Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 1,047 papers for “Compression artifact”

Deep Generative Adversarial Compression Artifact Removal

Leonardo Galteri, Lorenzo Seidenari, Marco Bertini et al. · Florence Research (University of Florence) · 2017

Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small structures; because of these effects they make images less pleasant for the human eye, and may also lead to decreased performance of computer vision algorithms such as object detectors. To eliminate such artifacts, when decompressing an image, it is required to recover the original image from a disturbed version. To this end, we present a feed-forward fully convolutional residual network model that directly optimizes the Structural Similarity (SSIM), which is a better loss with respect to the simpler Mean Squared Error (MSE). We then build on the same architecture to re-formulate the problem in a generative adversarial framework. Our GAN is able to produce images with more photorealistic details than MSE or SSIM based networks. Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail. In this task, our GAN method obtains better performance than MSE or SSIM trained networks.

Cited by 210

Alignment-Free Video Compression Artifact Reduction

Dengyan Luo, Mao Ye, Shengjie Chen et al. · 2021 International Conference on Visual Communications and Image Processing (VCIP) · 2021

The past few years have witnessed the great success of using multi-frame information to enhance the quality of compressed video. Most existing methods do frame or feature alignments to bring similar information from neighborhood frames much closer to enhance frame quality. However, inaccurate motion estimation will bring new artifacts. In this paper, we propose a new approach without alignment, which takes each non-Peak Quality Frame (non-PQF) and its two adjacent Peak Quality Frames (PQFs) as input. A Pre-processing module based on multi-scale feature extraction strategy is used to broaden receptive field of the network. Then, an enhancement module uses a two-stream feature extraction architecture to combine deep architecture and attention mechanism to further gather similar information. In this module, the lost high-frequency and similar information can be further retrieved from the adjacent PQFs. The proposed network is trained in an end-to-end manner. Compared with the alignment based methods, the competitive results can be obtained. A large number of qualitative and quantitative experimental results demonstrate the robustness and effectiveness of the proposed method.

Cited by 5

Deep Universal Generative Adversarial Compression Artifact Removal

Leonardo Galteri, Lorenzo Seidenari, Marco Bertini et al. · IEEE Transactions on Multimedia · 2019

Image compression is a need that arises in many circumstances. Unfortunately, whenever a lossy compression algorithm is used, artifacts will manifest. Image artifacts, caused by compression tend to eliminate higher frequency details and, in certain cases, may add noise or small image structures. There are two main drawbacks of this phenomenon. First, images appear much less pleasant to the human eye. Second, computer vision algorithms, such as object detectors, may be hindered and their performance reduced. Removing such artifacts means recovering the original image from a perturbed version of it. This means that one ideally should invert the compression process through a complicated nonlinear image transformation. We propose an image transformation approach based on a feedforward fully convolutional residual network model. We show that this model can be optimized either traditionally, directly optimizing an image similarity loss (SSIM), or using a generative adversarial approach (GAN). Our GAN is able to produce images with more photorealistic details than SSIM-based networks. We describe a novel training procedure based on subpatches and devise a novel testing protocol to evaluate restored images quantitatively. We show that our approach can be used as a preprocessing step for different computer vision tasks in case images are degraded by compression to a point that state-of-the art algorithms fail. In this case, our GAN-based approach obtains better performance than MSE or SSIM trained networks. Different from previously proposed approaches, we are able to remove artifacts generated at any QF by inferring the image quality directly from data.

