Filters








2,240 Hits in 2.8 sec

A Multi-task convolutional neural network for blind stereoscopic image quality assessment using naturalness analysis [article]

Salima Bourbia, Ayoub Karine, Aladine Chetouani, Mohammed El Hassouni
2021 arXiv   pre-print
This paper addresses the problem of blind stereoscopic image quality assessment (NR-SIQA) using a new multi-task deep learning based-method.  ...  In this work, we propose to integrate these characteristics to estimate the quality of stereoscopic images without reference through a convolutional neural network.  ...  Reference SIQA (RR-SIQA) that requests reduced information of the original image, and No Reference (NR-SIQA) that assesses the quality without the need of any information from the reference image.  ... 
arXiv:2106.09303v3 fatcat:ugvkgljqorasnpbbgo7bkk6qc4

Stereoscopic video quality assessment based on 3D convolutional neural networks

Jiachen Yang, Yinghao Zhu, Chaofan Ma, Wen Lu, Qinggang Meng
2018 Neurocomputing  
Keywords: 3D convolutional neural networks Stereoscopic video quality assessment Quality score fusion a b s t r a c t The research of stereoscopic video quality assessment (SVQA) plays an important role  ...  This paper introduces a 3D convolutional neural networks (CNN) based SVQA framework that can model not only local spatio-temporal information but also global temporal information with cubic difference  ...  Neural network based visual content quality assessment There were many early works applying neural networks to visual content quality assessment.  ... 
doi:10.1016/j.neucom.2018.04.072 fatcat:2axcnt7gd5d3no2urbvudgpec4

Learning structure of stereoscopic image for no-reference quality assessment with convolutional neural network

Wei Zhang, Chenfei Qu, Lin Ma, Jingwei Guan, Rui Huang
2016 Pattern Recognition  
In this paper, we propose to learn the structures of stereoscopic image based on convolutional neural network (CNN) for no-reference quality assessment.  ...  With the evaluation on public LIVE phase-I, LIVE phase-II, and IVC stereoscopic image databases, the proposed no-reference metric achieves the state-of-the-art performance for quality assessment of stereoscopic  ...  [61] present an information fidelity criterion for image quality assessment that relates the image quality with the amount of information shared between a reference and a distorted image.  ... 
doi:10.1016/j.patcog.2016.01.034 fatcat:cend7opm4bempp2vbqpocy33qu

Blind Stereoscopic Image Quality Assessment Based on Hierarchical Learning

Tsung-Jung Liu, Ching-Ti Lin, Hsin-Hua Liu, Soo-Chang Pei
2019 IEEE Access  
INDEX TERMS Hierarchical learning, image quality assessment, no reference, stereoscopic images. 8058 2169-3536  ...  We proposed a blind image quality assessment model which used classification and prediction for three-dimensional (3D) image quality assessment (denoted as CAP-3DIQA) that can automatically evaluate the  ...  [14] proposed a no-reference stereoscopic IQA metric based on the monocular and binocular image interaction.  ... 
doi:10.1109/access.2018.2890304 fatcat:stge3igiqzf7vptqnllwwbu3q4

VCIP 2020 Index

2020 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)  
In- loop Filtering in Video Coding Li, Sumei No-Reference Stereoscopic Image Quality Assessment Based on Convolutional Neural Network with A Long-Term Feature Fusion Li, Sumei No-Reference Stereoscopic  ...  Image Quality Assessment Based On Visual Attention Mechanism Li, Sumei A Weighted Mean Absolute Error Metric for Image Quality Assessment Li, Sumei No-Reference Stereoscopic Image Quality Assessment  ... 
doi:10.1109/vcip49819.2020.9301896 fatcat:bdh7cuvstzgrbaztnahjdp5s5y

No-Reference Stereoscopic Image Quality Assessment Based on Binocular Statistical Features and Machine Learning

Peng Xu, Man Guo, Lei Chen, Weifeng Hu, Qingshan Chen, Yujun Li, Jia Wu
2021 Complexity  
Inspired by the structure representation of the human visual system and the machine learning technique, we propose a no-reference quality assessment scheme for stereoscopic images.  ...  Learning a deep structure representation for complex information networks is a vital research area, and assessing the quality of stereoscopic images or videos is challenging due to complex 3D quality factors  ...  [33] proposed a dual-stream interactive network for stereoscopic image quality assessment.  ... 
doi:10.1155/2021/8834652 fatcat:jlati2yuonekzo4sdu33gkapce

3D Visual Comfort Assessment via Sparse Coding [chapter]

Qiuping Jiang, Feng Shao
2015 Lecture Notes in Computer Science  
This paper presents a novel visual comfort assessment (VCA) metric based on sparse coding strategy.  ...  A set of stereoscopic images with a wide range degree of visual comfort are selected to construct dictionary for sparse coding.  ...  These stereoscopic images are all with a full HD resolution of 1920 × 1080 pixels.  ... 
doi:10.1007/978-3-319-21978-3_2 fatcat:gtt2khnqofeahluwmgb6arammq

Hybrid Distortion Aggregated Visual Comfort Assessment for Stereoscopic Image Retargeting [article]

