A content-oriented no-reference perceptual video quality assessment method for computer graphics animation videos

Weizhi XIAN; Mingliang ZHOU; Bin FANG; Sam KWONG

doi:10.1016/j.ins.2022.07.053

A content-oriented no-reference perceptual video quality assessment method for computer graphics animation videos

Weizhi XIAN, Mingliang ZHOU, Bin FANG, Sam KWONG

Research output: Journal Publications › Journal Article (refereed) › peer-review

5 Citations (Scopus)

Abstract

In this paper, we propose a content-oriented no-reference (NR) perceptual video quality assessment (VQA) method for computer graphics (CG) animation videos. First, we extract features in terms of spatiotemporal information and its visual perception from the videos as inputs of our proposed artificial neural network-based VQA model. Second, to facilitate the video quality evaluation, we apply a convolutional neural network (CNN) in the VQA model to generate weight factors for the input features adaptively according to the different types of CG content in videos. Third, we build a subjective CG video quality database for validation of VQA metrics. Experiments demonstrated that our method achieved superior performance in terms of evaluating the quality of CG animation videos. Both the code and proposed database are publicly available at https://github.com/WeizhiXian/CGVQA. The corresponding newly established database is available at https:// pan.baidu.com/s/1_P2ZNrLzJwZfG6xa6tKnDQ (password: cgvq).

Original language	English
Pages (from-to)	1731-1746
Journal	Information Sciences
Volume	608
Early online date	16 Jul 2022
DOIs	https://doi.org/10.1016/j.ins.2022.07.053
Publication status	Published - Aug 2022
Externally published	Yes

Bibliographical note

This research was supported in part by the National Natural Science Foundation of China under Grant No. 62176027, No. 61876026 and No. 61672443, the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA), the Hong Kong GRF-RGC General Research Fund under Grant No. 11209819 (CityU 9042816) and Grant No. 11203820 (9042598), the General Program of National Natural Science Foundation of Chongqing under Grant cstc2020jcyj msxmX0790, the Fundamental Research Funds for the Central Universities under Grant 2021CDJJMRH-014, the Guangxi Key Laboratory of Cryptography and Information Security under Grant GCIS201905, the Human Resources and Social Security Bureau Project of Chongqing under Grant cx2020073, the Huawei Project under Grant H20210586, the Suzhou Institute of University of Science and Technology of China under Grant H20201528, the Youth Project of Guizhou Education Department under Grant Qian Jiao He KY No. [2017] 359, the University-Level Scientific Research Projects under Grant qnsy2018028, the Guizhou Provincial Education Department Young Science and Technology Talents Development Project under Grant Qian Jiao He KY No. [2020] 210, and the Key Project of Science and Technology Innovation 2030 supported by the Ministry of Science and Technology of China under 2018AAA0101301.

Keywords

Computer graphics animation videos
Convolutional neural network
No reference
Spatiotemporal features
Video quality assessment

Access to Document

10.1016/j.ins.2022.07.053

Cite this

@article{249032369ec24bedb19e3898ae48f2d8,

title = "A content-oriented no-reference perceptual video quality assessment method for computer graphics animation videos",

abstract = "In this paper, we propose a content-oriented no-reference (NR) perceptual video quality assessment (VQA) method for computer graphics (CG) animation videos. First, we extract features in terms of spatiotemporal information and its visual perception from the videos as inputs of our proposed artificial neural network-based VQA model. Second, to facilitate the video quality evaluation, we apply a convolutional neural network (CNN) in the VQA model to generate weight factors for the input features adaptively according to the different types of CG content in videos. Third, we build a subjective CG video quality database for validation of VQA metrics. Experiments demonstrated that our method achieved superior performance in terms of evaluating the quality of CG animation videos. Both the code and proposed database are publicly available at https://github.com/WeizhiXian/CGVQA. The corresponding newly established database is available at https:// pan.baidu.com/s/1_P2ZNrLzJwZfG6xa6tKnDQ (password: cgvq).",

keywords = "Computer graphics animation videos, Convolutional neural network, No reference, Spatiotemporal features, Video quality assessment",