Cited by 86

BOUNDARY ARTIFACT REDUCTION IN WAVELET IMAGE COMPRESSION

D. Černá, V. Finěk, M. Gottfried et al. · 2014

In our contribution, we compute new edge wavelet filters for image compression and we compare errors for several image compression techniques. Our numerical experiments confirm the theoretical assumption that the error of the compression is smaller for the discrete wavelet transform with derived edge filters than for other methods using an extension of an image. 1

Cited by 0

New Image Compression Artifact Measure Using Wavelets

Yung-kai Lai, C.-C. Jay Kuo, Jin Li · 2007

Traditional objective metrics for the quality measure of coded images such as the mean squared error (MSE) and the peak signal-to-noise ratio (PSNR) do not correlate with the subjective human visual experiences well, since they do not take human perception into account. Quantification of artifacts resulted from lossy image compression techniques is studied based on a human visual system (HVS) model and the time-space localization property of the wavelet transform is exploited to simulate HVS in this research. As a result of our research, a new image quality measure by using the wavelet basis function is proposed. This new metric works for a wide variety of compression artifacts. Experimental results are given to demonstrate that it is more consistent with human subjective ranking. KEYWORDS: image quality assessment, compression artifact measure, visual fidelity criterion, human visual system (HVS), wavelets. 1 INTRODUCTION The objective of lossy image compression is to store image d...

Cited by 0

Residual Network for Image Compression Artifact Reduction

Jianhua Hu, Guixiang Luo, Bo Wang et al. · International Journal of Pattern Recognition and Artificial Intelligence · 2024

This paper proposes an image compression algorithm based on Swin Transformer and residual network (STRN), aiming to reduce blurring and distortions in traditionally compressed images. The algorithm utilizes a dual-channel mechanism to remove artifacts from the image, which takes advantage of the complementary features of the transform and residual networks. The Swin Transformer networks address the issue of long-range dependency, leading to an enhanced and improved reconstructed image quality. The residual network is an effective network that mitigates gradient loss and recovers image details during the image compression process. The paper demonstrates that image compression can be achieved by training a convolutional network based on a transformer and residuals network, which significantly reduces artifacts and provides better reconstructed image quality compared to previously used and current mainstream methods based on traditional convolutional neural networks. The proposed approach can remove blocking artifacts by subtracting estimated artifacts from the input image, while still preserving most of the original details. Therefore, our proposed method is highly effective in improving image quality and reducing visual artifacts caused by traditional compression methods. Moreover, this method is useful for enhancing image transmission and storage efficiency in various computer vision systems that employ digital visual codecs.

Cited by 3

FOR COMPRESSION ARTIFACT REDUCTION IN JPEG IMAGES

Dung T. Vo, Truong Nguyen, Sehoon Yea et al. · 2008

We propose a novel method to reduce both blocking and ringing artifacts in compressed images and videos. Based on the directional characteristics of ringing artifacts along edges, we use a directional fuzzy filter which is adaptive to the direction of the ringing artifacts. The filter exploits the spatial order, the rank order and the spread information of the signal together with the position of the pixels to enhance the quality of the compressed image. Simulations results on compressed images and videos having simple and complex edges show the improvement of the proposed directional fuzzy filter over the conventional fuzzy filtering and approaches.

Cited by 0

Video-Based Point Cloud Compression Artifact Removal

Anique Akhtar, Wen Gao, Li Li et al. · IEEE Transactions on Multimedia · 2021

Photo-realistic point cloud capture and transmission are the fundamental enablers for immersive visual communication. The coding process of dynamic point clouds, especially video-based point cloud compression (V-PCC) developed by the MPEG standardization group, is now delivering state-of-the-art performance in compression efficiency. V-PCC is based on the projection of the point cloud patches to 2D planes and encoding the sequence as 2D texture and geometry patch sequences. However, the resulting quantization errors from coding can introduce compression artifacts, which can be very unpleasant for the quality of experience (QoE). In this work, we developed a novel out-of-the-loop point cloud geometry artifact removal solution that can significantly improve reconstruction quality without additional bandwidth cost. Our novel framework consists of a point cloud sampling scheme, an artifact removal network, and an aggregation scheme. The point cloud sampling scheme employs a cube-based neighborhood patch extraction to divide the point cloud into patches. The geometry artifact removal network then processes these patches to obtain artifact-removed patches. The artifact-removed patches are then merged together using an aggregation scheme to obtain the final artifact-removed point cloud. We employ 3D deep convolutional feature learning for geometry artifact removal that jointly recovers both the quantization direction and the quantization noise level by exploiting projection and quantization prior. The simulation results demonstrate that the proposed method is highly effective and can considerably improve the quality of the reconstructed point cloud.