Ya Zhou, Zhibo Chen, Weiping Li
2018 arXiv   pre-print
In this paper, we propose a Hybrid Distortion Aggregated Visual Comfort Assessment (HDA-VCA) scheme for stereoscopic retargeted images (SRI), considering aggregation of hybrid distortions including structure  ...  Finally, the semantic distortion is represented by the correlation distance of paired feature maps extracted from original stereoscopic image and its retargeted image by using trained deep neural network  ...  Chen et al. proposed a full-reference stereoscopic image quality assessment which accounts for binocular rivalry [18] .  ... 
arXiv:1811.12687v1 fatcat:643ydzywcbbfdjgrauaqfirjjy

Quality assessment for virtual reality technology based on real scene

Bin Jiang, Jiachen Yang, Na Jiang, Zhihan Lv, Qinggang Meng
2016 Neural computing & applications (Print)  
Quality assessment for virtual reality technology based on real scene. Neural Computing and Applications, 29(5), pp. 1199-1208.  ...  Abstract Virtual reality technology is a new display technology, which provides users with real viewing experience. As known, most of the virtual reality display through stereoscopic images.  ...  Quality assessment of stereoscopic image can be divided into subjective and objective quality evaluation [14, 15] .  ... 
doi:10.1007/s00521-016-2828-0 fatcat:b5o7j627hjcq3noqmm5r5dd6ya

Visual Comfort Assessment for Stereoscopic Image Retargeting [article]

Ya Zhou, Wei Zhou, Ping An, Zhibo Chen
2018 arXiv   pre-print
Furthermore, we propose a Visual Comfort Assessment metric for Stereoscopic Image Retargeting (VCA-SIR).  ...  Then, the subjective experiment is conducted to assess four aspects of visual distortion, i.e. visual comfort, image quality, depth quality and the overall quality.  ...  Image quality assessment algorithm can be divided into full-reference, reduced-reference and no-reference image quality.  ... 
arXiv:1805.05575v1 fatcat:mlolja7ldraororddup4jm2dl4

Quality assessment metric of stereo images considering cyclopean integration and visual saliency

Jiachen Yang, Yafang Wang, Baihua Li, Wen Lu, Qinggang Meng, Zhihan Lv, Dezong Zhao, Zhiqun Gao
2016 Information Sciences  
With increasing sources of 3D content, a useful tool is needed to evaluate the perceived quality of the 3D videos/images.  ...  It can thus be concluded that the proposed SIQA metric can provide an effective evaluation tool to assess stereoscopic image quality.  ...  With this inspiration, a cyclopean and saliency-based quality assessment metric for stereoscopic images is proposed.  ... 
doi:10.1016/j.ins.2016.09.004 fatcat:zhunmr6exffh7fw4goudnpb2dq

Stereoscopic image quality assessment method based on binocular combination saliency model

Yun Liu, Jiachen Yang, Qinggang Meng, Zhihan Lv, Zhanjie Song, Zhiqun Gao
2016 Signal Processing  
Stereoscopic image quality assessment method based on binocular combination saliency model.  ...  Abstract The objective quality assessment of stereoscopic images plays an important role in three-dimensional (3D) technologies.  ...  [13] built a public 3D images database based on subjective quality assessment method. Lee et al.  ... 
doi:10.1016/j.sigpro.2016.01.019 fatcat:76ncie44nbc7ti7ejfq7szazmu

Table of contents

2019 IEEE Transactions on Image Processing  
Rodríguez 1705 Corrupted Reference Image Quality Assessment of Denoised Images ........ C. Zhang, W. Cheng, and K.  ...  Ro 1646 Unified No-Reference Quality Assessment of Singly and Multiply Distorted Stereoscopic Images ...................... ............................................................... Q.  ... 
doi:10.1109/tip.2018.2889128 fatcat:vwth2bil2ze4lkngpckwi54ohu

Related Work on Image Quality Assessment [article]

Dongxu Wang
2021 arXiv   pre-print
Due to the existence of quality degradations introduced in various stages of visual signal acquisition, compression, transmission and display, image quality assessment (IQA) plays a vital role in image-based  ...  This article will review the state-of-the-art image quality assessment algorithms.  ...  [27] presented a no reference image (NR) quality assessment (IQA) method based on a deep convolutional neural network (CNN).  ... 
arXiv:2111.06291v1 fatcat:a3wrhqws7bg5thadvagtqvwl3q

Toward a Quality Predictor for Stereoscopic Images via Analysis of Human Binocular Visual Perception

Yun Liu, Fanhui Kong, Zhizhuo Zhen
2019 IEEE Access  
Perceptual stereoscopic image quality assessment (SIQA) has become a challenge research problem due to the poor understanding of human binocular visual characteristics.  ...  This model is based on a cyclopean image from a novel binocular combination model as image content quality description and a depth binocular combination model from a depth synthesized procedure as depth  ...  With this inspiration, an efficient cyclopean perception algorithm for stereoscopic images quality assessment is proposed, as shown in Fig.4 . A.  ... 
doi:10.1109/access.2019.2919155 fatcat:shomd4cb55glxk35b3fedxcace
« Previous Showing results 1 — 15 out of 2,240 results