ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

Chen, Liheng; Bampis, Christos G.; Li, Zhi; Norkin, Andrey; Bovik, Alan C.

doi:10.1109/tip.2020.3036752

Cited by 65 publications

(26 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These loss networks were trained to mimic various quality scores to be used in loss function. For example, Chen et al [69] trained their loss network to output objective VAMF between label and output, Talebi et al [74] and Yang et al [75] applied NIMA [76] as their loss network to get aesthetic subjective score on output image. Their loss networks shared the same motivation of mimicking a quality score which is unable to be directly implemented as loss function due to its complexity or non-differentiability (objective scores), and unquantifiability (subjective scores).…”

Section: Discussionmentioning

confidence: 99%

Deep Tone-Mapping Operator Using Image Quality Assessment Inspired Semi-Supervised Learning

Guo

Jiang

2021

IEEE Access

View full text Add to dashboard Cite

Tone-mapping operator (TMO) is intended to convert high dynamic range (HDR) content into a lower dynamic range so that it can be displayed on a standard dynamic range (SDR) device. The tonemapped result of HDR content is usually stored as SDR image. For different HDR scenes, traditional TMOs are able to obtain a satisfying SDR image only under manually fine-tuned parameters. In this paper, we address this problem by proposing a learning-based TMO using deep convolutional neural network (CNN). We explore different CNN structure and adopt multi-scale and multi-branch fully convolutional design. When training deep CNN, we introduce image quality assessments (IQA), specifically, tone-mapped image quality assessment, and implement it as semi-supervised loss terms. We discuss and prove the effectiveness of semisupervised loss terms, CNN structure, data pre-processing, etc. by several experiments. Finally, we demonstrate that our approach can produce appealing results under diversified HDR scenes.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Tone-Mapping Operator Using Image Quality Assessment Inspired Semi-Supervised Learning

Guo

Jiang

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Deep convolutional neural networks (CNNs) have been shown to deliver standout performance in a wide variety of low-level computer vision applications [17], [23], [25], [58]. Recently, the release of several large-scale psychometric visual quality databases [29]- [32], [51] have sped the application of deep CNNs to perceptual video and image quality modeling.…”

Section: B Deep Learning-based Bvqa Modelsmentioning

confidence: 99%

“…Another well-founded approach is to design a large number of distortion-specific features, whether individually [20]- [22], or combined, as is done in TLVQM [13] to achieve a final quality prediction score. Recently, convolutional neural networks (CNN) have been shown to deliver remarkable performance on a wide range of computer vision tasks [23]- [25]. Several deep CNN-based BVQA models have also been proposed [18], [19], [26], [27] by training them on recently created large-scale psychometric databases [28], [29].…”

Section: Introductionmentioning

confidence: 99%

RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content

Wang

et al. 2021

IEEE Open J. Signal Process.

Self Cite

131

View full text Add to dashboard Cite

Blind or no-reference video quality assessment of user-generated content (UGC) has become a trending, challenging, heretofore unsolved problem. Accurate and efficient video quality predictors suitable for this content are thus in great demand to achieve more intelligent analysis and processing of UGC videos. Previous studies have shown that natural scene statistics and deep learning features are both sufficient to capture spatial distortions, which contribute to a significant aspect of UGC video quality issues. However, these models are either incapable or inefficient for predicting the quality of complex and diverse UGC videos in practical applications. Here we introduce an effective and efficient video quality model for UGC content, which we dub the Rapid and Accurate Video Quality Evaluator (RAPIQUE), which we show performs comparably to state-of-the-art (SOTA) models but with orders-of-magnitude faster runtime. RAPIQUE combines and leverages the advantages of both quality-aware scene statistics features and semantics-aware deep convolutional features, allowing us to design the first general and efficient spatial and temporal (space-time) bandpass statistics model for video quality modeling. Our experimental results on recent large-scale UGC video quality databases show that RAPIQUE delivers top performances on all the datasets at a considerably lower computational expense. We hope this work promotes and inspires further efforts towards practical modeling of video quality problems for potential real-time and low-latency applications. To promote public usage, an implementation of RAPIQUE has been made freely available online: https://github.com/vztu/RAPIQUE.

show abstract

“…Deep convolutional neural networks (CNNs or ConvNets) have been shown to deliver standout performance on a wide variety of computer vision applications [18][19][20][21][22]. Recently, the release of several "large-scale" (in the context of IQA/VQA research) subjective quality databases [20,23] have sped the application of deep CNNs to perceptual quality modeling.…”

Section: Bvqa Modelsmentioning

confidence: 99%

Video Quality Assessment of User Generated Content: A Benchmark Study and a New Model

Chen

Wang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed an explosion of user-generated content (UGC) shared and streamed over the Internet. Accordingly, there is a great need for accurate video quality assessment (VQA) models for consumer or UGC videos to monitor, control, and optimize this vast content. Here we contribute to advancing the UGC-VQA problem by conducting a comprehensive evaluation of leading blind VQA (BVQA) models. Besides, we also created a new fusion-based BVQA model, which we dub the VIDeo quality EVALuator (VIDE-VAL), that effectively balances the trade-off between performance and efficiency. Our experimental results show that VIDEVAL achieves state-of-the-art performance at a lower computational cost. We believe our reliable and reproducible benchmark will facilitate further research on deep learningbased BVQA modeling. An implementation of VIDEVAL has been made available online 1 .

show abstract

ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

Cited by 65 publications

References 49 publications

Deep Tone-Mapping Operator Using Image Quality Assessment Inspired Semi-Supervised Learning

Deep Tone-Mapping Operator Using Image Quality Assessment Inspired Semi-Supervised Learning

RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content

Video Quality Assessment of User Generated Content: A Benchmark Study and a New Model

Contact Info

Product

Resources

About