NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results

Ren Yang; Radu Timofte; Bingchen Li; Xin Li; Mengxi Guo; Shijie Zhao; Li Zhang; Zhibo Chen; Dongyang Zhang; Yash Arora; Aditya Arora; Yuanbin Chen; Hui Tang; Tao Wang; Longxuan Zhao; Bin Chen; Tong Tong; Qiao Mo; Jingwei Bao; Jinhua Hao; Yukang Ding; Hantang Li; Ming Sun; Chao Zhou; Shuyuan Zhu; Zhi Jin; Wei Wang; Dandan Zhan; Jiawei Wu; Jiahao Wu; Luwei Tu; Hongyu An; Xinfeng Zhang; Woon Ha Yeo; Wang Taek Oh; Young Il Kim; Han Cheol Ryu; Long Sun; Mingjun Zhen; Jinshan Pan; Jiangxin Dong; Jinhui Tang; Yapeng Du; Ao Li; Ziyang He; Lei Luo; Ce Zhu; Xin Yao; Sunder Ali Khowaja; I. K.Hyun Lee; Jaeho Lee; Seongwan Kim; S. M.A. Sharif; Nodirkhuja Khujaev; Roman Tsoy

doi:10.1109/CVPRW63382.2024.00652

NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results

Ren Yang
, Radu Timofte
, Bingchen Li
, Xin Li
, Mengxi Guo
, Shijie Zhao
, Li Zhang
, Zhibo Chen
, Dongyang Zhang
, Yash Arora
, Aditya Arora
, Yuanbin Chen
, Hui Tang
, Tao Wang
, Longxuan Zhao
, Bin Chen
, Tong Tong
, Qiao Mo
, Jingwei Bao
, Jinhua Hao

Yukang Ding, Hantang Li, Ming Sun, Chao Zhou, Shuyuan Zhu, Zhi Jin, Wei Wang, Dandan Zhan, Jiawei Wu, Jiahao Wu, Luwei Tu, Hongyu An, Xinfeng Zhang, Woon Ha Yeo, Wang Taek Oh, Young Il Kim, Han Cheol Ryu, Long Sun, Mingjun Zhen, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Yapeng Du, Ao Li, Ziyang He, Lei Luo, Ce Zhu, Xin Yao, Sunder Ali Khowaja, I. K.Hyun Lee, Jaeho Lee, Seongwan Kim, S. M.A. Sharif, Nodirkhuja Khujaev, Roman Tsoy

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

Abstract

This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE 2024, which aims at enhancing the quality of JPEG images which are compressed with unknown quality factor. The challenge requires that the total size of codes and pre-trained model(s) cannot exceed 300 MB, since we encourage solutions for blind enhancement with generalized models, instead of separately training several models for each quality factor. In this report, we summarize the detailed settings of the challenge, the final results, and the solutions proposed by the participants. The challenge has 129 registered participants and received 13 valid submissions. Several teams (including all TOP 3 teams) have publicly released the codes (see Sec. 4). They gauge the state-of-the-art of blind quality enhancement of compressed image.

Original language	English
Title of host publication	Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
Publisher	IEEE Computer Society
Pages	6524-6535
Number of pages	12
ISBN (Electronic)	9798350365474
DOIs	https://doi.org/10.1109/CVPRW63382.2024.00652
Publication status	Published - 2024
Event	2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 - Seattle, United States Duration: 16 Jun 2024 → 22 Jun 2024

Publication series

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

Conference

Conference	2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
Country/Territory	United States
City	Seattle
Period	16/06/24 → 22/06/24

Access to Document

10.1109/CVPRW63382.2024.00652

Cite this

Yang, R., Timofte, R., Li, B., Li, X., Guo, M., Zhao, S., Zhang, L., Chen, Z., Zhang, D., Arora, Y., Arora, A., Chen, Y., Tang, H., Wang, T., Zhao, L., Chen, B., Tong, T., Mo, Q., Bao, J., ... Tsoy, R. (2024). NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results. In Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 (pp. 6524-6535). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW63382.2024.00652

Yang, Ren ; Timofte, Radu ; Li, Bingchen et al. / NTIRE 2024 Challenge on Blind Enhancement of Compressed Image : Methods and Results. Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024. IEEE Computer Society, 2024. pp. 6524-6535 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

@inproceedings{8ac8a998c976435f99bed8c92ad12097,

title = "NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results",

abstract = "This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE 2024, which aims at enhancing the quality of JPEG images which are compressed with unknown quality factor. The challenge requires that the total size of codes and pre-trained model(s) cannot exceed 300 MB, since we encourage solutions for blind enhancement with generalized models, instead of separately training several models for each quality factor. In this report, we summarize the detailed settings of the challenge, the final results, and the solutions proposed by the participants. The challenge has 129 registered participants and received 13 valid submissions. Several teams (including all TOP 3 teams) have publicly released the codes (see Sec. 4). They gauge the state-of-the-art of blind quality enhancement of compressed image.",

author = "Ren Yang and Radu Timofte and Bingchen Li and Xin Li and Mengxi Guo and Shijie Zhao and Li Zhang and Zhibo Chen and Dongyang Zhang and Yash Arora and Aditya Arora and Yuanbin Chen and Hui Tang and Tao Wang and Longxuan Zhao and Bin Chen and Tong Tong and Qiao Mo and Jingwei Bao and Jinhua Hao and Yukang Ding and Hantang Li and Ming Sun and Chao Zhou and Shuyuan Zhu and Zhi Jin and Wei Wang and Dandan Zhan and Jiawei Wu and Jiahao Wu and Luwei Tu and Hongyu An and Xinfeng Zhang and Yeo, \{Woon Ha\} and Oh, \{Wang Taek\} and Kim, \{Young Il\} and Ryu, \{Han Cheol\} and Long Sun and Mingjun Zhen and Jinshan Pan and Jiangxin Dong and Jinhui Tang and Yapeng Du and Ao Li and Ziyang He and Lei Luo and Ce Zhu and Xin Yao and Khowaja, \{Sunder Ali\} and Lee, \{I. K.Hyun\} and Jaeho Lee and Seongwan Kim and Sharif, \{S. M.A.\} and Nodirkhuja Khujaev and Roman Tsoy",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 ; Conference date: 16-06-2024 Through 22-06-2024",

