Published on Mon Jul 08 2019

Fully Convolutional Network for Removing DCT Artefacts From Images

Patryk Najgebauer, Rafal Scherer, Leszek Rutkowski

Image compression is one of the essential methods of image processing. Lossy compression is associated with the loss of some image details in favor of reducing its size. In this article, we propose three models of fully convolutional networks with different configurations.

0
0
0
Abstract

Image compression is one of the essential methods of image processing. Its most prominent advantage is the significant reduction of image size allowing for more efficient storage and transfer. However, lossy compression is associated with the loss of some image details in favor of reducing its size. In compressed images, the deficiencies are manifested by noticeable defects in the form of artifacts; the most common are block artifacts, ringing effect, or blur. In this article, we propose three models of fully convolutional networks with different configurations and examine their abilities in reducing compression artifacts. In the experiments, we research the extent to which the results are improved for models that will process the image in a similar way to the compression algorithm, and whether the initialization with predefined filters would allow for better image reconstruction than developed solely during learning.

Tue Nov 22 2016
Artificial Intelligence
CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppression
Deep convolutional neural networks have become a widespread tool to address high-level computer vision tasks. We show that a network trained for a specific quality factor (QF) is resilient to the quality factor used to compress the input image.
0
0
0
Tue Aug 09 2016
Computer Vision
Deep Convolution Networks for Compression Artifacts Reduction
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened images that are accompanied with ringing effects. Inspired by the success of deep convolutional networks (DCN)
0
0
0
Fri Jun 08 2018
Computer Vision
DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
JPG is one of the most commonly used standards among lossy image compression methods. Convolutional neural network (CNN) based methods have shown excellent performance for removing the JPEG artifacts.
0
0
0
Mon May 28 2018
Computer Vision
BlockCNN: A Deep Network for Artifact Removal and Image Compression
We present a general technique that performs both artifact removal and image compression. For artifact removal, we input a JPEG image and try to remove its compression artifacts. For compression, we process an image and process its 8 by 8 blocks in a sequence.
0
0
0
Wed Aug 02 2017
Computer Vision
An End-to-End Compression Framework Based on Convolutional Neural Networks
Two CNNs are seamlessly integrated into an end-to-end compression framework. The first CNN learns an optimal compact representation from an input image. The second CNN is used to reconstruct the decoded image with high-quality in the decoding end. The proposed compression framework is compatible with existing image coding standards.
0
0
0
Wed Apr 25 2018
Computer Vision
Deep Convolutional AutoEncoder-based Lossy Image Compression
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks. In this paper, we present a lossy image compression architecture.
0
0
0
Thu Sep 04 2014
Computer Vision
Very Deep Convolutional Networks for Large-Scale Image Recognition
Convolutional networks of increasing depth can achieve state-of-the-art results. The research was the basis of the team's ImageNet Challenge 2014.
3
3
7
Tue Feb 06 2018
Computer Vision
Scale-recurrent Network for Deep Image Deblurring
"Coarse-to-fine" scheme is very successful in both traditional optimization-based methods and recent neural-network-based approaches. We propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task.
0
0
0
Mon Apr 27 2015
Computer Vision
Compression Artifacts Reduction by a Deep Convolutional Network
Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output. We formulate a compact and efficient network for seamless attenuation of different compression artifacts.
0
0
0
Thu Jun 04 2015
Computer Vision
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
State-of-the-art object detection networks depend on region proposalgorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks.
0
0
0
Tue Aug 09 2016
Computer Vision
Deep Convolution Networks for Compression Artifacts Reduction
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened images that are accompanied with ringing effects. Inspired by the success of deep convolutional networks (DCN)
0
0
0
Wed Dec 07 2016
Computer Vision
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem. To remove blurs, conventional energy optimization based methods rely on simple assumptions. We propose a multi-scale convolutional neural network that restores sharp images.
0
0
0