Zhengxue Cheng 교수

Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there is still a performance gap between learned compression algorithms and reigning compression standards, especially in terms of widely used PSNR metric. In this paper, we explore the remaining redundancy of recent learned compression algorithms. We have found acc

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, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture to replace the conventional transforms and train this CAE using a ra

Image compression has been an important research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and its use in image compression has gradually been increasing. In this paper, we present an energy compaction-based image compression architecture using a convolutional autoencoder (CAE) to achieve high coding efficiency. Our main contributions include three aspects: 1) we propose a CAE architecture for image compression by decomposing it int

Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning based image and video compression. Inspired from related works, in this paper, we present an image compression architecture using a convolutional autoencoder, and then generalize image compression to video compression, by adding an interpolation loop into both encoder and decoder sides. Our basic idea is to r

Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there is still a performance gap between learned compression algorithms and reigning compression standards, especially in terms of widely used PSNR metric. In this paper, we explore the remaining redundancy of recent learned compression algorithms. We have found acc

In this paper, we provide a detailed description on our approach designed for CVPR 2019 Workshop and Challenge on Learned Image Compression (CLIC). Our approach mainly consists of two proposals, i.e. deep residual learning for image compression and sub-pixel convolution as up-sampling operations. Experimental results have indicated that our approaches, Kattolab, Kattolabv2 and KattolabSSIM, achieve 0.972 in MS-SSIM at the rate constraint of 0.15bpp with moderate complexity during the validation

Recently deep learning based image compression has made rapid advances with promising results based on objective quality metrics. However, a rigorous subjective quality evaluation on such compression schemes have rarely been reported. This paper aims at perceptual quality studies on learned compression. First, we build a general learned compression approach, and optimize the model. In total six compression algorithms are considered for this study. Then, we perform subjective quality tests in a c

In recent years, various approaches have been investigated towards blind image quality assessment (IQA) with high accuracy and low complexity. In this paper we develop a pre-saliency map based blind IQA method, which takes advantage of saliency information in prior of quality prediction for performance enhancement by two steps. 1) We split the image into patches and design a convolution neural network (CNN) to predict the patch-wise quality score. Then we explore the relation between image salie

Video streaming over networks has grown rapidly in recent years. Increasing focus has gradually turned from Quality of Service (QoS) awareness to user Quality of Experience (QoE) awareness. In this paper, we propose a unified QoE prediction framework for HEVC encoded video streaming. Firstly, the impact of network impairment on QoE is modelled by packet loss rate. Secondly, features of HEVC encoding process are analyzed and the most relevant one is selected to formulate the impact of HEVC encode

In this paper, we provide a detailed description on our approach designed for CVPR 2019 Workshop and Challenge on Learned Image Compression (CLIC). Our approach mainly consists of two proposals, i.e. deep residual learning for image compression and sub-pixel convolution as up-sampling operations. Experimental results have indicated that our approaches, Kattolab, Kattolabv2 and KattolabSSIM, achieve 0.972 in MS-SSIM at the rate constraint of 0.15bpp with moderate complexity during the validation

Image compression has been investigated for many decades. Recently, deep\nlearning approaches have achieved a great success in many computer vision\ntasks, and are gradually used in image compression. In this paper, we develop\nthree overall compression architectures based on convolutional autoencoders\n(CAEs), generative adversarial networks (GANs) as well as super-resolution\n(SR), and present a comprehensive performance comparison. According to\nexperimental results, CAEs achieve better codin

Image compression has been investigated for many decades. Recently, deep learning approaches have achieved a great success in many computer vision tasks, and are gradually used in image compression. In this paper, we develop three overall compression architectures based on convolutional autoencoders (CAEs), generative adversarial networks (GANs) as well as super-resolution (SR), and present a comprehensive performance comparison. According to experimental results, CAEs achieve better coding effi

Image quality assessment (IQA) is an inherent research topic in image processing field for several decades. Recently, machine learning has achieved success in many multimedia tasks and can be applied in IQA. Especially, screen content images (SCIs) is greatly increasing in various applications, but the characteristics of SCIs makes it difficult to directly apply general IQA methods to predict qualities. In this paper, we propose a fast no-reference SCIs quality prediction method. First, we use t

Lossless image compression is an important task in the field of multimedia communication. Traditional image codecs typically support lossless mode, such as WebP, JPEG2000, FLIF. Recently, deep learning based approaches have started to show the potential at this point. HyperPrior is an effective technique proposed for lossy image compression. This paper generalizes the hyperprior from lossy model to lossless compression, and proposes a L2-norm term into the loss function to speed up training proc

In this work, we provide a detailed description on our submitted methods ANTxNN and ANTxNN_SSIM to Workshop and Challenge on Learned Image Compression (CLIC) 2021. We propose to incorporate Relativistic average Least Squares GANs (RaLSGANs) into Rate-Distortion Optimization for end-to-end training, to achieve perceptual image compression. We also compare two types of discriminator networks and visualize their reconstructed images. Experimental results have validated our method optimized by RaLSG