year = "2024",

doi = "10.1109/CVPRW63382.2024.00652",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "6524--6535",

booktitle = "Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024",

address = "United States",

}

Yang, R, Timofte, R, Li, B, Li, X, Guo, M, Zhao, S, Zhang, L, Chen, Z, Zhang, D, Arora, Y, Arora, A, Chen, Y, Tang, H, Wang, T, Zhao, L, Chen, B, Tong, T, Mo, Q, Bao, J, Hao, J, Ding, Y, Li, H, Sun, M, Zhou, C, Zhu, S, Jin, Z, Wang, W, Zhan, D, Wu, J, Wu, J, Tu, L, An, H, Zhang, X, Yeo, WH, Oh, WT, Kim, YI, Ryu, HC, Sun, L, Zhen, M, Pan, J, Dong, J, Tang, J, Du, Y, Li, A, He, Z, Luo, L, Zhu, C, Yao, X, Khowaja, SA, Lee, IKH, Lee, J, Kim, S, Sharif, SMA, Khujaev, N & Tsoy, R 2024, NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results. in Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 6524-6535, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024, Seattle, United States, 16/06/24. https://doi.org/10.1109/CVPRW63382.2024.00652

NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results. / Yang, Ren; Timofte, Radu; Li, Bingchen et al.
Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024. IEEE Computer Society, 2024. p. 6524-6535 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

TY - GEN

T1 - NTIRE 2024 Challenge on Blind Enhancement of Compressed Image

T2 - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024

AU - Yang, Ren

AU - Timofte, Radu

AU - Li, Bingchen

AU - Li, Xin

AU - Guo, Mengxi

AU - Zhao, Shijie

AU - Zhang, Li

AU - Chen, Zhibo

AU - Zhang, Dongyang

AU - Arora, Yash

AU - Arora, Aditya

AU - Chen, Yuanbin

AU - Tang, Hui

AU - Wang, Tao

AU - Zhao, Longxuan

AU - Chen, Bin

AU - Tong, Tong

AU - Mo, Qiao

AU - Bao, Jingwei

AU - Hao, Jinhua

AU - Ding, Yukang

AU - Li, Hantang

AU - Sun, Ming

AU - Zhou, Chao

AU - Zhu, Shuyuan

AU - Jin, Zhi

AU - Wang, Wei

AU - Zhan, Dandan

AU - Wu, Jiawei

AU - Wu, Jiahao

AU - Tu, Luwei

AU - An, Hongyu

AU - Zhang, Xinfeng

AU - Yeo, Woon Ha

AU - Oh, Wang Taek

AU - Kim, Young Il

AU - Ryu, Han Cheol

AU - Sun, Long

AU - Zhen, Mingjun

AU - Pan, Jinshan

AU - Dong, Jiangxin

AU - Tang, Jinhui

AU - Du, Yapeng

AU - Li, Ao

AU - He, Ziyang

AU - Luo, Lei

AU - Zhu, Ce

AU - Yao, Xin

AU - Khowaja, Sunder Ali

AU - Lee, I. K.Hyun

AU - Lee, Jaeho

AU - Kim, Seongwan

AU - Sharif, S. M.A.

AU - Khujaev, Nodirkhuja

AU - Tsoy, Roman

PY - 2024

Y1 - 2024

N2 - This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE 2024, which aims at enhancing the quality of JPEG images which are compressed with unknown quality factor. The challenge requires that the total size of codes and pre-trained model(s) cannot exceed 300 MB, since we encourage solutions for blind enhancement with generalized models, instead of separately training several models for each quality factor. In this report, we summarize the detailed settings of the challenge, the final results, and the solutions proposed by the participants. The challenge has 129 registered participants and received 13 valid submissions. Several teams (including all TOP 3 teams) have publicly released the codes (see Sec. 4). They gauge the state-of-the-art of blind quality enhancement of compressed image.

AB - This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE 2024, which aims at enhancing the quality of JPEG images which are compressed with unknown quality factor. The challenge requires that the total size of codes and pre-trained model(s) cannot exceed 300 MB, since we encourage solutions for blind enhancement with generalized models, instead of separately training several models for each quality factor. In this report, we summarize the detailed settings of the challenge, the final results, and the solutions proposed by the participants. The challenge has 129 registered participants and received 13 valid submissions. Several teams (including all TOP 3 teams) have publicly released the codes (see Sec. 4). They gauge the state-of-the-art of blind quality enhancement of compressed image.

UR - https://www.scopus.com/pages/publications/85191690820

U2 - 10.1109/CVPRW63382.2024.00652

DO - 10.1109/CVPRW63382.2024.00652

M3 - Conference contribution

AN - SCOPUS:85191690820

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

SP - 6524

EP - 6535

BT - Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024

PB - IEEE Computer Society

Y2 - 16 June 2024 through 22 June 2024

ER -

Yang R, Timofte R, Li B, Li X, Guo M, Zhao S et al. NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results. In Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024. IEEE Computer Society. 2024. p. 6524-6535. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW63382.2024.00652

NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this