-
[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} }
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. They gauge the state-of-the-art of blind quality enhancement of compressed image.
Related Material