학술논문
NTIRE 2022 Challenge on Perceptual Image Quality Assessment
Document Type
Conference
Author
Gu, Jinjin; Cai, Haoming; Dong, Chao; Ren, Jimmy S.; Timofte, Radu; Gong, Yuan; Lao, Shanshan; Shi, Shuwei; Wang, Jiahao; Yang, Sidi; Wu, Tianhe; Xia, Weihao; Yang, Yujiu; Cao, Mingdeng; Heng, Cong; Fu, Lingzhi; Zhang, Rongyu; Zhang, Yusheng; Wang, Hao; Song, Hongjian; Wang, Jing; Fan, Haotian; Hou, Xiaoxia; Sun, Ming; Li, Mading; Zhao, Kai; Yuan, Kun; Kong, Zishang; Wu, Mingda; Zheng, Chuanchuan; Conde, Marcos V.; Burchi, Maxime; Feng, Longtao; Zhang, Tao; Li, Yang; Xu, Jingwen; Wang, Haiqiang; Liao, Yiting; Li, Junlin; Xu, Kele; Sun, Tao; Xiong, Yunsheng; Keshari, Abhisek; Komal, Komal; Thakur, Sadbhawana; Jakhetiya, Vinit; Subudhi, Badri N; Yang, Hao-Hsiang; Chang, Hua-En; Huang, Zhi-Kai; Chen, Wei-Ting; Kuo, Sy-Yen; Dutta, Saikat; Das, Sourya Dipta; Shah, Nisarg A.; Tiwari, Anil Kumar
Source
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) CVPRW Computer Vision and Pattern Recognition Workshops (CVPRW), 2022 IEEE/CVF Conference on. :950-966 Jun, 2022
Subject
Language
ISSN
2160-7516
Abstract
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022. This challenge is held to address the emerging challenge of IQA by perceptual image processing algorithms. The output images of these algorithms have completely different characteristics from traditional distortions and are included in the PIPAL dataset used in this challenge. This challenge is divided into two tracks, a full-reference IQA track similar to the previous NTIRE IQA challenge and a new track that focuses on the no-reference IQA methods. The challenge has 192 and 179 registered participants for two tracks. In the final testing stage, 7 and 8 participating teams submitted their models and fact sheets. Almost all of them have achieved better results than existing IQA methods, and the winning method can demonstrate state-of-the-art performance.