Cited by 56

Learned Compression Artifact Removal by Deep Residual Networks

Ogün Kırmemiş, Gonca Bakar, A. Murat Tekalp · arXiv (Cornell University) · 2018

We propose a method for learned compression artifact removal by post-processing of BPG compressed images. We trained three networks of different sizes. We encoded input images using BPG with different QP values. We submitted the best combination of test images, encoded with different QP and post-processed by one of three networks, which satisfy the file size and decode time constraints imposed by the Challenge. The selection of the best combination is posed as an integer programming problem. Although the visual improvements in image quality is impressive, the average PSNR improvement for the results is about 0.5 dB.

Cited by 1Open access

Deep JPEG Compression Artifact Removal with Harmonic Networks

Hasan H. Karaoğlu, Ender M. Ekşioğlu · 2025

Many modern learning algorithms try to solve a JPEG compression artifact removal (CAR) problem in pixel domain by mapping a low-quality compressed image to the corresponding high-quality image. Although JPEG artifacts arise from quantizing discrete cosine transform (DCT) coefficients of nonoverlapping image blocks, researchers have utilized a transform domain as auxiliary information at most. On the other hand, it is well known and approved that extracting image blocks with overlap improves decompression performance. Inspired by these observations, we propose novel and fully transformed domain convolutional neural networks (CNNs) for the problem. We choose the discrete cosine transform (DCT), discrete sine transform (DST), and discrete Hartley transform (DHT)—another effective DCT-like transform in terms of energy compactness—as the transforms to be utilized and refer to them as harmonic transforms. We perform harmonic transforms on small overlapping blocks of compressed images in the first layer of the proposed networks and create spectral feature maps by properly ordering their harmonic transform coefficients with the same frequency. After a series of convolution blocks, we take the inverse harmonic transform of the corresponding image blocks at the end of the network and put the resulting decompressed blocks back in their place. We show that forward and inverse transform layers of our harmonic networks are efficiently implemented with fast convolution and deconvolution layers by using 2D harmonic basis images as convolution kernels with a mathematical justification. Experimental study indicates that although our harmonic networks have a simple network topology and much fewer parameters than compared state-of-the art deep networks, they are effective and efficient to suppress compression artifacts and they give comparable results.

Cited by 0

Learned Compression Artifact Removal by Deep Residual Networks

Ogün Kırmemiş, Gonca Bakar, A. Murat Tekalp · arXiv (Cornell University) · 2018

We propose a method for learned compression artifact removal by post-processing of BPG compressed images. We trained three networks of different sizes. We encoded input images using BPG with different QP values. We submitted the best combination of test images, encoded with different QP and post-processed by one of three networks, which satisfy the file size and decode time constraints imposed by the Challenge. The selection of the best combination is posed as an integer programming problem. Although the visual improvements in image quality is impressive, the average PSNR improvement for the results is about 0.5 dB.

Cited by 4Open access

Residual Hybrid Attention Network for Compression Artifact Reduction

Bingchun Luo, Yu Wei · 2023

Residual Hybrid Attention Network (RHAN) can restore images of arbitrary compression quality through flexibly fusing high-frequency features in the spatial and frequency domains based on the input quality factor. Specifically, to remove the compression artifacts, we propose a hybrid attention block (HAB) to adaptively restore the loss of high-frequency components, which parallelly predicts attention maps along two separate dimensions spatial and frequency spectra. To recover the compressed image flexibly and controllably, we further design a modulation decompression block (MDB), which employs a prior factor to learn a pair of modulation parameters and performs adaptively affine transformation on the obtained high-frequency features, thereby achieving high-quality image restoration at arbitrary compression levels. The quantitative and qualitative experiments on various public data sets show that the RHAN achieves the best performance and optimal visual perceptual quality in the JPEG image restoration with arbitrary compression levels.

