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

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

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, Ik Hyun Lee, Jaeho Lee, Seongwan Kim, Sharif S M A, Nodirkhuja Khujaev, Roman Tsoy; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6524-6535

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. They gauge the state-of-the-art of blind quality enhancement of compressed image.

Related Material

[pdf]

[bibtex]

@InProceedings{Yang_2024_CVPR, author = {Yang, Ren and Timofte, Radu and Li, Bingchen and Li, Xin and Guo, Mengxi and Zhao, Shijie and Zhang, Li and Chen, Zhibo and Zhang, Dongyang and Arora, Yash and Arora, Aditya and Chen, Yuanbin and Tang, Hui and Wang, Tao and Zhao, Longxuan and Chen, Bin and Tong, Tong and Mo, Qiao and Bao, Jingwei and Hao, Jinhua and Ding, Yukang and Li, Hantang and Sun, Ming and Zhou, Chao and Zhu, Shuyuan and Jin, Zhi and Wang, Wei and Zhan, Dandan and Wu, Jiawei and Wu, Jiahao and Tu, Luwei and An, Hongyu and Zhang, Xinfeng and Yeo, Woon-Ha and Oh, Wang-Taek and Kim, Young-Il and Ryu, Han-Cheol and Sun, Long and Zhen, Mingjun and Pan, Jinshan and Dong, Jiangxin and Tang, Jinhui and Du, Yapeng and Li, Ao and He, Ziyang and Luo, Lei and Zhu, Ce and Yao, Xin and Khowaja, Sunder Ali and Lee, Ik Hyun and Lee, Jaeho and Kim, Seongwan and A, Sharif S M and Khujaev, Nodirkhuja and Tsoy, Roman}, title = {NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6524-6535} }