NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results

Ren Yang; Radu Timofte; Jing Liu; Yi Xu; Xinjian Zhang; Minyi Zhao; Shuigeng Zhou; Kelvin C.K. Chan; Shangchen Zhou; Xiangyu Xu; Chen Change Loy; Xin Li; Fanglong Liu; He Zheng; Lielin Jiang; Qi Zhang; Dongliang He; Fu Li; Qingqing Dang; Yibin Huang; Matteo Maggioni; Zhongqian Fu; Shuai Xiao; Cheng Li; Thomas Tanay; Fenglong Song; Wentao Chao; Qiang Guo; Yan Liu; Jiang Li; Xiaochao Qu; Dewang Hou; Jiayu Yang; Lyn Jiang; Di You; Zhenyu Zhang; Chong Mou; Iaroslav Koshelev; Pavel Ostyakov; Andrey Somov; Jia Hao; Xueyi Zou; Shijie Zhao; Xiaopeng Sun; Yiting Liao; Yuanzhi Zhang; Qing Wang; Gen Zhan; Mengxi Guo; Junlin Li; Ming Lu; Zhan Ma; Pablo Navarrete Michelini; Hai Wang; Yiyun Chen; Jingyu Guo; Liliang Zhang; Wenming Yang; Sijung Kim; Syehoon Oh; Yucong Wang; Minjie Cai; Wei Hao; Kangdi Shi; Liangyan Li; Jun Chen; Wei Gao; Wang Liu; Xiaoyu Zhang; Linjie Zhou; Sixin Lin; Ru Wang

doi:10.1109/CVPRW53098.2021.00075

NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results

Ren Yang, Radu Timofte, Jing Liu, Yi Xu, Xinjian Zhang, Minyi Zhao, Shuigeng Zhou, Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy, Xin Li, Fanglong Liu, He Zheng, Lielin Jiang, Qi Zhang, Dongliang He, Fu Li, Qingqing Dang, Yibin HuangMatteo Maggioni, Zhongqian Fu, Shuai Xiao, Cheng Li, Thomas Tanay, Fenglong Song, Wentao Chao, Qiang Guo, Yan Liu, Jiang Li, Xiaochao Qu, Dewang Hou, Jiayu Yang, Lyn Jiang, Di You, Zhenyu Zhang, Chong Mou, Iaroslav Koshelev, Pavel Ostyakov, Andrey Somov, Jia Hao, Xueyi Zou, Shijie Zhao, Xiaopeng Sun, Yiting Liao, Yuanzhi Zhang, Qing Wang, Gen Zhan, Mengxi Guo, Junlin Li, Ming Lu, Zhan Ma, Pablo Navarrete Michelini, Hai Wang, Yiyun Chen, Jingyu Guo, Liliang Zhang, Wenming Yang, Sijung Kim, Syehoon Oh, Yucong Wang, Minjie Cai, Wei Hao, Kangdi Shi, Liangyan Li, Jun Chen, Wei Gao, Wang Liu, Xiaoyu Zhang, Linjie Zhou, Sixin Lin, Ru Wang

College of Computing and Data Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

33 Citations (Scopus)

Abstract

This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is de-signed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

Original language	English
Title of host publication	Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Publisher	IEEE Computer Society
Pages	647-666
Number of pages	20
ISBN (Electronic)	9781665448994
DOIs	https://doi.org/10.1109/CVPRW53098.2021.00075
Publication status	Published - Jun 2021
Event	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, United States Duration: Jun 19 2021 → Jun 25 2021

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Country/Territory	United States
City	Virtual, Online
Period	6/19/21 → 6/25/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

ASJC Scopus Subject Areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW53098.2021.00075

Cite this

Yang, R., Timofte, R., Liu, J., Xu, Y., Zhang, X., Zhao, M., Zhou, S., Chan, K. C. K., Zhou, S., Xu, X., Loy, C. C., Li, X., Liu, F., Zheng, H., Jiang, L., Zhang, Q., He, D., Li, F., Dang, Q., ... Wang, R. (2021). NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results. In Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 (pp. 647-666). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW53098.2021.00075

@inproceedings{a680bf5e2b874f0382327c2efb6bead6,

title = "NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results",

abstract = "This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is de-signed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21\_VEnh",

author = "Ren Yang and Radu Timofte and Jing Liu and Yi Xu and Xinjian Zhang and Minyi Zhao and Shuigeng Zhou and Chan, \{Kelvin C.K.\} and Shangchen Zhou and Xiangyu Xu and Loy, \{Chen Change\} and Xin Li and Fanglong Liu and He Zheng and Lielin Jiang and Qi Zhang and Dongliang He and Fu Li and Qingqing Dang and Yibin Huang and Matteo Maggioni and Zhongqian Fu and Shuai Xiao and Cheng Li and Thomas Tanay and Fenglong Song and Wentao Chao and Qiang Guo and Yan Liu and Jiang Li and Xiaochao Qu and Dewang Hou and Jiayu Yang and Lyn Jiang and Di You and Zhenyu Zhang and Chong Mou and Iaroslav Koshelev and Pavel Ostyakov and Andrey Somov and Jia Hao and Xueyi Zou and Shijie Zhao and Xiaopeng Sun and Yiting Liao and Yuanzhi Zhang and Qing Wang and Gen Zhan and Mengxi Guo and Junlin Li and Ming Lu and Zhan Ma and Michelini, \{Pablo Navarrete\} and Hai Wang and Yiyun Chen and Jingyu Guo and Liliang Zhang and Wenming Yang and Sijung Kim and Syehoon Oh and Yucong Wang and Minjie Cai and Wei Hao and Kangdi Shi and Liangyan Li and Jun Chen and Wei Gao and Wang Liu and Xiaoyu Zhang and Linjie Zhou and Sixin Lin and Ru Wang",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 ; Conference date: 19-06-2021 Through 25-06-2021",