Cited by 0

Artifact Reduction by Post-Processing in Image Compression

Tao Chen, Hong Ren Wu · Signal processing and communications · 2005

In this chapter, the post-processing techniques developed for reducing artifacts in low bit rate image compression will be discussed. They mainly emphasize the reduction of blocking and ringing artifacts, on which brief discussions will be given first. Then a review of recent developments on deblocking filters will be presented. Specifically, an adaptive DCT domain postfilter will be described in detail. Though the approach was designed to remove blocking artifacts, interestingly it is also observed to be capable of suppressing ringing artifacts in block-based DCT image compression. Following that, recent works on the ringing artifact reduction will be reviewed. The de-ringing techniques tailored for the DCT and wavelet transform based compression will both be discussed.

Cited by 4

Artifact Reduction by Post-Processing in Image Compression

Tao Chen, HongRen Wu · 2017

This chapter discusses the post-processing techniques developed for reducing artifacts in low bit rate image compression. It examines the discussion on the post-processing methods that have been developed to reduce the blocking and ringing artifacts. The chapter reviews the developments on ringing artifact reduction. Methods designed for discrete cosine transform and wavelet transform coding. In image and video coding, for a given encoding algorithm and a bit rate constraint, the quality of reconstructed images can be enhanced by pre filtering approaches. In the case of large quantization errors of wavelet coefficients in coded images, the decoded images still carry obvious artifacts among smooth regions and around sharp edges. The chapter describes how the proposed post filter works in such a way that it adaptively filters the transform coefficients based on the local signal characteristics to efficiently smooth out blocking artifacts, while preserving image details at the same time.

Cited by 1

Abstract 260: Automatic Shock Advisory Without Interrupting Chest Compression by Filtering Compression Artifact

Saeed Babaeizadeh · Circulation · 2013

Background: Both AHA and ERC Guidelines 2010 focus on minimizing “hands-off time” - the time interval a patient in cardiac arrest is not receiving chest compressions (CC). The primary device-related cause of CC interruption is automated ECG rhythm analysis for accurate shock advisory. The mechanical activity of CC produces artifact on the ECG waveform that most automated ECG analysis programs cannot fully differentiate from the patient’s inherent ECG morphology. Furthermore, clinicians observing an ECG waveform on the defibrillator’s display cannot see the patient’s underlying rhythm through the electrical noise created by CC, forcing an interruption to CC for rhythm assessment. Objective: Improving the performance of ECG analysis programs by filtering artifacts due to CC in out of hospital cardiac arrest (OHCA) patients. Methods: Recordings from 175 OHCA patients collected for a separate study using Laerdal HeartStart 4000 defibrillators in 6 ambulances in 3 European regions between March 2002 and October 2003. The transition times from CC to hands-off were marked. Assuming no rhythm change within a few seconds around the transition time, experts selected 1378 4.5-second ECG segments with CC artifact, and the same number without the artifact. Each category included 340 shockable ventricular fibrillation, 342 asystole, 646 pulseless electrical activity, and 50 pulsatile rhythms. A two-step process was designed to filter the CC artifact prior to the analysis by the shock advisory algorithm. By analyzing both ECG and thoracic impedance waveforms the fundamental frequency of CC was found, to then be filtered along with all its harmonics using a comb filter. Results: Defining a positive event as shock advice for shockable rhythm, the shock advisory algorithm achieved sensitivity of 97% and specificity of 99% when no CC was being performed. However during CC both sensitivity and specificity dropped to 63% and 91% respectively. Filtering the CC artifact increased the sensitivity back up to 89% at the expense of slightly reducing the specificity to 90%. Conclusion: It is possible to improve the performance of shock advisory algorithms during CC by filtering the CC artifact. However additional techniques may be needed to achieve accuracy high enough for practical use.

Cited by 0Open access