CAS-CNN: A deep convolutional neural network for image compression artifact suppression

@article{Cavigelli2017CASCNNAD,
  title={CAS-CNN: A deep convolutional neural network for image compression artifact suppression},
  author={L. Cavigelli and P. Hager and L. Benini},
  journal={2017 International Joint Conference on Neural Networks (IJCNN)},
  year={2017},
  pages={752-759}
}
Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. [...] Key Method We present a novel 12-layer deep convolutional network for image compression artifact suppression with hierarchical skip connections and a multi-scale loss function. We achieve a boost of up to 1.79 dB in PSNR over ordinary JPEG and an improvement of up to 0.36 dB over the best previous ConvNet result. We show that a network trained for a specific…Expand
Dmcnn: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
TLDR
It is illustrated that the quality of output images can be significantly improved by enlarging the receptive fields in many cases, and a Dual-domain Multi-scale CNN (DMCNN) to take full advantage of redundancies on both the pixel and DCT domains is proposed. Expand
S-Net: a scalable convolutional neural network for JPEG compression artifact reduction
TLDR
Experimental results indicate that the proposed S-Net CNN outperforms other CNN-based methods and achieves state-of-the-art performance. Expand
Learning a Virtual Codec Based on Deep Convolutional Neural Network to Compress Image
TLDR
An end-to-end image compression framework based on convolutional neural network to resolve the problem of non-differentiability of the quantization function in the standard codec and an advanced learning algorithm is proposed to train the deep neural networks for compression. Expand
SF-CNN: A Fast Compression Artifacts Removal via Spatial-To-Frequency Convolutional Neural Networks
TLDR
SF-CNN, a fast convolutional neural network structure for JPEG image compression artifacts removal that takes Spatial input and predicts residual Frequency using downsampling operations only is proposed. Expand
Artifacts Reduction for Compression Image with Pyramid Residual Convolutional Neural Network
A pyramid residual convolutional neural network (PRCNN) is proposed to restore image with compression artifacts in this paper, and the method is enable to process multiple resolutions by fixing patchExpand
Dual-Stream Multi-Path Recursive Residual Network for JPEG Image Compression Artifacts Reduction
TLDR
A dual-stream recursive residual network (STRRN) which consists of structure and texture streams for separately reducing the specific artifacts related to high-frequency or low-frequency image components and which reduces the total number of training parameters significantly. Expand
Blind compression artifact reduction using dense parallel convolutional neural network
TLDR
A novel deep neural network with densely connected parallel convolutions to remove compression artifacts generated at any quality factor (QF) and to recover the original image from its perturbed version is introduced. Expand
Learning a Single Model With a Wide Range of Quality Factors for JPEG Image Artifacts Removal
TLDR
The proposed network is a single model approach that can be trained for handling a wide range of quality factors while consistently delivering superior or comparable image artifacts removal performance. Expand
Deep Multi-Scale Residual Learning-based Blocking Artifacts Reduction for Compressed Images
TLDR
A deep learning-based compression artifacts reduction (or deblocking) framework relying on multi-scale residual learning that can be successfully removed by subtracting the predicted artifacts from the input image while preserving most original visual details. Expand
Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks
TLDR
A end-to-end mixed-resolution image compression framework with convolutional neural networks that has a large margin improvement, when comparing with several state-of-the-art approaches. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
Deep Convolution Networks for Compression Artifacts Reduction
TLDR
A compact and efficient network for seamless attenuation of different compression artifacts and shows superior performance than the state-of-the-art methods both on benchmark datasets and a real-world use case. Expand
Compression Artifacts Reduction by a Deep Convolutional Network
TLDR
A compact and efficient network for seamless attenuation of different compression artifacts is formulated and it is demonstrated that a deeper model can be effectively trained with the features learned in a shallow network. Expand
Compression Artifacts Removal Using Convolutional Neural Networks
This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly betterExpand
Learning a Deep Convolutional Network for Image Super-Resolution
TLDR
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. Expand
Building Dual-Domain Representations for Compression Artifacts Reduction
TLDR
This work proposes a highly accurate approach to remove artifacts of JPEG-compressed images that jointly learns a very deep convolutional network in both DCT and pixel domains and shows large improvements over the state of the arts. Expand
D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
In this paper, we design a Deep Dual-Domain (D3) based fast restoration model to remove artifacts of JPEG compressed images. It leverages the large learning capacity of deep networks, as well as theExpand
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Reducing Artifacts in JPEG Decompression Via a Learned Dictionary
TLDR
A novel artifact reducing approach for the JPEG decompression is proposed via sparse and redundant representations over a learned dictionary, and an effective two-step algorithm is developed that outperforms the total variation and weighted total variation decompression methods. Expand
Pointwise shape-adaptive DCT for high-quality deblocking of compressed color images
TLDR
The SA-DCT filtering used for the chrominance channels allows to faithfully reconstruct the missing structural information of the chrominances, thus correcting color-bleeding artifacts, and the visual quality of the estimates is high, with sharp detail preservation, clean edges. Expand
Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art
TLDR
This work introduces a powerful non-parametric image restoration framework based on Regression Tree Fields (RTF), a densely-connected tractable conditional random field that leverages existing methods to produce an image-dependent, globally consistent prediction. Expand
...
1
2
3
4
5
...