deep Self-ONNs consistently achieve superior results with performance gains of up to 1.76dB in PSNR. Expand
Reconstructing the Noise Manifold for Image Denoising
TLDR
This work introduces the idea of a cGAN which explicitly leverages structure in the image noise space, and substantially outperforms existing state-of-the-art architectures, resulting in denoised images with less oversmoothing and better detail. Expand
NERNet: Noise estimation and removal network for image denoising
TLDR
A novel network including noise estimation module and removal module (NERNet), which adaptively fuses features from convolution layers with different dilation rates, but also aggregates the global and local information, which is benefit to preserving more details and textures. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 73 REFERENCES
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance. Expand
Image Blind Denoising with Generative Adversarial Network Based Noise Modeling
TLDR
A novel two-step framework is proposed, in which a Generative Adversarial Network is trained to estimate the noise distribution over the input noisy images and to generate noise samples to train a deep Convolutional Neural Network for denoising. Expand
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
TLDR
The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance, and enjoys several desirable properties, including the ability to handle a wide range of noise levels effectively with a single network. Expand
Benchmarking Denoising Algorithms with Real Photographs
  • Tobias Plötz, S. Roth
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This work develops a methodology for benchmarking denoising techniques on real photographs, and captures pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference. Expand
A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising
TLDR
This paper develops a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising and introduces three weight matrices into the data and regularization terms of the sparse coding framework to characterize the statistics of realistic noise and image priors. Expand
Natural Image Denoising with Convolutional Networks
TLDR
An approach to low-level vision is presented that combines the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models to avoid computational difficulties in MRF approaches that arise from probabilistic learning and inference. Expand
From Noise Modeling to Blind Image Denoising
TLDR
A novel blind image denoising algorithm which can cope with real-world noisy images even when the noise model is not provided is proposed, realized by modeling image noise with mixture of Gaussian distribution (MoG) which can approximate large varieties of continuous distributions. Expand
Image Denoising and Inpainting with Deep Neural Networks
TLDR
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Expand
Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
TLDR
This paper proposes a multi-channel (MC) optimization model for real color image denoising under the weighted nuclear norm minimization (WNNM) framework, concatenate the RGB patches to make use of the channel redundancy, and introduces a weight matrix to balance the data fidelity of the three channels in consideration of their different noise statistics. Expand
Multiscale Image Blind Denoising
TLDR
This work proposes here a multiscale denoising algorithm adapted to this broad noise model, which is demonstrated on real JPEG images and on scans of old photographs for which the formation model is unknown, and is compared with the unique state of the art previous blind Denoising method. Expand
...
1
2
3
4
5
...