year = "2021",

month = jun,

doi = "10.1109/CVPRW53098.2021.00075",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "647--666",

booktitle = "Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021",

address = "United States",

}

Yang, R, Timofte, R, Liu, J, Xu, Y, Zhang, X, Zhao, M, Zhou, S, Chan, KCK, Zhou, S, Xu, X, Loy, CC, Li, X, Liu, F, Zheng, H, Jiang, L, Zhang, Q, He, D, Li, F, Dang, Q, Huang, Y, Maggioni, M, Fu, Z, Xiao, S, Li, C, Tanay, T, Song, F, Chao, W, Guo, Q, Liu, Y, Li, J, Qu, X, Hou, D, Yang, J, Jiang, L, You, D, Zhang, Z, Mou, C, Koshelev, I, Ostyakov, P, Somov, A, Hao, J, Zou, X, Zhao, S, Sun, X, Liao, Y, Zhang, Y, Wang, Q, Zhan, G, Guo, M, Li, J, Lu, M, Ma, Z, Michelini, PN, Wang, H, Chen, Y, Guo, J, Zhang, L, Yang, W, Kim, S, Oh, S, Wang, Y, Cai, M, Hao, W, Shi, K, Li, L, Chen, J, Gao, W, Liu, W, Zhang, X, Zhou, L, Lin, S & Wang, R 2021, NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results. in Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 647-666, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021, Virtual, Online, United States, 6/19/21. https://doi.org/10.1109/CVPRW53098.2021.00075

NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results. / Yang, Ren; Timofte, Radu; Liu, Jing et al.
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society, 2021. p. 647-666 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - NTIRE 2021 challenge on quality enhancement of compressed video

T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021

AU - Yang, Ren

AU - Timofte, Radu

AU - Liu, Jing

AU - Xu, Yi

AU - Zhang, Xinjian

AU - Zhao, Minyi

AU - Zhou, Shuigeng

AU - Chan, Kelvin C.K.

AU - Zhou, Shangchen

AU - Xu, Xiangyu

AU - Loy, Chen Change

AU - Li, Xin

AU - Liu, Fanglong

AU - Zheng, He

AU - Jiang, Lielin

AU - Zhang, Qi

AU - He, Dongliang

AU - Li, Fu

AU - Dang, Qingqing

AU - Huang, Yibin

AU - Maggioni, Matteo

AU - Fu, Zhongqian

AU - Xiao, Shuai

AU - Li, Cheng

AU - Tanay, Thomas

AU - Song, Fenglong

AU - Chao, Wentao

AU - Guo, Qiang

AU - Liu, Yan

AU - Li, Jiang

AU - Qu, Xiaochao

AU - Hou, Dewang

AU - Yang, Jiayu

AU - Jiang, Lyn

AU - You, Di

AU - Zhang, Zhenyu

AU - Mou, Chong

AU - Koshelev, Iaroslav

AU - Ostyakov, Pavel

AU - Somov, Andrey

AU - Hao, Jia

AU - Zou, Xueyi

AU - Zhao, Shijie

AU - Sun, Xiaopeng

AU - Liao, Yiting

AU - Zhang, Yuanzhi

AU - Wang, Qing

AU - Zhan, Gen

AU - Guo, Mengxi

AU - Li, Junlin

AU - Lu, Ming

AU - Ma, Zhan

AU - Michelini, Pablo Navarrete

AU - Wang, Hai

AU - Chen, Yiyun

AU - Guo, Jingyu

AU - Zhang, Liliang

AU - Yang, Wenming

AU - Kim, Sijung

AU - Oh, Syehoon

AU - Wang, Yucong

AU - Cai, Minjie

AU - Hao, Wei

AU - Shi, Kangdi

AU - Li, Liangyan

AU - Chen, Jun

AU - Gao, Wei

AU - Liu, Wang

AU - Zhang, Xiaoyu

AU - Zhou, Linjie

AU - Lin, Sixin

AU - Wang, Ru

PY - 2021/6

Y1 - 2021/6

N2 - This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is de-signed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

AB - This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is de-signed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

UR - http://www.scopus.com/inward/record.url?scp=85106108707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85106108707&partnerID=8YFLogxK

U2 - 10.1109/CVPRW53098.2021.00075

DO - 10.1109/CVPRW53098.2021.00075

M3 - Conference contribution

AN - SCOPUS:85106108707

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 647

EP - 666

BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021

PB - IEEE Computer Society

Y2 - 19 June 2021 through 25 June 2021

ER -

Yang R, Timofte R, Liu J, Xu Y, Zhang X, Zhao M et al. NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results. In Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society. 2021. p. 647-666. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW53098.2021.00075

NTIRE 2021 challenge on quality enhancement of compressed video: Methods and results

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Access to Document

Other files and links

Cite this