author = "Weizhi XIAN and Mingliang ZHOU and Bin FANG and Sam KWONG",

note = "This research was supported in part by the National Natural Science Foundation of China under Grant No. 62176027, No. 61876026 and No. 61672443, the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA), the Hong Kong GRF-RGC General Research Fund under Grant No. 11209819 (CityU 9042816) and Grant No. 11203820 (9042598), the General Program of National Natural Science Foundation of Chongqing under Grant cstc2020jcyj msxmX0790, the Fundamental Research Funds for the Central Universities under Grant 2021CDJJMRH-014, the Guangxi Key Laboratory of Cryptography and Information Security under Grant GCIS201905, the Human Resources and Social Security Bureau Project of Chongqing under Grant cx2020073, the Huawei Project under Grant H20210586, the Suzhou Institute of University of Science and Technology of China under Grant H20201528, the Youth Project of Guizhou Education Department under Grant Qian Jiao He KY No. [2017] 359, the University-Level Scientific Research Projects under Grant qnsy2018028, the Guizhou Provincial Education Department Young Science and Technology Talents Development Project under Grant Qian Jiao He KY No. [2020] 210, and the Key Project of Science and Technology Innovation 2030 supported by the Ministry of Science and Technology of China under 2018AAA0101301.",

year = "2022",

month = aug,

doi = "10.1016/j.ins.2022.07.053",

language = "English",

volume = "608",

pages = "1731--1746",

journal = "Information Sciences",

issn = "0020-0255",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - A content-oriented no-reference perceptual video quality assessment method for computer graphics animation videos

AU - XIAN, Weizhi

AU - ZHOU, Mingliang

AU - FANG, Bin

AU - KWONG, Sam

N1 - This research was supported in part by the National Natural Science Foundation of China under Grant No. 62176027, No. 61876026 and No. 61672443, the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA), the Hong Kong GRF-RGC General Research Fund under Grant No. 11209819 (CityU 9042816) and Grant No. 11203820 (9042598), the General Program of National Natural Science Foundation of Chongqing under Grant cstc2020jcyj msxmX0790, the Fundamental Research Funds for the Central Universities under Grant 2021CDJJMRH-014, the Guangxi Key Laboratory of Cryptography and Information Security under Grant GCIS201905, the Human Resources and Social Security Bureau Project of Chongqing under Grant cx2020073, the Huawei Project under Grant H20210586, the Suzhou Institute of University of Science and Technology of China under Grant H20201528, the Youth Project of Guizhou Education Department under Grant Qian Jiao He KY No. [2017] 359, the University-Level Scientific Research Projects under Grant qnsy2018028, the Guizhou Provincial Education Department Young Science and Technology Talents Development Project under Grant Qian Jiao He KY No. [2020] 210, and the Key Project of Science and Technology Innovation 2030 supported by the Ministry of Science and Technology of China under 2018AAA0101301.

PY - 2022/8

Y1 - 2022/8

N2 - In this paper, we propose a content-oriented no-reference (NR) perceptual video quality assessment (VQA) method for computer graphics (CG) animation videos. First, we extract features in terms of spatiotemporal information and its visual perception from the videos as inputs of our proposed artificial neural network-based VQA model. Second, to facilitate the video quality evaluation, we apply a convolutional neural network (CNN) in the VQA model to generate weight factors for the input features adaptively according to the different types of CG content in videos. Third, we build a subjective CG video quality database for validation of VQA metrics. Experiments demonstrated that our method achieved superior performance in terms of evaluating the quality of CG animation videos. Both the code and proposed database are publicly available at https://github.com/WeizhiXian/CGVQA. The corresponding newly established database is available at https:// pan.baidu.com/s/1_P2ZNrLzJwZfG6xa6tKnDQ (password: cgvq).

AB - In this paper, we propose a content-oriented no-reference (NR) perceptual video quality assessment (VQA) method for computer graphics (CG) animation videos. First, we extract features in terms of spatiotemporal information and its visual perception from the videos as inputs of our proposed artificial neural network-based VQA model. Second, to facilitate the video quality evaluation, we apply a convolutional neural network (CNN) in the VQA model to generate weight factors for the input features adaptively according to the different types of CG content in videos. Third, we build a subjective CG video quality database for validation of VQA metrics. Experiments demonstrated that our method achieved superior performance in terms of evaluating the quality of CG animation videos. Both the code and proposed database are publicly available at https://github.com/WeizhiXian/CGVQA. The corresponding newly established database is available at https:// pan.baidu.com/s/1_P2ZNrLzJwZfG6xa6tKnDQ (password: cgvq).

KW - Computer graphics animation videos

KW - Convolutional neural network

KW - No reference

KW - Spatiotemporal features

KW - Video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85134679131&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2022.07.053

DO - 10.1016/j.ins.2022.07.053

M3 - Journal Article (refereed)

SN - 0020-0255

VL - 608

SP - 1731

EP - 1746

JO - Information Sciences

JF - Information Sciences

ER -

A content-oriented no-reference perceptual video quality assessment method for computer graphics animation videos

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Adaptive Dynamic Range Enhancement Oriented to High Dynamic Display (面向高動態顯示的自適應動態範圍增強)

Cite this