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

Abstract

Abstract-Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. However, we pay for their high compression rate with visual artifacts degrading the user experience. Deep convolutional neural networks have become a widespread tool to address high-level computer vision tasks very successfully. Recently, they have found their way into the areas of low-level computer vision and image processing to solve regression problems mostly with relatively shallow networks.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 quality factor (QF) is resilient to the QF used to compress the input image-a single network trained for QF 60 provides a PSNR gain of more than 1.5 dB over the wide QF range from 40 to 76.

Deep Residual Autoencoder for Blind Universal JPEG Restoration

“…The first attempt with this kind of models has been done by Dong et al [9] who proposed the ARCNN, a model inspired by SRCNN [17], a neural network for Super-Resolution. This first attempt has been followed by DnCNN [10], a CNN for general denoising task that has also been used on JPEG compressed images, and CAS-CNN [11], a model proposed by Cavigelli et al, who presented a much deeper model capable to obtain higher quality images. Wang et al proposed D3 [12], a deep neural network that adopts JPEG-related priors to improve reconstruction quality which obtained an improvement in speed and performances with respect with to the previous models.…”

“…The results for the considered evaluation metrics over the five categories of the frequency and detail density are respectively reported in Table V and TABLE IV COMPARISON ON TEST SET CLASSIC-5: FOR THE METHODS IN THE STATE OF THE ART A FIVE DIFFERENT MODELS ARE TRAINED FOR EACH QF CONSIDERED. THE PROPOSED METHOD USES THE SAME MODEL FOR ALL THE QFS. Quality ARCNN [9] DnCNN [10] CAS-CNN [11] D3 [12] DMCNN [15] MWCNN [14] S-NET [16] ARGAN VI. From the results reported it is possible to notice that the proposed method consistently outperforms the state of the art on all the frequency and detail density categories.…”

AIM 2019 Challenge on Image Demoireing: Methods and Results

“…MBCNN not only removes the moire artifact, but also enhances the luminance of moire image. In practice, the method referenced the architecture of CAS-CNN [3] and proposes a 3-level multiscale bandpass convolutional neural network, hence the name MBCNN. MBCNN first uses pixel shuffle to reduce the input image resolution to half of original image.…”

S-Net: a scalable convolutional neural network for JPEG compression artifact reduction

“…Several researchers replaced the ReLU layer in networks with a parametric rectified linear unit (PReLU) 2,5,37 layer. PReLU imports a learnable parameter α to restrict the negative output, whereas ReLU compulsively cuts the negative output to zero E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 0 2 ; 6 3 ; 3 4 1 PRðxÞ ¼…”

“…However, these methods have several limitations. First, most existing methods 2,4,5 focus on the construction performance of grayscale images and try to restore each channel separately when applied to color images; however, this will introduce palpable chromatic aberrations in the reconstructed image (Fig. 1).…”