SSIM-Motivated Rate-Distortion Optimization for Video Coding

Wang, Shiqi; Rehman, Abdul; Wang, Zhou; Ma, Siwei; Gao, Wen

doi:10.1109/tcsvt.2011.2168269

Cited by 193 publications

(98 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This largely restricts its applications in designing image processing algorithms such as image compression and restoration. Recently, some works [36][37][38] have been reported to adopt SSIM for image/video perceptual compression. However, these methods are not "one-pass" and they have high complexity.…”

Section: G Discussionmentioning

confidence: 99%

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Xue

Zhang

Mou

et al. 2014

IEEE Trans. on Image Process.

1,367

644

View full text Add to dashboard Cite

Abstract-It is an important task to faithfully evaluate the perceptual quality of output images in many applications such as image compression, image restoration and multimedia streaming. A good image quality assessment (IQA) model should not only deliver high quality prediction accuracy but also be computationally efficient. The efficiency of IQA metrics is becoming particularly important due to the increasing proliferation of high-volume visual data in high-speed networks. We present a new effective and efficient IQA model, called gradient magnitude similarity deviation (GMSD). The image gradients are sensitive to image distortions, while different local structures in a distorted image suffer different degrees of degradations. This motivates us to explore the use of global variation of gradient based local quality map for overall image quality prediction. We find that the pixel-wise gradient magnitude similarity (GMS) between the reference and distorted images combined with a novel pooling strategy -the standard deviation of the GMS map -can predict accurately perceptual image quality. The resulting GMSD algorithm is much faster than most state-of-the-art IQA methods, and delivers highly competitive prediction accuracy. MATLAB source code of GMSD can be downloaded at http://www4.comp.polyu.edu.hk/~cslzhang/IQA/ GMSD/GMSD.htm.Index Terms-Gradient magnitude similarity, image quality assessment, standard deviation pooling, full reference

show abstract

Section: G Discussionmentioning

confidence: 99%

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Xue

Zhang

Mou

et al. 2014

IEEE Trans. on Image Process.

1,367

644

View full text Add to dashboard Cite

show abstract

“…Most of the existing compression schemes still adopt MSE or PSNR during RDO, which does not well correspond to visual quality. Optimizing compression for visual quality is a promising direction to further improve compression ratio, such as using SSIM to replace PSNR [29]. More recently, a perceptual screen content coding scheme is developed based on the newly proposed quality assessment measure [28].…”

Section: Related Workmentioning

confidence: 99%

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Liu

Wang

2016

Sens Imaging

View full text Add to dashboard Cite

Traditionally, image compression was optimized for the pixel-wise fidelity or the perceptual quality of the compressed images given a bit-rate budget. But recently, compressed images are more and more utilized for automatic semantic analysis tasks such as recognition and retrieval. For these tasks, we argue that the optimization target of compression is no longer perceptual quality, but the utility of the compressed images in the given automatic semantic analysis task. Accordingly, we propose to evaluate the quality of the compressed images neither at pixel level nor at perceptual level, but at semantic level. In this paper, we make preliminary efforts towards image semantic quality assessment (ISQA), focusing on the task of optical character recognition (OCR) from compressed images. We propose a fullreference ISQA measure by comparing the features extracted from text regions of original and compressed images. We then propose to integrate the ISQA measure into an image compression scheme. Experimental results show that our proposed ISQA measure is much better than PSNR and SSIM in evaluating the semantic quality of compressed images; accordingly, adopting our ISQA measure to optimize compression for OCR leads to significant bit-rate saving compared to using PSNR or SSIM. Moreover, we perform subjective test about text recognition from compressed images, and observe that our ISQA measure has high consistency with subjective recognizability. Our work explores new dimensions in image quality assessment, and demonstrates promising direction to achieve higher compression ratio for specific semantic analysis tasks.

show abstract

“…Moreover, it was found that, despite several uses of SSIM [9][10][11], in most cases MSE is employed for optimization in coding. "Why the state-of-theart FR IQA models cannot be applied to compression?"…”

Section: Proposed Quality Metricmentioning

confidence: 99%

“…the mean opinion score (MOS). Subjective quality scores are quite valuable, because on the one hand they can be used to justify the performance of objective IQA algorithms (e.g., LIVE [1], TID2008 [2], CSIQ [3], IVC [4], Toyama [5] and TID2013 [6]), and on the other hand, they are able to instruct denoising [7], restoration [8], coding [9][10][11], and compare tone-mapped operators [12][13][14]. But subjective methods easily suffer the drawbacks of being laborious, costly and time-consuming, and thus cannot be adapted to real-time applications.…”

Section: Introductionmentioning

confidence: 99%

Content-weighted mean-squared error for quality assessment of compressed images

Wang

Zhai

et al. 2015

SIViP

Self Cite

View full text Add to dashboard Cite

Image quality assessment (IQA) has been intensively studied, especially for the full-reference (FR) scenario. However, only the mean-squared error (MSE) is widely employed in compression. Why other IQA metrics work ineffectively? We first sum up three main limitations including the computational time, portability, and working manner.To address these problems, we then in this paper propose a new content-weighted MSE (CW-MSE) method to assess the quality of compressed images. The design principle of our model is to use adaptive Gaussian convolution to estimate the influence of image content in a block-based manner, thereby to approximate the human visual perception to image quality. Results of experiments on six popular subjective image quality databases (including LIVE, TID2008, CSIQ, IVC, Toyama and TID2013) confirm the superiority of our CW-MSE over state-of-the-art FR IQA approaches.

show abstract

SSIM-Motivated Rate-Distortion Optimization for Video Coding

Cited by 193 publications

References 41 publications

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Content-weighted mean-squared error for quality assessment of compressed images

Contact Info

Product

Resources

About